diff --git a/packages/kbot/dist-in/data/openai_models.json b/packages/kbot/dist-in/data/openai_models.json
index f0870d6b..b66340cf 100644
--- a/packages/kbot/dist-in/data/openai_models.json
+++ b/packages/kbot/dist-in/data/openai_models.json
@@ -1,5 +1,5 @@
{
- "timestamp": 1760432036753,
+ "timestamp": 1766607018996,
"models": [
{
"id": "gpt-4-0613",
@@ -20,33 +20,33 @@
"owned_by": "openai"
},
{
- "id": "sora-2-pro",
+ "id": "chatgpt-image-latest",
"object": "model",
- "created": 1759708663,
+ "created": 1765925279,
"owned_by": "system"
},
{
- "id": "gpt-audio-mini-2025-10-06",
+ "id": "gpt-4o-mini-tts-2025-03-20",
"object": "model",
- "created": 1759512137,
+ "created": 1765610731,
"owned_by": "system"
},
{
- "id": "gpt-realtime-mini",
+ "id": "gpt-4o-mini-tts-2025-12-15",
"object": "model",
- "created": 1759517133,
+ "created": 1765610837,
"owned_by": "system"
},
{
- "id": "gpt-realtime-mini-2025-10-06",
+ "id": "gpt-realtime-mini-2025-12-15",
"object": "model",
- "created": 1759517175,
+ "created": 1765612007,
"owned_by": "system"
},
{
- "id": "sora-2",
+ "id": "gpt-audio-mini-2025-12-15",
"object": "model",
- "created": 1759708615,
+ "created": 1765760008,
"owned_by": "system"
},
{
@@ -193,30 +193,6 @@
"created": 1723515131,
"owned_by": "system"
},
- {
- "id": "o1-mini-2024-09-12",
- "object": "model",
- "created": 1725648979,
- "owned_by": "system"
- },
- {
- "id": "o1-mini",
- "object": "model",
- "created": 1725649008,
- "owned_by": "system"
- },
- {
- "id": "gpt-4o-realtime-preview-2024-10-01",
- "object": "model",
- "created": 1727131766,
- "owned_by": "system"
- },
- {
- "id": "gpt-4o-audio-preview-2024-10-01",
- "object": "model",
- "created": 1727389042,
- "owned_by": "system"
- },
{
"id": "gpt-4o-audio-preview",
"object": "model",
@@ -451,6 +427,12 @@
"created": 1749685485,
"owned_by": "system"
},
+ {
+ "id": "gpt-4o-transcribe-diarize",
+ "object": "model",
+ "created": 1750798887,
+ "owned_by": "system"
+ },
{
"id": "o4-mini-deep-research-2025-06-26",
"object": "model",
@@ -553,6 +535,132 @@
"created": 1759512027,
"owned_by": "system"
},
+ {
+ "id": "gpt-audio-mini-2025-10-06",
+ "object": "model",
+ "created": 1759512137,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5-search-api",
+ "object": "model",
+ "created": 1759514629,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-realtime-mini",
+ "object": "model",
+ "created": 1759517133,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-realtime-mini-2025-10-06",
+ "object": "model",
+ "created": 1759517175,
+ "owned_by": "system"
+ },
+ {
+ "id": "sora-2",
+ "object": "model",
+ "created": 1759708615,
+ "owned_by": "system"
+ },
+ {
+ "id": "sora-2-pro",
+ "object": "model",
+ "created": 1759708663,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5-search-api-2025-10-14",
+ "object": "model",
+ "created": 1760043960,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.1-chat-latest",
+ "object": "model",
+ "created": 1762547951,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.1-2025-11-13",
+ "object": "model",
+ "created": 1762800353,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.1",
+ "object": "model",
+ "created": 1762800673,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.1-codex",
+ "object": "model",
+ "created": 1762988221,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.1-codex-mini",
+ "object": "model",
+ "created": 1763007109,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.1-codex-max",
+ "object": "model",
+ "created": 1763671532,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-image-1.5",
+ "object": "model",
+ "created": 1764030620,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.2-2025-12-11",
+ "object": "model",
+ "created": 1765313028,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.2",
+ "object": "model",
+ "created": 1765313051,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.2-pro-2025-12-11",
+ "object": "model",
+ "created": 1765343959,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.2-pro",
+ "object": "model",
+ "created": 1765343983,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-5.2-chat-latest",
+ "object": "model",
+ "created": 1765344352,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-4o-mini-transcribe-2025-12-15",
+ "object": "model",
+ "created": 1765610407,
+ "owned_by": "system"
+ },
+ {
+ "id": "gpt-4o-mini-transcribe-2025-03-20",
+ "object": "model",
+ "created": 1765610545,
+ "owned_by": "system"
+ },
{
"id": "gpt-3.5-turbo-16k",
"object": "model",
diff --git a/packages/kbot/dist-in/data/openrouter_models.json b/packages/kbot/dist-in/data/openrouter_models.json
index 73d129b6..9bb3cc75 100644
--- a/packages/kbot/dist-in/data/openrouter_models.json
+++ b/packages/kbot/dist-in/data/openrouter_models.json
@@ -1,14 +1,803 @@
{
- "timestamp": 1760432037245,
+ "timestamp": 1766607019100,
"models": [
{
- "id": "inclusionai/ling-1t",
- "canonical_slug": "inclusionai/ling-1t",
- "hugging_face_id": "inclusionAI/Ling-1T",
- "name": "inclusionAI: Ling-1T",
- "created": 1760316076,
- "description": "Ling-1T is a trillion-parameter open-weight large language model developed by inclusionAI and released under the MIT license. It represents the first flagship non-thinking model in the Ling 2.0 series, built around a sparse-activation architecture with roughly 50 billion active parameters per token. The model supports up to 128 K tokens of context and emphasizes efficient reasoning through an “Evolutionary Chain-of-Thought (Evo-CoT)” training strategy.\n\nPre-trained on more than 20 trillion reasoning-dense tokens, Ling-1T achieves strong results across code generation, mathematics, and logical reasoning benchmarks while maintaining high inference efficiency. It employs FP8 mixed-precision training, MoE routing with QK normalization, and MTP layers for compositional reasoning stability. The model also introduces LPO (Linguistics-unit Policy Optimization) for post-training alignment, enhancing sentence-level semantic control.\n\nLing-1T can perform complex text generation, multilingual reasoning, and front-end code synthesis with a focus on both functionality and aesthetics.",
- "context_length": 131072,
+ "id": "bytedance-seed/seed-1.6-flash",
+ "canonical_slug": "bytedance-seed/seed-1.6-flash-20250625",
+ "hugging_face_id": "",
+ "name": "ByteDance Seed: Seed 1.6 Flash",
+ "created": 1766505011,
+ "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000075",
+ "completion": "0.0000003",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 16384,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "bytedance-seed/seed-1.6",
+ "canonical_slug": "bytedance-seed/seed-1.6-20250625",
+ "hugging_face_id": "",
+ "name": "ByteDance Seed: Seed 1.6",
+ "created": 1766504997,
+ "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000025",
+ "completion": "0.000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 32768,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "minimax/minimax-m2.1",
+ "canonical_slug": "minimax/minimax-m2.1",
+ "hugging_face_id": "MiniMaxAI/MiniMax-M2.1",
+ "name": "MiniMax: MiniMax M2.1",
+ "created": 1766454997,
+ "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.\n\nCompared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).",
+ "context_length": 204800,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000003",
+ "completion": "0.0000012",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000003",
+ "input_cache_write": "0.000000375"
+ },
+ "top_provider": {
+ "context_length": 204800,
+ "max_completion_tokens": 131072,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 0.9,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "z-ai/glm-4.7",
+ "canonical_slug": "z-ai/glm-4.7-20251222",
+ "hugging_face_id": "zai-org/GLM-4.7",
+ "name": "Z.AI: GLM 4.7",
+ "created": 1766378014,
+ "description": "GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.",
+ "context_length": 202752,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000004",
+ "completion": "0.0000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 202752,
+ "max_completion_tokens": 65535,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "google/gemini-3-flash-preview",
+ "canonical_slug": "google/gemini-3-flash-preview-20251217",
+ "hugging_face_id": "",
+ "name": "Google: Gemini 3 Flash Preview",
+ "created": 1765987078,
+ "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.",
+ "context_length": 1048576,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image",
+ "file",
+ "audio",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Gemini",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000005",
+ "completion": "0.000003",
+ "request": "0",
+ "image": "0",
+ "audio": "0.000001",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000005"
+ },
+ "top_provider": {
+ "context_length": 1048576,
+ "max_completion_tokens": 65535,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/mistral-small-creative",
+ "canonical_slug": "mistralai/mistral-small-creative-20251216",
+ "hugging_face_id": null,
+ "name": "Mistral: Mistral Small Creative",
+ "created": 1765908653,
+ "description": "Mistral Small Creative is an experimental small model designed for creative writing, narrative generation, roleplay and character-driven dialogue, general-purpose instruction following, and conversational agents.",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000001",
+ "completion": "0.0000003",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": 0.3,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "allenai/olmo-3.1-32b-think:free",
+ "canonical_slug": "allenai/olmo-3.1-32b-think-20251215",
+ "hugging_face_id": "allenai/Olmo-3.1-32B-Think",
+ "name": "AllenAI: Olmo 3.1 32B Think (free)",
+ "created": 1765907719,
+ "description": "Olmo 3.1 32B Think is a large-scale, 32-billion-parameter model designed for deep reasoning, complex multi-step logic, and advanced instruction following. Building on the Olmo 3 series, version 3.1 delivers refined reasoning behavior and stronger performance across demanding evaluations and nuanced conversational tasks. Developed by Ai2 under the Apache 2.0 license, Olmo 3.1 32B Think continues the Olmo initiative’s commitment to openness, providing full transparency across model weights, code, and training methodology.",
+ "context_length": 65536,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 65536,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.6,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "xiaomi/mimo-v2-flash:free",
+ "canonical_slug": "xiaomi/mimo-v2-flash-20251210",
+ "hugging_face_id": "XiaomiMiMo/MiMo-V2-Flash",
+ "name": "Xiaomi: MiMo-V2-Flash (free)",
+ "created": 1765731308,
+ "description": "MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.\n\nNote: when integrating with agentic tools such as Claude Code, Cline, or Roo Code, **turn off reasoning mode** for the best and fastest performance—this model is deeply optimized for this scenario.\n\nUsers can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config).",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "response_format",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "nvidia/nemotron-3-nano-30b-a3b:free",
+ "canonical_slug": "nvidia/nemotron-3-nano-30b-a3b",
+ "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
+ "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)",
+ "created": 1765731275,
+ "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.\n\nThe model is fully open with open-weights, datasets and recipes so developers can easily\ncustomize, optimize, and deploy the model on their infrastructure for maximum privacy and\nsecurity.\n\nNote: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.",
+ "context_length": 256000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 256000,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "seed",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "nvidia/nemotron-3-nano-30b-a3b",
+ "canonical_slug": "nvidia/nemotron-3-nano-30b-a3b",
+ "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
+ "name": "NVIDIA: Nemotron 3 Nano 30B A3B",
+ "created": 1765731275,
+ "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.\n\nThe model is fully open with open-weights, datasets and recipes so developers can easily\ncustomize, optimize, and deploy the model on their infrastructure for maximum privacy and\nsecurity.\n\nNote: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000006",
+ "completion": "0.00000024",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 262144,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.2-chat",
+ "canonical_slug": "openai/gpt-5.2-chat-20251211",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.2 Chat",
+ "created": 1765389783,
+ "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.2 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.",
+ "context_length": 128000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "file",
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000175",
+ "completion": "0.000014",
+ "request": "0",
+ "image": "0",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000175"
+ },
+ "top_provider": {
+ "context_length": 128000,
+ "max_completion_tokens": 16384,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "max_tokens",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.2-pro",
+ "canonical_slug": "openai/gpt-5.2-pro-20251211",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.2 Pro",
+ "created": 1765389780,
+ "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "file"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000021",
+ "completion": "0.000168",
+ "request": "0",
+ "image": "0",
+ "web_search": "0.01",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.2",
+ "canonical_slug": "openai/gpt-5.2-20251211",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.2",
+ "created": 1765389775,
+ "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "file",
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000175",
+ "completion": "0.000014",
+ "request": "0",
+ "image": "0",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000175"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/devstral-2512:free",
+ "canonical_slug": "mistralai/devstral-2512",
+ "hugging_face_id": "mistralai/Devstral-2-123B-Instruct-2512",
+ "name": "Mistral: Devstral 2 2512 (free)",
+ "created": 1765285419,
+ "description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.\n\nDevstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/devstral-2512",
+ "canonical_slug": "mistralai/devstral-2512",
+ "hugging_face_id": "mistralai/Devstral-2-123B-Instruct-2512",
+ "name": "Mistral: Devstral 2 2512",
+ "created": 1765285419,
+ "description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.\n\nDevstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000005",
+ "completion": "0.00000022",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "relace/relace-search",
+ "canonical_slug": "relace/relace-search-20251208",
+ "hugging_face_id": null,
+ "name": "Relace: Relace Search",
+ "created": 1765213560,
+ "description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. \n\nIn contrast to RAG, relace-search performs agentic multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an \"oracle\" coding agent, who orchestrates/performs the rest of the coding task.\n\nTo use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the [Relace documentation](https://docs.relace.ai/docs/fast-agentic-search/agent).",
+ "context_length": 256000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -26,8 +815,630 @@
"request": "0",
"image": "0",
"web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0"
+ },
+ "top_provider": {
+ "context_length": 256000,
+ "max_completion_tokens": 128000,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "max_tokens",
+ "seed",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "z-ai/glm-4.6v",
+ "canonical_slug": "z-ai/glm-4.6-20251208",
+ "hugging_face_id": "zai-org/GLM-4.6V",
+ "name": "Z.AI: GLM 4.6V",
+ "created": 1765207462,
+ "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000003",
+ "completion": "0.0000009",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000005"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": 24000,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.8,
+ "top_p": 0.6,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "nex-agi/deepseek-v3.1-nex-n1:free",
+ "canonical_slug": "nex-agi/deepseek-v3.1-nex-n1",
+ "hugging_face_id": "nex-agi/DeepSeek-V3.1-Nex-N1",
+ "name": "Nex AGI: DeepSeek V3.1 Nex N1 (free)",
+ "created": 1765204393,
+ "description": "DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. \n\nNex-N1 demonstrates competitive performance across all evaluation scenarios, showing particularly strong results in practical coding and HTML generation tasks.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "DeepSeek",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0",
+ "input_cache_write": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": 163840,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "response_format",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "essentialai/rnj-1-instruct",
+ "canonical_slug": "essentialai/rnj-1-instruct",
+ "hugging_face_id": "EssentialAI/rnj-1-instruct",
+ "name": "EssentialAI: Rnj 1 Instruct",
+ "created": 1765094847,
+ "description": "Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance across multiple programming languages, tool-use workflows, and agentic execution environments (e.g., mini-SWE-agent). ",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000015",
+ "completion": "0.00000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
"internal_reasoning": "0"
},
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openrouter/bodybuilder",
+ "canonical_slug": "openrouter/bodybuilder",
+ "hugging_face_id": "",
+ "name": "Body Builder (beta)",
+ "created": 1764903653,
+ "description": "Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example: \"count to 10 using gemini and opus.\"\n\nThis is useful for creating multi-model requests, custom model routers, or programmatic generation of API calls from human descriptions.\n\n**BETA NOTICE**: Body Builder is in beta, and currently free. Pricing and functionality may change in the future.",
+ "context_length": 128000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Router",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "-1",
+ "completion": "-1"
+ },
+ "top_provider": {
+ "context_length": null,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.1-codex-max",
+ "canonical_slug": "openai/gpt-5.1-codex-max-20251204",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.1-Codex-Max",
+ "created": 1764878934,
+ "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. \nGPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle. ",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000125",
+ "completion": "0.00001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000125"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "amazon/nova-2-lite-v1",
+ "canonical_slug": "amazon/nova-2-lite-v1",
+ "hugging_face_id": "",
+ "name": "Amazon: Nova 2 Lite",
+ "created": 1764696672,
+ "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. \n\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.",
+ "context_length": 1000000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image",
+ "video",
+ "file"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Nova",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000003",
+ "completion": "0.0000025",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 1000000,
+ "max_completion_tokens": 65535,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/ministral-14b-2512",
+ "canonical_slug": "mistralai/ministral-14b-2512",
+ "hugging_face_id": "mistralai/Ministral-3-14B-Instruct-2512",
+ "name": "Mistral: Ministral 3 14B 2512",
+ "created": 1764681735,
+ "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000002",
+ "completion": "0.0000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/ministral-8b-2512",
+ "canonical_slug": "mistralai/ministral-8b-2512",
+ "hugging_face_id": "mistralai/Ministral-3-8B-Instruct-2512",
+ "name": "Mistral: Ministral 3 8B 2512",
+ "created": 1764681654,
+ "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000015",
+ "completion": "0.00000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/ministral-3b-2512",
+ "canonical_slug": "mistralai/ministral-3b-2512",
+ "hugging_face_id": "mistralai/Ministral-3-3B-Instruct-2512",
+ "name": "Mistral: Ministral 3 3B 2512",
+ "created": 1764681560,
+ "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000001",
+ "completion": "0.0000001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/mistral-large-2512",
+ "canonical_slug": "mistralai/mistral-large-2512",
+ "hugging_face_id": "",
+ "name": "Mistral: Mistral Large 3 2512",
+ "created": 1764624472,
+ "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000005",
+ "completion": "0.0000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.0645,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "arcee-ai/trinity-mini:free",
+ "canonical_slug": "arcee-ai/trinity-mini-20251201",
+ "hugging_face_id": "arcee-ai/Trinity-Mini",
+ "name": "Arcee AI: Trinity Mini (free)",
+ "created": 1764601720,
+ "description": "Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.15,
+ "top_p": 0.75,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "arcee-ai/trinity-mini",
+ "canonical_slug": "arcee-ai/trinity-mini-20251201",
+ "hugging_face_id": "arcee-ai/Trinity-Mini",
+ "name": "Arcee AI: Trinity Mini",
+ "created": 1764601720,
+ "description": "Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000045",
+ "completion": "0.00000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0"
+ },
"top_provider": {
"context_length": 131072,
"max_completion_tokens": 131072,
@@ -36,12 +1447,128 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.15,
+ "top_p": 0.75,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "deepseek/deepseek-v3.2-speciale",
+ "canonical_slug": "deepseek/deepseek-v3.2-speciale-20251201",
+ "hugging_face_id": "deepseek-ai/DeepSeek-V3.2-Speciale",
+ "name": "DeepSeek: DeepSeek V3.2 Speciale",
+ "created": 1764594837,
+ "description": "DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning to push capability beyond the base model. Reported evaluations place Speciale ahead of GPT-5 on difficult reasoning workloads, with proficiency comparable to Gemini-3.0-Pro, while retaining strong coding and tool-use reliability. Like V3.2, it benefits from a large-scale agentic task synthesis pipeline that improves compliance and generalization in interactive environments.",
+ "context_length": 163840,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "DeepSeek",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000027",
+ "completion": "0.00000041",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 163840,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "deepseek/deepseek-v3.2",
+ "canonical_slug": "deepseek/deepseek-v3.2-20251201",
+ "hugging_face_id": "deepseek-ai/DeepSeek-V3.2",
+ "name": "DeepSeek: DeepSeek V3.2",
+ "created": 1764594642,
+ "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.\n\nUsers can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)",
+ "context_length": 163840,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "DeepSeek",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000224",
+ "completion": "0.00000032",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 163840,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
+ "reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
"structured_outputs",
@@ -52,10 +1579,1976 @@
"top_logprobs",
"top_p"
],
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "prime-intellect/intellect-3",
+ "canonical_slug": "prime-intellect/intellect-3-20251126",
+ "hugging_face_id": "PrimeIntellect/INTELLECT-3-FP8",
+ "name": "Prime Intellect: INTELLECT-3",
+ "created": 1764212534,
+ "description": "INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math, code, science, and general reasoning, consistently outperforming many larger frontier models. Designed for strong multi-step problem solving, it maintains high accuracy on structured tasks while remaining efficient at inference thanks to its MoE architecture.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000002",
+ "completion": "0.0000011",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": 131072,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.6,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "tngtech/tng-r1t-chimera:free",
+ "canonical_slug": "tngtech/tng-r1t-chimera",
+ "hugging_face_id": null,
+ "name": "TNG: R1T Chimera (free)",
+ "created": 1764184161,
+ "description": "TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is available exclusively via Chutes and OpenRouter.\n\nCharacteristics and improvements include:\n\nWe think that it has a creative and pleasant personality.\nIt has a preliminary EQ-Bench3 value of about 1305.\nIt is quite a bit more intelligent than the original, albeit a slightly slower.\nIt is much more think-token consistent, i.e. reasoning and answer blocks are properly delineated.\nTool calling is much improved.\n\nTNG Tech, the model authors, ask that users follow the careful guidelines that Microsoft has created for their \"MAI-DS-R1\" DeepSeek-based model. These guidelines are available on Hugging Face (https://huggingface.co/microsoft/MAI-DS-R1).",
+ "context_length": 163840,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 163840,
+ "max_completion_tokens": 163840,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "tngtech/tng-r1t-chimera",
+ "canonical_slug": "tngtech/tng-r1t-chimera",
+ "hugging_face_id": null,
+ "name": "TNG: R1T Chimera",
+ "created": 1764184161,
+ "description": "TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is available exclusively via Chutes and OpenRouter.\n\nCharacteristics and improvements include:\n\nWe think that it has a creative and pleasant personality.\nIt has a preliminary EQ-Bench3 value of about 1305.\nIt is quite a bit more intelligent than the original, albeit a slightly slower.\nIt is much more think-token consistent, i.e. reasoning and answer blocks are properly delineated.\nTool calling is much improved.\n\nTNG Tech, the model authors, ask that users follow the careful guidelines that Microsoft has created for their \"MAI-DS-R1\" DeepSeek-based model. These guidelines are available on Hugging Face (https://huggingface.co/microsoft/MAI-DS-R1).",
+ "context_length": 163840,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000003",
+ "completion": "0.0000012",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 163840,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "anthropic/claude-opus-4.5",
+ "canonical_slug": "anthropic/claude-4.5-opus-20251124",
+ "hugging_face_id": "",
+ "name": "Anthropic: Claude Opus 4.5",
+ "created": 1764010580,
+ "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "file",
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Claude",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000005",
+ "completion": "0.000025",
+ "request": "0",
+ "image": "0",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000005",
+ "input_cache_write": "0.00000625"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 32000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "verbosity"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "allenai/olmo-3-32b-think:free",
+ "canonical_slug": "allenai/olmo-3-32b-think-20251121",
+ "hugging_face_id": "allenai/Olmo-3-32B-Think",
+ "name": "AllenAI: Olmo 3 32B Think (free)",
+ "created": 1763758276,
+ "description": "Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and highly nuanced conversational reasoning. Developed by Ai2 under the Apache 2.0 license, Olmo 3 32B Think embodies the Olmo initiative’s commitment to openness, offering full transparency across weights, code and training methodology.",
+ "context_length": 65536,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 65536,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.6,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "allenai/olmo-3-7b-instruct",
+ "canonical_slug": "allenai/olmo-3-7b-instruct-20251121",
+ "hugging_face_id": "allenai/Olmo-3-7B-Instruct",
+ "name": "AllenAI: Olmo 3 7B Instruct",
+ "created": 1763758273,
+ "description": "Olmo 3 7B Instruct is a supervised instruction-fine-tuned variant of the Olmo 3 7B base model, optimized for instruction-following, question-answering, and natural conversational dialogue. By leveraging high-quality instruction data and an open training pipeline, it delivers strong performance across everyday NLP tasks while remaining accessible and easy to integrate. Developed by Ai2 under the Apache 2.0 license, the model offers a transparent, community-friendly option for instruction-driven applications.",
+ "context_length": 65536,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000001",
+ "completion": "0.0000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 65536,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.6,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "allenai/olmo-3-7b-think",
+ "canonical_slug": "allenai/olmo-3-7b-think-20251121",
+ "hugging_face_id": "allenai/Olmo-3-7B-Think",
+ "name": "AllenAI: Olmo 3 7B Think",
+ "created": 1763758270,
+ "description": "Olmo 3 7B Think is a research-oriented language model in the Olmo family designed for advanced reasoning and instruction-driven tasks. It excels at multi-step problem solving, logical inference, and maintaining coherent conversational context. Developed by Ai2 under the Apache 2.0 license, Olmo 3 7B Think supports transparent, fully open experimentation and provides a lightweight yet capable foundation for academic research and practical NLP workflows.",
+ "context_length": 65536,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000012",
+ "completion": "0.0000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 65536,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.6,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "google/gemini-3-pro-image-preview",
+ "canonical_slug": "google/gemini-3-pro-image-preview-20251120",
+ "hugging_face_id": "",
+ "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)",
+ "created": 1763653797,
+ "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.",
+ "context_length": 65536,
+ "architecture": {
+ "modality": "text+image->text+image",
+ "input_modalities": [
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "image",
+ "text"
+ ],
+ "tokenizer": "Gemini",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000002",
+ "completion": "0.000012",
+ "request": "0",
+ "image": "0.067",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 65536,
+ "max_completion_tokens": 32768,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "temperature",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "x-ai/grok-4.1-fast",
+ "canonical_slug": "x-ai/grok-4.1-fast",
+ "hugging_face_id": "",
+ "name": "xAI: Grok 4.1 Fast",
+ "created": 1763587502,
+ "description": "Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window.\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)",
+ "context_length": 2000000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Grok",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000002",
+ "completion": "0.0000005",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000005"
+ },
+ "top_provider": {
+ "context_length": 2000000,
+ "max_completion_tokens": 30000,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "logprobs",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.7,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "google/gemini-3-pro-preview",
+ "canonical_slug": "google/gemini-3-pro-preview-20251117",
+ "hugging_face_id": "",
+ "name": "Google: Gemini 3 Pro Preview",
+ "created": 1763474668,
+ "description": "Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses.\n\nBuilt for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.",
+ "context_length": 1048576,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image",
+ "file",
+ "audio",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Gemini",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000002",
+ "completion": "0.000012",
+ "request": "0",
+ "image": "0.008256",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000002",
+ "input_cache_write": "0.000002375"
+ },
+ "top_provider": {
+ "context_length": 1048576,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "deepcogito/cogito-v2.1-671b",
+ "canonical_slug": "deepcogito/cogito-v2.1-671b-20251118",
+ "hugging_face_id": "",
+ "name": "Deep Cogito: Cogito v2.1 671B",
+ "created": 1763071233,
+ "description": "Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning to reach state-of-the-art performance on multiple categories (instruction following, coding, longer queries and creative writing). This advanced system demonstrates significant progress toward scalable superintelligence through policy improvement.",
+ "context_length": 128000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000125",
+ "completion": "0.00000125",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 128000,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.1",
+ "canonical_slug": "openai/gpt-5.1-20251113",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.1",
+ "created": 1763060305,
+ "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "file"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000125",
+ "completion": "0.00001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000125"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.1-chat",
+ "canonical_slug": "openai/gpt-5.1-chat-20251113",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.1 Chat",
+ "created": 1763060302,
+ "description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.1 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.\n",
+ "context_length": 128000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "file",
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000125",
+ "completion": "0.00001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000125"
+ },
+ "top_provider": {
+ "context_length": 128000,
+ "max_completion_tokens": 16384,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "max_tokens",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.1-codex",
+ "canonical_slug": "openai/gpt-5.1-codex-20251113",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.1-Codex",
+ "created": 1763060298,
+ "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000125",
+ "completion": "0.00001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000125"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5.1-codex-mini",
+ "canonical_slug": "openai/gpt-5.1-codex-mini-20251113",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5.1-Codex-Mini",
+ "created": 1763057820,
+ "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000025",
+ "completion": "0.000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000025"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 100000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "kwaipilot/kat-coder-pro:free",
+ "canonical_slug": "kwaipilot/kat-coder-pro-v1",
+ "hugging_face_id": "",
+ "name": "Kwaipilot: KAT-Coder-Pro V1 (free)",
+ "created": 1762745912,
+ "description": "KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark. \n\nThe model has been optimized for tool-use capability, multi-turn interaction, instruction following, generalization, and comprehensive capabilities through a multi-stage training process, including mid-training, supervised fine-tuning (SFT), reinforcement fine-tuning (RFT), and scalable agentic RL.",
+ "context_length": 256000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 256000,
+ "max_completion_tokens": 32768,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "moonshotai/kimi-k2-thinking",
+ "canonical_slug": "moonshotai/kimi-k2-thinking-20251106",
+ "hugging_face_id": "moonshotai/Kimi-K2-Thinking",
+ "name": "MoonshotAI: Kimi K2 Thinking",
+ "created": 1762440622,
+ "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\n\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000004",
+ "completion": "0.00000175",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 65535,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "amazon/nova-premier-v1",
+ "canonical_slug": "amazon/nova-premier-v1",
+ "hugging_face_id": "",
+ "name": "Amazon: Nova Premier 1.0",
+ "created": 1761950332,
+ "description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.",
+ "context_length": 1000000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Nova",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000025",
+ "completion": "0.0000125",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000625"
+ },
+ "top_provider": {
+ "context_length": 1000000,
+ "max_completion_tokens": 32000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "max_tokens",
+ "stop",
+ "temperature",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "perplexity/sonar-pro-search",
+ "canonical_slug": "perplexity/sonar-pro-search",
+ "hugging_face_id": "",
+ "name": "Perplexity: Sonar Pro Search",
+ "created": 1761854366,
+ "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform.\n\nSonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000003",
+ "completion": "0.000015",
+ "request": "0.018",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 8000,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p",
+ "web_search_options"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "mistralai/voxtral-small-24b-2507",
+ "canonical_slug": "mistralai/voxtral-small-24b-2507",
+ "hugging_face_id": "mistralai/Voxtral-Small-24B-2507",
+ "name": "Mistral: Voxtral Small 24B 2507",
+ "created": 1761835144,
+ "description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio is priced at $100 per million seconds.",
+ "context_length": 32000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text",
+ "audio"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000001",
+ "completion": "0.0000003",
+ "request": "0",
+ "image": "0",
+ "audio": "0.0001",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32000,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.2,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-oss-safeguard-20b",
+ "canonical_slug": "openai/gpt-oss-safeguard-20b",
+ "hugging_face_id": "openai/gpt-oss-safeguard-20b",
+ "name": "OpenAI: gpt-oss-safeguard-20b",
+ "created": 1761752836,
+ "description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.\n\nLearn more about this model in OpenAI's gpt-oss-safeguard [user guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000075",
+ "completion": "0.0000003",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000037"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "nvidia/nemotron-nano-12b-v2-vl:free",
+ "canonical_slug": "nvidia/nemotron-nano-12b-v2-vl",
+ "hugging_face_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16",
+ "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)",
+ "created": 1761675565,
+ "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.",
+ "context_length": 128000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 128000,
+ "max_completion_tokens": 128000,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "seed",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "nvidia/nemotron-nano-12b-v2-vl",
+ "canonical_slug": "nvidia/nemotron-nano-12b-v2-vl",
+ "hugging_face_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16",
+ "name": "NVIDIA: Nemotron Nano 12B 2 VL",
+ "created": 1761675565,
+ "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "video"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000002",
+ "completion": "0.0000006",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "minimax/minimax-m2",
+ "canonical_slug": "minimax/minimax-m2",
+ "hugging_face_id": "MiniMaxAI/MiniMax-M2",
+ "name": "MiniMax: MiniMax M2",
+ "created": 1761252093,
+ "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.\n\nThe model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.\n\nBenchmarked by [Artificial Analysis](https://artificialanalysis.ai/models/minimax-m2), MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).",
+ "context_length": 196608,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000002",
+ "completion": "0.000001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000003"
+ },
+ "top_provider": {
+ "context_length": 196608,
+ "max_completion_tokens": 131072,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 0.95,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "qwen/qwen3-vl-32b-instruct",
+ "canonical_slug": "qwen/qwen3-vl-32b-instruct",
+ "hugging_face_id": "Qwen/Qwen3-VL-32B-Instruct",
+ "name": "Qwen: Qwen3 VL 32B Instruct",
+ "created": 1761231332,
+ "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text comprehension, enabling fine-grained spatial reasoning, document and scene analysis, and long-horizon video understanding.Robust OCR in 32 languages, and enhanced multimodal fusion through Interleaved-MRoPE and DeepStack architectures. Optimized for agentic interaction and visual tool use, Qwen3-VL-32B delivers state-of-the-art performance for complex real-world multimodal tasks.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Qwen",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000005",
+ "completion": "0.0000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "liquid/lfm2-8b-a1b",
+ "canonical_slug": "liquid/lfm2-8b-a1b",
+ "hugging_face_id": "LiquidAI/LFM2-8B-A1B",
+ "name": "LiquidAI/LFM2-8B-A1B",
+ "created": 1760970984,
+ "description": "Model created via inbox interface",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000005",
+ "completion": "0.0000001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "seed",
+ "stop",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
+ {
+ "id": "liquid/lfm-2.2-6b",
+ "canonical_slug": "liquid/lfm-2.2-6b",
+ "hugging_face_id": "LiquidAI/LFM2-2.6B",
+ "name": "LiquidAI/LFM2-2.6B",
+ "created": 1760970889,
+ "description": "LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000005",
+ "completion": "0.0000001",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "seed",
+ "stop",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "ibm-granite/granite-4.0-h-micro",
+ "canonical_slug": "ibm-granite/granite-4.0-h-micro",
+ "hugging_face_id": "ibm-granite/granite-4.0-h-micro",
+ "name": "IBM: Granite 4.0 Micro",
+ "created": 1760927695,
+ "description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling. ",
+ "context_length": 131000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000017",
+ "completion": "0.00000011",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131000,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "seed",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "deepcogito/cogito-v2-preview-llama-405b",
+ "canonical_slug": "deepcogito/cogito-v2-preview-llama-405b",
+ "hugging_face_id": "deepcogito/cogito-v2-preview-llama-405B",
+ "name": "Deep Cogito: Cogito V2 Preview Llama 405B",
+ "created": 1760709933,
+ "description": "Cogito v2 405B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. It represents a significant step toward frontier intelligence with dense architecture delivering performance competitive with leading closed models. This advanced reasoning system combines policy improvement with massive scale for exceptional capabilities.\n",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Llama3",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000035",
+ "completion": "0.0000035",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5-image-mini",
+ "canonical_slug": "openai/gpt-5-image-mini",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5 Image Mini",
+ "created": 1760624583,
+ "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text+image",
+ "input_modalities": [
+ "file",
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "image",
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000025",
+ "completion": "0.000002",
+ "request": "0",
+ "image": "0.0000025",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000025"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "anthropic/claude-haiku-4.5",
+ "canonical_slug": "anthropic/claude-4.5-haiku-20251001",
+ "hugging_face_id": "",
+ "name": "Anthropic: Claude Haiku 4.5",
+ "created": 1760547638,
+ "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Claude",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000001",
+ "completion": "0.000005",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000001",
+ "input_cache_write": "0.00000125"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 64000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "qwen/qwen3-vl-8b-thinking",
+ "canonical_slug": "qwen/qwen3-vl-8b-thinking",
+ "hugging_face_id": "Qwen/Qwen3-VL-8B-Thinking",
+ "name": "Qwen: Qwen3 VL 8B Thinking",
+ "created": 1760463746,
+ "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and long-context processing (native 256K, expandable to 1M tokens) for tasks such as scientific visual analysis, causal inference, and mathematical reasoning over image or video inputs.\n\nCompared to the Instruct edition, the Thinking version introduces deeper visual-language fusion and deliberate reasoning pathways that improve performance on long-chain logic tasks, STEM problem-solving, and multi-step video understanding. It achieves stronger temporal grounding via Interleaved-MRoPE and timestamp-aware embeddings, while maintaining robust OCR, multilingual comprehension, and text generation on par with large text-only LLMs.",
+ "context_length": 256000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Qwen3",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000018",
+ "completion": "0.0000021",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 256000,
+ "max_completion_tokens": 32768,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 0.95
+ }
+ },
+ {
+ "id": "qwen/qwen3-vl-8b-instruct",
+ "canonical_slug": "qwen/qwen3-vl-8b-instruct",
+ "hugging_face_id": "Qwen/Qwen3-VL-8B-Instruct",
+ "name": "Qwen: Qwen3 VL 8B Instruct",
+ "created": 1760463308,
+ "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization.\n\nThe model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Qwen3",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000064",
+ "completion": "0.0000004",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": 32768,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
"default_parameters": {
"temperature": 0.7,
"top_p": 0.8,
- "frequency_penalty": 1.05
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-5-image",
+ "canonical_slug": "openai/gpt-5-image",
+ "hugging_face_id": "",
+ "name": "OpenAI: GPT-5 Image",
+ "created": 1760447986,
+ "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.",
+ "context_length": 400000,
+ "architecture": {
+ "modality": "text+image->text+image",
+ "input_modalities": [
+ "image",
+ "text",
+ "file"
+ ],
+ "output_modalities": [
+ "image",
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00001",
+ "completion": "0.00001",
+ "request": "0",
+ "image": "0.00001",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000125"
+ },
+ "top_provider": {
+ "context_length": 400000,
+ "max_completion_tokens": 128000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/o3-deep-research",
+ "canonical_slug": "openai/o3-deep-research-2025-06-26",
+ "hugging_face_id": "",
+ "name": "OpenAI: o3 Deep Research",
+ "created": 1760129661,
+ "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "image",
+ "text",
+ "file"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00001",
+ "completion": "0.00004",
+ "request": "0",
+ "image": "0.00765",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000025"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 100000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/o4-mini-deep-research",
+ "canonical_slug": "openai/o4-mini-deep-research-2025-06-26",
+ "hugging_face_id": "",
+ "name": "OpenAI: o4 Mini Deep Research",
+ "created": 1760129642,
+ "description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "file",
+ "image",
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000002",
+ "completion": "0.000008",
+ "request": "0",
+ "image": "0.00153",
+ "web_search": "0.01",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000005"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 100000,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
}
},
{
@@ -130,8 +3623,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000007",
- "completion": "0.00000028",
+ "prompt": "0.000000056",
+ "completion": "0.000000224",
"request": "0",
"image": "0",
"web_search": "0",
@@ -193,7 +3686,7 @@
},
"top_provider": {
"context_length": 32768,
- "max_completion_tokens": 8192,
+ "max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
@@ -218,7 +3711,7 @@
"name": "Qwen: Qwen3 VL 30B A3B Thinking",
"created": 1759794479,
"description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.",
- "context_length": 262144,
+ "context_length": 131072,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
@@ -232,25 +3725,24 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000029",
- "completion": "0.000001",
+ "prompt": "0.00000016",
+ "completion": "0.0000008",
"request": "0",
"image": "0",
"web_search": "0",
- "internal_reasoning": "0"
+ "internal_reasoning": "0",
+ "input_cache_read": "0"
},
"top_provider": {
- "context_length": 262144,
- "max_completion_tokens": 262144,
+ "context_length": 131072,
+ "max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
@@ -290,8 +3782,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000029",
- "completion": "0.000001",
+ "prompt": "0.00000015",
+ "completion": "0.0000006",
"request": "0",
"image": "0",
"web_search": "0",
@@ -299,13 +3791,14 @@
},
"top_provider": {
"context_length": 262144,
- "max_completion_tokens": 262144,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
+ "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -318,11 +3811,13 @@
"tool_choice",
"tools",
"top_k",
+ "top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 0.7,
- "top_p": 0.8
+ "top_p": 0.8,
+ "frequency_penalty": null
}
},
{
@@ -351,7 +3846,7 @@
"completion": "0.00012",
"request": "0",
"image": "0",
- "web_search": "0",
+ "web_search": "0.01",
"internal_reasoning": "0"
},
"top_provider": {
@@ -383,7 +3878,7 @@
"name": "Z.AI: GLM 4.6",
"created": 1759235576,
"description": "Compared with GLM-4.5, this generation brings several key improvements:\n\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.",
- "context_length": 202752,
+ "context_length": 204800,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -396,16 +3891,16 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.0000005",
- "completion": "0.00000175",
+ "prompt": "0.00000039",
+ "completion": "0.0000019",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 202752,
- "max_completion_tokens": 202752,
+ "context_length": 204800,
+ "max_completion_tokens": 204800,
"is_moderated": false
},
"per_request_limits": null,
@@ -437,6 +3932,62 @@
"frequency_penalty": null
}
},
+ {
+ "id": "z-ai/glm-4.6:exacto",
+ "canonical_slug": "z-ai/glm-4.6",
+ "hugging_face_id": "",
+ "name": "Z.AI: GLM 4.6 (exacto)",
+ "created": 1759235576,
+ "description": "Compared with GLM-4.5, this generation brings several key improvements:\n\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.",
+ "context_length": 204800,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000044",
+ "completion": "0.00000176",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 204800,
+ "max_completion_tokens": 131072,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.6,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
{
"id": "anthropic/claude-sonnet-4.5",
"canonical_slug": "anthropic/claude-4.5-sonnet-20250929",
@@ -464,7 +4015,9 @@
"request": "0",
"image": "0",
"web_search": "0",
- "internal_reasoning": "0"
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000003",
+ "input_cache_write": "0.00000375"
},
"top_provider": {
"context_length": 1000000,
@@ -476,7 +4029,9 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "response_format",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
@@ -509,8 +4064,8 @@
"instruct_type": "deepseek-v3.1"
},
"pricing": {
- "prompt": "0.00000027",
- "completion": "0.0000004",
+ "prompt": "0.00000021",
+ "completion": "0.00000032",
"request": "0",
"image": "0",
"web_search": "0",
@@ -518,14 +4073,13 @@
},
"top_provider": {
"context_length": 163840,
- "max_completion_tokens": null,
+ "max_completion_tokens": 65536,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -539,7 +4093,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -588,8 +4141,10 @@
"min_p",
"presence_penalty",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
"top_p"
@@ -606,7 +4161,7 @@
"hugging_face_id": "",
"name": "Relace: Relace Apply 3",
"created": 1758891572,
- "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 7,500 tokens/sec on average.\n\nThe model requires the prompt to be in the following format: \n{instruction}\n{initial_code}\n{edit_snippet}\n\nZero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)",
+ "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average.\n\nThe model requires the prompt to be in the following format: \n{instruction}\n{initial_code}\n{edit_snippet}\n\nZero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)",
"context_length": 256000,
"architecture": {
"modality": "text->text",
@@ -657,7 +4212,9 @@
"input_modalities": [
"image",
"file",
- "text"
+ "text",
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -670,6 +4227,7 @@
"completion": "0.0000025",
"request": "0",
"image": "0.001238",
+ "audio": "0.000001",
"web_search": "0",
"internal_reasoning": "0",
"input_cache_read": "0.000000075",
@@ -711,10 +4269,11 @@
"architecture": {
"modality": "text+image->text",
"input_modalities": [
- "file",
- "image",
"text",
- "audio"
+ "image",
+ "file",
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -776,8 +4335,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000045",
- "completion": "0.0000035",
+ "prompt": "0.0000003",
+ "completion": "0.0000012",
"request": "0",
"image": "0",
"web_search": "0",
@@ -792,9 +4351,7 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
@@ -821,7 +4378,7 @@
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
"created": 1758668687,
"description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.",
- "context_length": 131072,
+ "context_length": 262144,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
@@ -835,7 +4392,7 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.0000003",
+ "prompt": "0.0000002",
"completion": "0.0000012",
"request": "0",
"image": "0",
@@ -843,20 +4400,18 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 131072,
+ "context_length": 262144,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
- "reasoning",
"repetition_penalty",
"response_format",
"seed",
@@ -919,7 +4474,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": 1,
+ "top_p": 1,
+ "frequency_penalty": null
+ }
},
{
"id": "qwen/qwen3-coder-plus",
@@ -1023,6 +4582,64 @@
"frequency_penalty": null
}
},
+ {
+ "id": "deepseek/deepseek-v3.1-terminus:exacto",
+ "canonical_slug": "deepseek/deepseek-v3.1-terminus",
+ "hugging_face_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
+ "name": "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
+ "created": 1758548275,
+ "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. ",
+ "context_length": 163840,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "DeepSeek",
+ "instruct_type": "deepseek-v3.1"
+ },
+ "pricing": {
+ "prompt": "0.00000021",
+ "completion": "0.00000079",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000168"
+ },
+ "top_provider": {
+ "context_length": 163840,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
{
"id": "deepseek/deepseek-v3.1-terminus",
"canonical_slug": "deepseek/deepseek-v3.1-terminus",
@@ -1043,24 +4660,23 @@
"instruct_type": "deepseek-v3.1"
},
"pricing": {
- "prompt": "0.00000023",
- "completion": "0.0000009",
+ "prompt": "0.00000021",
+ "completion": "0.00000079",
"request": "0",
"image": "0",
"web_search": "0",
- "internal_reasoning": "0"
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000168"
},
"top_provider": {
"context_length": 163840,
- "max_completion_tokens": 163840,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -1074,7 +4690,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -1089,7 +4704,7 @@
"hugging_face_id": "",
"name": "xAI: Grok 4 Fast",
"created": 1758240090,
- "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)\n\nPrompts and completions on Grok 4 Fast Free may be used by xAI or OpenRouter to improve future models.",
+ "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast).\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)",
"context_length": 2000000,
"architecture": {
"modality": "text+image->text",
@@ -1173,11 +4788,10 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
+ "include_reasoning",
"max_tokens",
- "min_p",
"presence_penalty",
+ "reasoning",
"repetition_penalty",
"response_format",
"seed",
@@ -1187,7 +4801,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -1303,59 +4916,6 @@
"frequency_penalty": null
}
},
- {
- "id": "arcee-ai/afm-4.5b",
- "canonical_slug": "arcee-ai/afm-4.5b",
- "hugging_face_id": "arcee-ai/AFM-4.5B",
- "name": "Arcee AI: AFM 4.5B",
- "created": 1758040484,
- "description": "AFM-4.5B is a 4.5 billion parameter instruction-tuned language model developed by Arcee AI. The model was pretrained on approximately 8 trillion tokens, including 6.5 trillion tokens of general data and 1.5 trillion tokens with an emphasis on mathematical reasoning and code generation. ",
- "context_length": 65536,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.000000048",
- "completion": "0.00000015",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 65536,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "stop",
- "structured_outputs",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {
- "temperature": null,
- "top_p": null,
- "frequency_penalty": null
- }
- },
{
"id": "opengvlab/internvl3-78b",
"canonical_slug": "opengvlab/internvl3-78b",
@@ -1377,8 +4937,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000007",
- "completion": "0.00000026",
+ "prompt": "0.0000001",
+ "completion": "0.00000039",
"request": "0",
"image": "0",
"web_search": "0",
@@ -1392,10 +4952,7 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
@@ -1404,7 +4961,6 @@
"structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -1416,7 +4972,7 @@
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
"created": 1757612284,
"description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.\n\nThe model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.",
- "context_length": 262144,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -1429,7 +4985,7 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000014",
+ "prompt": "0.00000012",
"completion": "0.0000012",
"request": "0",
"image": "0",
@@ -1437,8 +4993,8 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 262144,
- "max_completion_tokens": null,
+ "context_length": 131072,
+ "max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
@@ -1463,7 +5019,11 @@
"top_logprobs",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
@@ -1485,8 +5045,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.0000001",
- "completion": "0.0000008",
+ "prompt": "0.00000009",
+ "completion": "0.0000011",
"request": "0",
"image": "0",
"web_search": "0",
@@ -1494,14 +5054,13 @@
},
"top_provider": {
"context_length": 262144,
- "max_completion_tokens": 262144,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -1514,61 +5073,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "meituan/longcat-flash-chat:free",
- "canonical_slug": "meituan/longcat-flash-chat",
- "hugging_face_id": "meituan-longcat/LongCat-Flash-Chat",
- "name": "Meituan: LongCat Flash Chat (free)",
- "created": 1757427658,
- "description": "LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce communication overhead and achieve high throughput while maintaining training stability through advanced scaling strategies such as hyperparameter transfer, deterministic computation, and multi-stage optimization.\n\nThis release, LongCat-Flash-Chat, is a non-thinking foundation model optimized for conversational and agentic tasks. It supports long context windows up to 128K tokens and shows competitive performance across reasoning, coding, instruction following, and domain benchmarks, with particular strengths in tool use and complex multi-step interactions.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 131072,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -1593,8 +5097,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000015",
- "completion": "0.00000075",
+ "prompt": "0.0000002",
+ "completion": "0.0000008",
"request": "0",
"image": "0",
"web_search": "0",
@@ -1657,7 +5161,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "qwen/qwen-plus-2025-07-28:thinking",
@@ -1705,7 +5213,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "nvidia/nemotron-nano-9b-v2:free",
@@ -1742,11 +5254,15 @@
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
+ "max_tokens",
"reasoning",
"response_format",
+ "seed",
"structured_outputs",
+ "temperature",
"tool_choice",
- "tools"
+ "tools",
+ "top_p"
],
"default_parameters": {}
},
@@ -1857,6 +5373,111 @@
],
"default_parameters": {}
},
+ {
+ "id": "moonshotai/kimi-k2-0905:exacto",
+ "canonical_slug": "moonshotai/kimi-k2-0905",
+ "hugging_face_id": "moonshotai/Kimi-K2-Instruct-0905",
+ "name": "MoonshotAI: Kimi K2 0905 (exacto)",
+ "created": 1757021147,
+ "description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k.\n\nThis update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Other",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000006",
+ "completion": "0.0000025",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
+ {
+ "id": "deepcogito/cogito-v2-preview-llama-70b",
+ "canonical_slug": "deepcogito/cogito-v2-preview-llama-70b",
+ "hugging_face_id": "deepcogito/cogito-v2-preview-llama-70B",
+ "name": "Deep Cogito: Cogito V2 Preview Llama 70B",
+ "created": 1756831784,
+ "description": "Cogito v2 70B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. Built with iterative policy improvement, it delivers strong performance across reasoning tasks while maintaining efficiency through shorter reasoning chains and improved intuition.",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Llama3",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000088",
+ "completion": "0.00000088",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
{
"id": "deepcogito/cogito-v2-preview-llama-109b-moe",
"canonical_slug": "deepcogito/cogito-v2-preview-llama-109b-moe",
@@ -1909,55 +5530,6 @@
],
"default_parameters": {}
},
- {
- "id": "deepcogito/cogito-v2-preview-deepseek-671b",
- "canonical_slug": "deepcogito/cogito-v2-preview-deepseek-671b",
- "hugging_face_id": "deepcogito/cogito-v2-preview-deepseek-671B-MoE",
- "name": "Deep Cogito: Cogito V2 Preview Deepseek 671B",
- "created": 1756830949,
- "description": "Cogito v2 is a multilingual, instruction-tuned Mixture of Experts (MoE) large language model with 671 billion parameters. It supports both standard and reasoning-based generation modes. The model introduces hybrid reasoning via Iterated Distillation and Amplification (IDA)—an iterative self-improvement strategy designed to scale alignment with general intelligence. Cogito v2 has been optimized for STEM, programming, instruction following, and tool use. It supports 128k context length and offers strong performance in both multilingual and code-heavy environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)",
- "context_length": 163840,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.00000125",
- "completion": "0.00000125",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 163840,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "stepfun-ai/step3",
"canonical_slug": "stepfun-ai/step3",
@@ -2013,7 +5585,7 @@
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
"created": 1756399192,
"description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.\n\nCompared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.",
- "context_length": 262144,
+ "context_length": 32768,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -2026,38 +5598,33 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000008",
- "completion": "0.00000029",
+ "prompt": "0.000000051",
+ "completion": "0.00000034",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 262144,
- "max_completion_tokens": 262144,
+ "context_length": 32768,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
- "stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -2149,20 +5716,18 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -2203,20 +5768,18 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -2252,7 +5815,7 @@
},
"top_provider": {
"context_length": 32768,
- "max_completion_tokens": 8192,
+ "max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
@@ -2270,49 +5833,6 @@
"frequency_penalty": null
}
},
- {
- "id": "deepseek/deepseek-chat-v3.1:free",
- "canonical_slug": "deepseek/deepseek-chat-v3.1",
- "hugging_face_id": "deepseek-ai/DeepSeek-V3.1",
- "name": "DeepSeek: DeepSeek V3.1 (free)",
- "created": 1755779628,
- "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. \n\nIt succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.",
- "context_length": 163800,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": "deepseek-v3.1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 163800,
- "max_completion_tokens": null,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "seed",
- "stop",
- "temperature"
- ],
- "default_parameters": {}
- },
{
"id": "deepseek/deepseek-chat-v3.1",
"canonical_slug": "deepseek/deepseek-chat-v3.1",
@@ -2320,7 +5840,7 @@
"name": "DeepSeek: DeepSeek V3.1",
"created": 1755779628,
"description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. \n\nIt succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.",
- "context_length": 163840,
+ "context_length": 32768,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -2333,16 +5853,16 @@
"instruct_type": "deepseek-v3.1"
},
"pricing": {
- "prompt": "0.0000002",
- "completion": "0.0000008",
+ "prompt": "0.00000015",
+ "completion": "0.00000075",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 163840,
- "max_completion_tokens": 163840,
+ "context_length": 32768,
+ "max_completion_tokens": 7168,
"is_moderated": false
},
"per_request_limits": null,
@@ -2493,8 +6013,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000007",
- "completion": "0.00000028",
+ "prompt": "0.000000056",
+ "completion": "0.000000224",
"request": "0",
"image": "0",
"web_search": "0",
@@ -2514,6 +6034,8 @@
"seed",
"stop",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
"top_p"
],
@@ -2544,8 +6066,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000014",
- "completion": "0.00000056",
+ "prompt": "0.000000112",
+ "completion": "0.000000448",
"request": "0",
"image": "0",
"web_search": "0",
@@ -2567,6 +6089,8 @@
"seed",
"stop",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
"top_p"
],
@@ -2593,12 +6117,14 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.0000006",
- "completion": "0.0000018",
+ "prompt": "0.00000048",
+ "completion": "0.00000144",
"request": "0",
"image": "0",
"web_search": "0",
- "internal_reasoning": "0"
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000088",
+ "input_cache_write": "0"
},
"top_provider": {
"context_length": 65536,
@@ -2609,14 +6135,14 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
@@ -2743,7 +6269,7 @@
"completion": "0.00001",
"request": "0",
"image": "0",
- "web_search": "0",
+ "web_search": "0.01",
"internal_reasoning": "0",
"input_cache_read": "0.000000125"
},
@@ -2909,6 +6435,55 @@
],
"default_parameters": {}
},
+ {
+ "id": "openai/gpt-oss-120b:free",
+ "canonical_slug": "openai/gpt-oss-120b",
+ "hugging_face_id": "openai/gpt-oss-120b",
+ "name": "OpenAI: gpt-oss-120b (free)",
+ "created": 1754414231,
+ "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": null,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "seed",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
{
"id": "openai/gpt-oss-120b",
"canonical_slug": "openai/gpt-oss-120b",
@@ -2929,8 +6504,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000004",
- "completion": "0.0000004",
+ "prompt": "0.000000039",
+ "completion": "0.00000019",
"request": "0",
"image": "0",
"web_search": "0",
@@ -2938,7 +6513,7 @@
},
"top_provider": {
"context_length": 131072,
- "max_completion_tokens": 131072,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
@@ -2951,6 +6526,65 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "openai/gpt-oss-120b:exacto",
+ "canonical_slug": "openai/gpt-oss-120b",
+ "hugging_face_id": "openai/gpt-oss-120b",
+ "name": "OpenAI: gpt-oss-120b (exacto)",
+ "created": 1754414231,
+ "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000000039",
+ "completion": "0.00000019",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "reasoning",
"repetition_penalty",
"response_format",
"seed",
@@ -2960,10 +6594,13 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
- "default_parameters": null
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "openai/gpt-oss-20b:free",
@@ -2994,17 +6631,14 @@
},
"top_provider": {
"context_length": 131072,
- "max_completion_tokens": 131072,
+ "max_completion_tokens": 128000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
@@ -3013,11 +6647,16 @@
"stop",
"structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
- "top_logprobs",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "openai/gpt-oss-20b",
@@ -3056,11 +6695,11 @@
"frequency_penalty",
"include_reasoning",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -3070,10 +6709,13 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "anthropic/claude-opus-4.1",
@@ -3108,15 +6750,17 @@
},
"top_provider": {
"context_length": 200000,
- "max_completion_tokens": 32000,
- "is_moderated": false
+ "max_completion_tokens": null,
+ "is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"reasoning",
+ "response_format",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
@@ -3186,7 +6830,7 @@
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
"created": 1753972379,
"description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.\n\nThis model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats. ",
- "context_length": 262144,
+ "context_length": 160000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -3199,25 +6843,22 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000006",
- "completion": "0.00000025",
+ "prompt": "0.00000007",
+ "completion": "0.00000027",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 262144,
- "max_completion_tokens": 262144,
+ "context_length": 160000,
+ "max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
@@ -3228,7 +6869,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -3268,10 +6908,7 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
@@ -3282,7 +6919,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -3316,15 +6952,13 @@
},
"top_provider": {
"context_length": 131072,
- "max_completion_tokens": 131072,
+ "max_completion_tokens": 65536,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -3337,9 +6971,7 @@
"temperature",
"tool_choice",
"tools",
- "top_a",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -3384,21 +7016,18 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -3427,27 +7056,27 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000014",
- "completion": "0.00000086",
+ "prompt": "0.000000104",
+ "completion": "0.00000068",
"request": "0",
"image": "0",
"web_search": "0",
- "internal_reasoning": "0"
+ "internal_reasoning": "0",
+ "input_cache_read": "0"
},
"top_provider": {
"context_length": 131072,
- "max_completion_tokens": 131072,
+ "max_completion_tokens": 98304,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"presence_penalty",
"reasoning",
+ "repetition_penalty",
"response_format",
"seed",
"stop",
@@ -3456,7 +7085,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -3502,7 +7130,6 @@
"frequency_penalty",
"include_reasoning",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -3516,7 +7143,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -3574,7 +7200,7 @@
"name": "Qwen: Qwen3 Coder 480B A35B (free)",
"created": 1753230546,
"description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).\n\nPricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.",
- "context_length": 262144,
+ "context_length": 262000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -3595,17 +7221,14 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 262144,
- "max_completion_tokens": null,
+ "context_length": 262000,
+ "max_completion_tokens": 262000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
"seed",
@@ -3614,7 +7237,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -3659,6 +7281,7 @@
"max_tokens",
"min_p",
"presence_penalty",
+ "reasoning",
"repetition_penalty",
"response_format",
"seed",
@@ -3673,6 +7296,57 @@
],
"default_parameters": {}
},
+ {
+ "id": "qwen/qwen3-coder:exacto",
+ "canonical_slug": "qwen/qwen3-coder-480b-a35b-07-25",
+ "hugging_face_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+ "name": "Qwen: Qwen3 Coder 480B A35B (exacto)",
+ "created": 1753230546,
+ "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).\n\nPricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.",
+ "context_length": 262144,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Qwen3",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.00000022",
+ "completion": "0.0000018",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 262144,
+ "max_completion_tokens": 65536,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
{
"id": "bytedance/ui-tars-1.5-7b",
"canonical_slug": "bytedance/ui-tars-1.5-7b",
@@ -3733,10 +7407,11 @@
"architecture": {
"modality": "text+image->text",
"input_modalities": [
- "file",
- "image",
"text",
- "audio"
+ "image",
+ "file",
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -3751,7 +7426,7 @@
"image": "0",
"web_search": "0",
"internal_reasoning": "0",
- "input_cache_read": "0.000000025",
+ "input_cache_read": "0.00000001",
"input_cache_write": "0.0000001833"
},
"top_provider": {
@@ -3773,7 +7448,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "qwen/qwen3-235b-a22b-2507",
@@ -3795,8 +7474,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000008",
- "completion": "0.00000055",
+ "prompt": "0.000000071",
+ "completion": "0.000000463",
"request": "0",
"image": "0",
"web_search": "0",
@@ -3804,17 +7483,20 @@
},
"top_provider": {
"context_length": 262144,
- "max_completion_tokens": 262144,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
+ "include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
+ "reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -3922,7 +7604,7 @@
"name": "MoonshotAI: Kimi K2 0711",
"created": 1752263252,
"description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.",
- "context_length": 63000,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -3935,22 +7617,21 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000014",
- "completion": "0.00000249",
+ "prompt": "0.000000456",
+ "completion": "0.00000184",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 63000,
- "max_completion_tokens": 63000,
+ "context_length": 131072,
+ "max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
"logprobs",
"max_tokens",
"min_p",
@@ -3990,8 +7671,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.000000035",
- "completion": "0.000000138",
+ "prompt": "0.000000028",
+ "completion": "0.0000001104",
"request": "0",
"image": "0",
"web_search": "0",
@@ -4263,58 +7944,6 @@
],
"default_parameters": {}
},
- {
- "id": "tencent/hunyuan-a13b-instruct:free",
- "canonical_slug": "tencent/hunyuan-a13b-instruct",
- "hugging_face_id": "tencent/Hunyuan-A13B-Instruct",
- "name": "Tencent: Hunyuan A13B Instruct (free)",
- "created": 1751987664,
- "description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "tencent/hunyuan-a13b-instruct",
"canonical_slug": "tencent/hunyuan-a13b-instruct",
@@ -4322,7 +7951,7 @@
"name": "Tencent: Hunyuan A13B Instruct",
"created": 1751987664,
"description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).",
- "context_length": 32768,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -4335,36 +7964,27 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000003",
- "completion": "0.00000003",
+ "prompt": "0.00000014",
+ "completion": "0.00000057",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
+ "context_length": 131072,
+ "max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
"reasoning",
- "repetition_penalty",
"response_format",
- "seed",
- "stop",
"structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -4405,10 +8025,7 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
@@ -4416,7 +8033,6 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -4457,18 +8073,18 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -4480,7 +8096,7 @@
"name": "Morph: Morph V3 Large",
"created": 1751910858,
"description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations.\n\nThe model requires the prompt to be in the following format: \n{instruction}\n{initial_code}\n{edit_snippet}\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)",
- "context_length": 81920,
+ "context_length": 262144,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -4501,8 +8117,8 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 81920,
- "max_completion_tokens": 38000,
+ "context_length": 262144,
+ "max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
@@ -4582,8 +8198,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000042",
- "completion": "0.00000125",
+ "prompt": "0.000000336",
+ "completion": "0.000001",
"request": "0",
"image": "0",
"web_search": "0",
@@ -4630,8 +8246,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000028",
- "completion": "0.0000011",
+ "prompt": "0.000000224",
+ "completion": "0.00000088",
"request": "0",
"image": "0",
"web_search": "0",
@@ -4658,61 +8274,13 @@
],
"default_parameters": {}
},
- {
- "id": "thedrummer/anubis-70b-v1.1",
- "canonical_slug": "thedrummer/anubis-70b-v1.1",
- "hugging_face_id": "TheDrummer/Anubis-70B-v1.1",
- "name": "TheDrummer: Anubis 70B V1.1",
- "created": 1751208347,
- "description": "TheDrummer's Anubis v1.1 is an unaligned, creative Llama 3.3 70B model focused on providing character-driven roleplay & stories. It excels at gritty, visceral prose, unique character adherence, and coherent narratives, while maintaining the instruction following Llama 3.3 70B is known for.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.00000065",
- "completion": "0.000001",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 131072,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "inception/mercury",
"canonical_slug": "inception/mercury",
"hugging_face_id": "",
"name": "Inception: Mercury",
"created": 1750973026,
- "description": "Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots. Read more in the blog post here. ",
+ "description": "Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots. Read more in the [blog post]\n(https://www.inceptionlabs.ai/blog/introducing-mercury) here. ",
"context_length": 128000,
"architecture": {
"modality": "text->text",
@@ -4758,62 +8326,6 @@
"frequency_penalty": null
}
},
- {
- "id": "mistralai/mistral-small-3.2-24b-instruct:free",
- "canonical_slug": "mistralai/mistral-small-3.2-24b-instruct-2506",
- "hugging_face_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
- "name": "Mistral: Mistral Small 3.2 24B (free)",
- "created": 1750443016,
- "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\n\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).",
- "context_length": 131072,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "image",
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "mistralai/mistral-small-3.2-24b-instruct",
"canonical_slug": "mistralai/mistral-small-3.2-24b-instruct-2506",
@@ -4851,7 +8363,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -4864,7 +8375,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -4913,7 +8423,6 @@
"repetition_penalty",
"seed",
"stop",
- "structured_outputs",
"temperature",
"tool_choice",
"tools",
@@ -4922,60 +8431,6 @@
],
"default_parameters": {}
},
- {
- "id": "google/gemini-2.5-flash-lite-preview-06-17",
- "canonical_slug": "google/gemini-2.5-flash-lite-preview-06-17",
- "hugging_face_id": "",
- "name": "Google: Gemini 2.5 Flash Lite Preview 06-17",
- "created": 1750173831,
- "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ",
- "context_length": 1048576,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "file",
- "image",
- "text",
- "audio"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Gemini",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000001",
- "completion": "0.0000004",
- "request": "0",
- "image": "0",
- "audio": "0.0000003",
- "web_search": "0",
- "internal_reasoning": "0",
- "input_cache_read": "0.000000025",
- "input_cache_write": "0.0000001833"
- },
- "top_provider": {
- "context_length": 1048576,
- "max_completion_tokens": 65535,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "google/gemini-2.5-flash",
"canonical_slug": "google/gemini-2.5-flash",
@@ -4990,7 +8445,8 @@
"file",
"image",
"text",
- "audio"
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -5003,9 +8459,10 @@
"completion": "0.0000025",
"request": "0",
"image": "0.001238",
+ "audio": "0.000001",
"web_search": "0",
"internal_reasoning": "0",
- "input_cache_read": "0.000000075",
+ "input_cache_read": "0.00000003",
"input_cache_write": "0.0000003833"
},
"top_provider": {
@@ -5027,7 +8484,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "google/gemini-2.5-pro",
@@ -5040,10 +8501,11 @@
"architecture": {
"modality": "text+image->text",
"input_modalities": [
- "file",
- "image",
"text",
- "audio"
+ "image",
+ "file",
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -5058,7 +8520,7 @@
"image": "0.00516",
"web_search": "0",
"internal_reasoning": "0",
- "input_cache_read": "0.00000031",
+ "input_cache_read": "0.000000125",
"input_cache_write": "0.000001625"
},
"top_provider": {
@@ -5080,59 +8542,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
- },
- {
- "id": "moonshotai/kimi-dev-72b:free",
- "canonical_slug": "moonshotai/kimi-dev-72b",
- "hugging_face_id": "moonshotai/Kimi-Dev-72B",
- "name": "MoonshotAI: Kimi Dev 72B (free)",
- "created": 1750115909,
- "description": "Kimi-Dev-72B is an open-source large language model fine-tuned for software engineering and issue resolution tasks. Based on Qwen2.5-72B, it is optimized using large-scale reinforcement learning that applies code patches in real repositories and validates them via full test suite execution—rewarding only correct, robust completions. The model achieves 60.4% on SWE-bench Verified, setting a new benchmark among open-source models for software bug fixing and code reasoning.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "moonshotai/kimi-dev-72b",
@@ -5328,162 +8742,6 @@
],
"default_parameters": {}
},
- {
- "id": "mistralai/magistral-small-2506",
- "canonical_slug": "mistralai/magistral-small-2506",
- "hugging_face_id": "mistralai/Magistral-Small-2506",
- "name": "Mistral: Magistral Small 2506",
- "created": 1749569561,
- "description": "Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.",
- "context_length": 40000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000005",
- "completion": "0.0000015",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 40000,
- "max_completion_tokens": 40000,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "max_tokens",
- "presence_penalty",
- "reasoning",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
- {
- "id": "mistralai/magistral-medium-2506",
- "canonical_slug": "mistralai/magistral-medium-2506",
- "hugging_face_id": "",
- "name": "Mistral: Magistral Medium 2506",
- "created": 1749354054,
- "description": "Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.",
- "context_length": 40960,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.000002",
- "completion": "0.000005",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 40960,
- "max_completion_tokens": 40000,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "max_tokens",
- "presence_penalty",
- "reasoning",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
- {
- "id": "mistralai/magistral-medium-2506:thinking",
- "canonical_slug": "mistralai/magistral-medium-2506",
- "hugging_face_id": "",
- "name": "Mistral: Magistral Medium 2506 (thinking)",
- "created": 1749354054,
- "description": "Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.",
- "context_length": 40960,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.000002",
- "completion": "0.000005",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 40960,
- "max_completion_tokens": 40000,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "max_tokens",
- "presence_penalty",
- "reasoning",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "google/gemini-2.5-pro-preview",
"canonical_slug": "google/gemini-2.5-pro-preview-06-05",
@@ -5537,63 +8795,11 @@
],
"default_parameters": {}
},
- {
- "id": "deepseek/deepseek-r1-0528-qwen3-8b:free",
- "canonical_slug": "deepseek/deepseek-r1-0528-qwen3-8b",
- "hugging_face_id": "deepseek-ai/deepseek-r1-0528-qwen3-8b",
- "name": "DeepSeek: Deepseek R1 0528 Qwen3 8B (free)",
- "created": 1748538543,
- "description": "DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.\nIt now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.\nThe distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "deepseek/deepseek-r1-0528-qwen3-8b",
"canonical_slug": "deepseek/deepseek-r1-0528-qwen3-8b",
"hugging_face_id": "deepseek-ai/deepseek-r1-0528-qwen3-8b",
- "name": "DeepSeek: Deepseek R1 0528 Qwen3 8B",
+ "name": "DeepSeek: DeepSeek R1 0528 Qwen3 8B",
"created": 1748538543,
"description": "DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.\nIt now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.\nThe distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.",
"context_length": 32768,
@@ -5609,8 +8815,8 @@
"instruct_type": "deepseek-r1"
},
"pricing": {
- "prompt": "0.00000003",
- "completion": "0.00000011",
+ "prompt": "0.00000002",
+ "completion": "0.0000001",
"request": "0",
"image": "0",
"web_search": "0",
@@ -5625,21 +8831,23 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "deepseek/deepseek-r1-0528:free",
@@ -5677,19 +8885,11 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
+ "temperature"
],
"default_parameters": {}
},
@@ -5783,7 +8983,7 @@
"top_provider": {
"context_length": 200000,
"max_completion_tokens": 32000,
- "is_moderated": false
+ "is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
@@ -5851,60 +9051,10 @@
"top_k",
"top_p"
],
- "default_parameters": {}
- },
- {
- "id": "mistralai/devstral-small-2505:free",
- "canonical_slug": "mistralai/devstral-small-2505",
- "hugging_face_id": "mistralai/Devstral-Small-2505",
- "name": "Mistral: Devstral Small 2505 (free)",
- "created": 1747837379,
- "description": "Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).\n\nDevstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
"default_parameters": {
- "temperature": 0.3
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
}
},
{
@@ -5914,7 +9064,7 @@
"name": "Mistral: Devstral Small 2505",
"created": 1747837379,
"description": "Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).\n\nDevstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.",
- "context_length": 131072,
+ "context_length": 128000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -5927,23 +9077,21 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000005",
- "completion": "0.00000022",
+ "prompt": "0.00000006",
+ "completion": "0.00000012",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 131072,
+ "context_length": 128000,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -5951,12 +9099,8 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
- "tool_choice",
- "tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -6102,52 +9246,6 @@
],
"default_parameters": {}
},
- {
- "id": "meta-llama/llama-3.3-8b-instruct:free",
- "canonical_slug": "meta-llama/llama-3.3-8b-instruct",
- "hugging_face_id": "",
- "name": "Meta: Llama 3.3 8B Instruct (free)",
- "created": 1747230154,
- "description": "A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.",
- "context_length": 128000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 128000,
- "max_completion_tokens": 4028,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "repetition_penalty",
- "response_format",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "nousresearch/deephermes-3-mistral-24b-preview",
"canonical_slug": "nousresearch/deephermes-3-mistral-24b-preview",
@@ -6168,8 +9266,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000015",
- "completion": "0.00000059",
+ "prompt": "0.00000002",
+ "completion": "0.0000001",
"request": "0",
"image": "0",
"web_search": "0",
@@ -6184,18 +9282,18 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -6265,7 +9363,8 @@
"text",
"image",
"file",
- "audio"
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -6302,7 +9401,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "arcee-ai/spotlight",
@@ -6551,7 +9654,7 @@
"hugging_face_id": "",
"name": "Inception: Mercury Coder",
"created": 1746033880,
- "description": "Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the [blog post here](https://www.inceptionlabs.ai/introducing-mercury).",
+ "description": "Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the [blog post here](https://www.inceptionlabs.ai/blog/introducing-mercury).",
"context_length": 128000,
"architecture": {
"modality": "text->text",
@@ -6745,58 +9848,6 @@
],
"default_parameters": {}
},
- {
- "id": "qwen/qwen3-30b-a3b:free",
- "canonical_slug": "qwen/qwen3-30b-a3b-04-28",
- "hugging_face_id": "Qwen/Qwen3-30B-A3B",
- "name": "Qwen: Qwen3 30B A3B (free)",
- "created": 1745878604,
- "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.",
- "context_length": 40960,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen3",
- "instruct_type": "qwen3"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 40960,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "qwen/qwen3-30b-a3b",
"canonical_slug": "qwen/qwen3-30b-a3b-04-28",
@@ -6833,8 +9884,6 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -6848,59 +9897,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "qwen/qwen3-8b:free",
- "canonical_slug": "qwen/qwen3-8b-04-28",
- "hugging_face_id": "Qwen/Qwen3-8B",
- "name": "Qwen: Qwen3 8B (free)",
- "created": 1745876632,
- "description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math, coding, and logical inference, and \"non-thinking\" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.",
- "context_length": 40960,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen3",
- "instruct_type": "qwen3"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 40960,
- "max_completion_tokens": 40960,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -6925,8 +9921,8 @@
"instruct_type": "qwen3"
},
"pricing": {
- "prompt": "0.000000035",
- "completion": "0.000000138",
+ "prompt": "0.000000028",
+ "completion": "0.0000001104",
"request": "0",
"image": "0",
"web_search": "0",
@@ -6938,67 +9934,22 @@
"is_moderated": false
},
"per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "max_tokens",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "qwen/qwen3-14b:free",
- "canonical_slug": "qwen/qwen3-14b-04-28",
- "hugging_face_id": "Qwen/Qwen3-14B",
- "name": "Qwen: Qwen3 14B (free)",
- "created": 1745876478,
- "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, programming, and logical inference, and a \"non-thinking\" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.",
- "context_length": 40960,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen3",
- "instruct_type": "qwen3"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 40960,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
"top_logprobs",
"top_p"
@@ -7041,8 +9992,6 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -7056,7 +10005,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -7081,8 +10029,8 @@
"instruct_type": "qwen3"
},
"pricing": {
- "prompt": "0.00000005",
- "completion": "0.0000002",
+ "prompt": "0.00000008",
+ "completion": "0.00000024",
"request": "0",
"image": "0",
"web_search": "0",
@@ -7097,63 +10045,6 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "qwen/qwen3-235b-a22b:free",
- "canonical_slug": "qwen/qwen3-235b-a22b-04-28",
- "hugging_face_id": "Qwen/Qwen3-235B-A22B",
- "name": "Qwen: Qwen3 235B A22B (free)",
- "created": 1745875757,
- "description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and code tasks, and a \"non-thinking\" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen3",
- "instruct_type": "qwen3"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
"logprobs",
"max_tokens",
"min_p",
@@ -7265,10 +10156,7 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
@@ -7276,7 +10164,6 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -7317,174 +10204,16 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "microsoft/mai-ds-r1:free",
- "canonical_slug": "microsoft/mai-ds-r1",
- "hugging_face_id": "microsoft/MAI-DS-R1",
- "name": "Microsoft: MAI DS R1 (free)",
- "created": 1745194100,
- "description": "MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model’s responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1’s reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1.\n\nMAI-DS-R1 demonstrates improved performance on harm mitigation benchmarks and maintains competitive results across general reasoning tasks. It surpasses R1-1776 in satisfaction metrics for blocked queries and reduces leakage in harmful content categories. The model is based on a transformer MoE architecture and is suitable for general-purpose use cases, excluding high-stakes domains such as legal, medical, or autonomous systems.",
- "context_length": 163840,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 163840,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "microsoft/mai-ds-r1",
- "canonical_slug": "microsoft/mai-ds-r1",
- "hugging_face_id": "microsoft/MAI-DS-R1",
- "name": "Microsoft: MAI DS R1",
- "created": 1745194100,
- "description": "MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model’s responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1’s reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1.\n\nMAI-DS-R1 demonstrates improved performance on harm mitigation benchmarks and maintains competitive results across general reasoning tasks. It surpasses R1-1776 in satisfaction metrics for blocked queries and reduces leakage in harmful content categories. The model is based on a transformer MoE architecture and is suitable for general-purpose use cases, excluding high-stakes domains such as legal, medical, or autonomous systems.",
- "context_length": 163840,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0.0000003",
- "completion": "0.0000012",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 163840,
- "max_completion_tokens": 163840,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "thudm/glm-z1-32b",
- "canonical_slug": "thudm/glm-z1-32b-0414",
- "hugging_face_id": "THUDM/GLM-Z1-32B-0414",
- "name": "THUDM: GLM Z1 32B",
- "created": 1744924148,
- "description": "GLM-Z1-32B-0414 is an enhanced reasoning variant of GLM-4-32B, built for deep mathematical, logical, and code-oriented problem solving. It applies extended reinforcement learning—both task-specific and general pairwise preference-based—to improve performance on complex multi-step tasks. Compared to the base GLM-4-32B model, Z1 significantly boosts capabilities in structured reasoning and formal domains.\n\nThe model supports enforced “thinking” steps via prompt engineering and offers improved coherence for long-form outputs. It’s optimized for use in agentic workflows, and includes support for long context (via YaRN), JSON tool calling, and fine-grained sampling configuration for stable inference. Ideal for use cases requiring deliberate, multi-step reasoning or formal derivations.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0.00000005",
- "completion": "0.00000022",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": 32768,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -7633,106 +10362,6 @@
],
"default_parameters": {}
},
- {
- "id": "shisa-ai/shisa-v2-llama3.3-70b:free",
- "canonical_slug": "shisa-ai/shisa-v2-llama3.3-70b",
- "hugging_face_id": "shisa-ai/shisa-v2-llama3.3-70b",
- "name": "Shisa AI: Shisa V2 Llama 3.3 70B (free)",
- "created": 1744754858,
- "description": "Shisa V2 Llama 3.3 70B is a bilingual Japanese-English chat model fine-tuned by Shisa.AI on Meta’s Llama-3.3-70B-Instruct base. It prioritizes Japanese language performance while retaining strong English capabilities. The model was optimized entirely through post-training, using a refined mix of supervised fine-tuning (SFT) and DPO datasets including regenerated ShareGPT-style data, translation tasks, roleplaying conversations, and instruction-following prompts. Unlike earlier Shisa releases, this version avoids tokenizer modifications or extended pretraining.\n\nShisa V2 70B achieves leading Japanese task performance across a wide range of custom and public benchmarks, including JA MT Bench, ELYZA 100, and Rakuda. It supports a 128K token context length and integrates smoothly with inference frameworks like vLLM and SGLang. While it inherits safety characteristics from its base model, no additional alignment was applied. The model is intended for high-performance bilingual chat, instruction following, and translation tasks across JA/EN.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "shisa-ai/shisa-v2-llama3.3-70b",
- "canonical_slug": "shisa-ai/shisa-v2-llama3.3-70b",
- "hugging_face_id": "shisa-ai/shisa-v2-llama3.3-70b",
- "name": "Shisa AI: Shisa V2 Llama 3.3 70B ",
- "created": 1744754858,
- "description": "Shisa V2 Llama 3.3 70B is a bilingual Japanese-English chat model fine-tuned by Shisa.AI on Meta’s Llama-3.3-70B-Instruct base. It prioritizes Japanese language performance while retaining strong English capabilities. The model was optimized entirely through post-training, using a refined mix of supervised fine-tuning (SFT) and DPO datasets including regenerated ShareGPT-style data, translation tasks, roleplaying conversations, and instruction-following prompts. Unlike earlier Shisa releases, this version avoids tokenizer modifications or extended pretraining.\n\nShisa V2 70B achieves leading Japanese task performance across a wide range of custom and public benchmarks, including JA MT Bench, ELYZA 100, and Rakuda. It supports a 128K token context length and integrates smoothly with inference frameworks like vLLM and SGLang. While it inherits safety characteristics from its base model, no additional alignment was applied. The model is intended for high-performance bilingual chat, instruction following, and translation tasks across JA/EN.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.00000005",
- "completion": "0.00000022",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": 32768,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "qwen/qwen2.5-coder-7b-instruct",
"canonical_slug": "qwen/qwen2.5-coder-7b-instruct",
@@ -7768,17 +10397,13 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"presence_penalty",
+ "repetition_penalty",
"response_format",
- "seed",
- "stop",
"structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -7820,21 +10445,12 @@
},
"per_request_limits": null,
"supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "presence_penalty",
"response_format",
"seed",
- "stop",
"structured_outputs",
- "temperature",
"tool_choice",
- "tools",
- "top_logprobs",
- "top_p",
- "web_search_options"
+ "tools"
],
"default_parameters": {}
},
@@ -7875,21 +10491,12 @@
},
"per_request_limits": null,
"supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "presence_penalty",
"response_format",
"seed",
- "stop",
"structured_outputs",
- "temperature",
"tool_choice",
- "tools",
- "top_logprobs",
- "top_p",
- "web_search_options"
+ "tools"
],
"default_parameters": {}
},
@@ -7930,20 +10537,12 @@
},
"per_request_limits": null,
"supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "presence_penalty",
"response_format",
"seed",
- "stop",
"structured_outputs",
- "temperature",
"tool_choice",
- "tools",
- "top_logprobs",
- "top_p"
+ "tools"
],
"default_parameters": {}
},
@@ -8041,58 +10640,6 @@
],
"default_parameters": {}
},
- {
- "id": "arliai/qwq-32b-arliai-rpr-v1:free",
- "canonical_slug": "arliai/qwq-32b-arliai-rpr-v1",
- "hugging_face_id": "ArliAI/QwQ-32B-ArliAI-RpR-v1",
- "name": "ArliAI: QwQ 32B RpR v1 (free)",
- "created": 1744555982,
- "description": "QwQ-32B-ArliAI-RpR-v1 is a 32B parameter model fine-tuned from Qwen/QwQ-32B using a curated creative writing and roleplay dataset originally developed for the RPMax series. It is designed to maintain coherence and reasoning across long multi-turn conversations by introducing explicit reasoning steps per dialogue turn, generated and refined using the base model itself.\n\nThe model was trained using RS-QLORA+ on 8K sequence lengths and supports up to 128K context windows (with practical performance around 32K). It is optimized for creative roleplay and dialogue generation, with an emphasis on minimizing cross-context repetition while preserving stylistic diversity.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "arliai/qwq-32b-arliai-rpr-v1",
"canonical_slug": "arliai/qwq-32b-arliai-rpr-v1",
@@ -8129,122 +10676,16 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "agentica-org/deepcoder-14b-preview:free",
- "canonical_slug": "agentica-org/deepcoder-14b-preview",
- "hugging_face_id": "agentica-org/DeepCoder-14B-Preview",
- "name": "Agentica: Deepcoder 14B Preview (free)",
- "created": 1744555395,
- "description": "DeepCoder-14B-Preview is a 14B parameter code generation model fine-tuned from DeepSeek-R1-Distill-Qwen-14B using reinforcement learning with GRPO+ and iterative context lengthening. It is optimized for long-context program synthesis and achieves strong performance across coding benchmarks, including 60.6% on LiveCodeBench v5, competitive with models like o3-Mini",
- "context_length": 96000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 96000,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "agentica-org/deepcoder-14b-preview",
- "canonical_slug": "agentica-org/deepcoder-14b-preview",
- "hugging_face_id": "agentica-org/DeepCoder-14B-Preview",
- "name": "Agentica: Deepcoder 14B Preview",
- "created": 1744555395,
- "description": "DeepCoder-14B-Preview is a 14B parameter code generation model fine-tuned from DeepSeek-R1-Distill-Qwen-14B using reinforcement learning with GRPO+ and iterative context lengthening. It is optimized for long-context program synthesis and achieves strong performance across coding benchmarks, including 60.6% on LiveCodeBench v5, competitive with models like o3-Mini",
- "context_length": 96000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0.000000015",
- "completion": "0.000000015",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 96000,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -8385,62 +10826,13 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"presence_penalty",
"reasoning",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "meta-llama/llama-4-maverick:free",
- "canonical_slug": "meta-llama/llama-4-maverick-17b-128e-instruct",
- "hugging_face_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
- "name": "Meta: Llama 4 Maverick (free)",
- "created": 1743881822,
- "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\n\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.",
- "context_length": 128000,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama4",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 128000,
- "max_completion_tokens": 4028,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
"repetition_penalty",
"response_format",
"structured_outputs",
"temperature",
- "tool_choice",
- "tools",
"top_k",
"top_p"
],
@@ -8483,7 +10875,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -8496,54 +10887,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "meta-llama/llama-4-scout:free",
- "canonical_slug": "meta-llama/llama-4-scout-17b-16e-instruct",
- "hugging_face_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
- "name": "Meta: Llama 4 Scout (free)",
- "created": 1743881519,
- "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\n\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.",
- "context_length": 128000,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama4",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 128000,
- "max_completion_tokens": 4028,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "repetition_penalty",
- "response_format",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
"top_p"
],
"default_parameters": {}
@@ -8585,7 +10928,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -8598,112 +10940,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "allenai/molmo-7b-d",
- "canonical_slug": "allenai/molmo-7b-d-0924",
- "hugging_face_id": "allenai/Molmo-7B-D-0924",
- "name": "AllenAI: Molmo 7B D",
- "created": 1743023247,
- "description": "Molmo is a family of open vision-language models developed by the Allen Institute for AI. Molmo models are trained on PixMo, a dataset of 1 million, highly-curated image-text pairs. It has state-of-the-art performance among multimodal models with a similar size while being fully open-source. You can find all models in the Molmo family [here](https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19). Learn more about the Molmo family [in the announcement blog post](https://molmo.allenai.org/blog) or the [paper](https://huggingface.co/papers/2409.17146).\n\nMolmo 7B-D is based on [Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) and uses [OpenAI CLIP](https://huggingface.co/openai/clip-vit-large-patch14-336) as vision backbone. It performs comfortably between GPT-4V and GPT-4o on both academic benchmarks and human evaluation.\n\nThis checkpoint is a preview of the Molmo release. All artifacts used in creating Molmo (PixMo dataset, training code, evaluations, intermediate checkpoints) will be made available at a later date, furthering our commitment to open-source AI development and reproducibility.",
- "context_length": 4096,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000001",
- "completion": "0.0000002",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 4096,
- "max_completion_tokens": 4096,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0,
- "top_p": null,
- "frequency_penalty": null
- }
- },
- {
- "id": "qwen/qwen2.5-vl-32b-instruct:free",
- "canonical_slug": "qwen/qwen2.5-vl-32b-instruct",
- "hugging_face_id": "Qwen/Qwen2.5-VL-32B-Instruct",
- "name": "Qwen: Qwen2.5 VL 32B Instruct (free)",
- "created": 1742839838,
- "description": "Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving capabilities. It excels at visual analysis tasks, including object recognition, textual interpretation within images, and precise event localization in extended videos. Qwen2.5-VL-32B demonstrates state-of-the-art performance across multimodal benchmarks such as MMMU, MathVista, and VideoMME, while maintaining strong reasoning and clarity in text-based tasks like MMLU, mathematical problem-solving, and code generation.",
- "context_length": 16384,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 16384,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -8761,58 +10997,6 @@
],
"default_parameters": {}
},
- {
- "id": "deepseek/deepseek-chat-v3-0324:free",
- "canonical_slug": "deepseek/deepseek-chat-v3-0324",
- "hugging_face_id": "deepseek-ai/DeepSeek-V3-0324",
- "name": "DeepSeek: DeepSeek V3 0324 (free)",
- "created": 1742824755,
- "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.\n\nIt succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.",
- "context_length": 163840,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 163840,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "deepseek/deepseek-chat-v3-0324",
"canonical_slug": "deepseek/deepseek-chat-v3-0324",
@@ -8833,16 +11017,17 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000024",
- "completion": "0.00000084",
+ "prompt": "0.0000002",
+ "completion": "0.00000088",
"request": "0",
"image": "0",
"web_search": "0",
- "internal_reasoning": "0"
+ "internal_reasoning": "0",
+ "input_cache_read": "0.000000106"
},
"top_provider": {
"context_length": 163840,
- "max_completion_tokens": 163840,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
@@ -8853,6 +11038,7 @@
"max_tokens",
"min_p",
"presence_penalty",
+ "reasoning",
"repetition_penalty",
"response_format",
"seed",
@@ -8948,21 +11134,15 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
- "repetition_penalty",
"response_format",
- "seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -8976,7 +11156,7 @@
"name": "Mistral: Mistral Small 3.1 24B",
"created": 1742238937,
"description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)",
- "context_length": 128000,
+ "context_length": 131072,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
@@ -8990,25 +11170,22 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000005",
- "completion": "0.0000001",
+ "prompt": "0.00000003",
+ "completion": "0.00000011",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 128000,
- "max_completion_tokens": null,
+ "context_length": 131072,
+ "max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
@@ -9019,7 +11196,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -9033,7 +11209,7 @@
"name": "AllenAI: Olmo 2 32B Instruct",
"created": 1741988556,
"description": "OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning and instruction-following tasks across diverse benchmarks such as GSM8K, MATH, IFEval, and general NLP evaluation. Developed by AI2, OLMo-2 32B is part of an open, research-oriented initiative, trained primarily on English-language datasets to advance the understanding and development of open-source language models.",
- "context_length": 4096,
+ "context_length": 128000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -9046,32 +11222,20 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.0000002",
- "completion": "0.00000035",
+ "prompt": "0.00000005",
+ "completion": "0.0000002",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 4096,
- "max_completion_tokens": 4096,
+ "context_length": 128000,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
+ "supported_parameters": [],
"default_parameters": {}
},
{
@@ -9154,8 +11318,6 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -9165,7 +11327,6 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -9249,7 +11410,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -9260,7 +11420,6 @@
"structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -9401,7 +11560,7 @@
"name": "Google: Gemma 3 27B (free)",
"created": 1741756359,
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)",
- "context_length": 96000,
+ "context_length": 131072,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
@@ -9423,17 +11582,14 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 96000,
- "max_completion_tokens": 8192,
+ "context_length": 131072,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
@@ -9441,8 +11597,8 @@
"stop",
"structured_outputs",
"temperature",
- "top_k",
- "top_logprobs",
+ "tool_choice",
+ "tools",
"top_p"
],
"default_parameters": {}
@@ -9454,7 +11610,7 @@
"name": "Google: Gemma 3 27B",
"created": 1741756359,
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)",
- "context_length": 131072,
+ "context_length": 96000,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
@@ -9468,23 +11624,22 @@
"instruct_type": "gemma"
},
"pricing": {
- "prompt": "0.00000009",
- "completion": "0.00000016",
+ "prompt": "0.00000004",
+ "completion": "0.00000015",
"request": "0",
- "image": "0.0000256",
+ "image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 16384,
+ "context_length": 96000,
+ "max_completion_tokens": 96000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -9494,8 +11649,9 @@
"stop",
"structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -9520,8 +11676,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000008",
- "completion": "0.00000033",
+ "prompt": "0.00000055",
+ "completion": "0.0000008",
"request": "0",
"image": "0",
"web_search": "0",
@@ -9536,7 +11692,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -9545,7 +11700,6 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -9593,10 +11747,7 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
- "tool_choice",
- "tools",
"top_k",
"top_p"
],
@@ -9777,7 +11928,6 @@
"frequency_penalty",
"include_reasoning",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -9791,107 +11941,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "nousresearch/deephermes-3-llama-3-8b-preview:free",
- "canonical_slug": "nousresearch/deephermes-3-llama-3-8b-preview",
- "hugging_face_id": "NousResearch/DeepHermes-3-Llama-3-8B-Preview",
- "name": "Nous: DeepHermes 3 Llama 3 8B Preview (free)",
- "created": 1740719372,
- "description": "DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one model. We have also improved LLM annotation, judgement, and function calling.\n\nDeepHermes 3 Preview is one of the first LLM models to unify both \"intuitive\", traditional mode responses and long chain of thought reasoning responses into a single model, toggled by a system prompt.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "nousresearch/deephermes-3-llama-3-8b-preview",
- "canonical_slug": "nousresearch/deephermes-3-llama-3-8b-preview",
- "hugging_face_id": "NousResearch/DeepHermes-3-Llama-3-8B-Preview",
- "name": "Nous: DeepHermes 3 Llama 3 8B Preview",
- "created": 1740719372,
- "description": "DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one model. We have also improved LLM annotation, judgement, and function calling.\n\nDeepHermes 3 Preview is one of the first LLM models to unify both \"intuitive\", traditional mode responses and long chain of thought reasoning responses into a single model, toggled by a system prompt.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.00000003",
- "completion": "0.00000011",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 131072,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -9910,7 +11959,8 @@
"text",
"image",
"file",
- "audio"
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -9943,7 +11993,64 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
+ {
+ "id": "anthropic/claude-3.7-sonnet:thinking",
+ "canonical_slug": "anthropic/claude-3-7-sonnet-20250219",
+ "hugging_face_id": "",
+ "name": "Anthropic: Claude 3.7 Sonnet (thinking)",
+ "created": 1740422110,
+ "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image",
+ "file"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Claude",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000003",
+ "completion": "0.000015",
+ "request": "0",
+ "image": "0.0048",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.0000003",
+ "input_cache_write": "0.00000375"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 64000,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_tokens",
+ "reasoning",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "anthropic/claude-3.7-sonnet",
@@ -9993,100 +12100,11 @@
"top_k",
"top_p"
],
- "default_parameters": {}
- },
- {
- "id": "anthropic/claude-3.7-sonnet:thinking",
- "canonical_slug": "anthropic/claude-3-7-sonnet-20250219",
- "hugging_face_id": "",
- "name": "Anthropic: Claude 3.7 Sonnet (thinking)",
- "created": 1740422110,
- "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)",
- "context_length": 200000,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image",
- "file"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Claude",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.000003",
- "completion": "0.000015",
- "request": "0",
- "image": "0.0048",
- "web_search": "0",
- "internal_reasoning": "0",
- "input_cache_read": "0.0000003",
- "input_cache_write": "0.00000375"
- },
- "top_provider": {
- "context_length": 200000,
- "max_completion_tokens": 64000,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "stop",
- "temperature",
- "tool_choice",
- "tools"
- ],
- "default_parameters": {}
- },
- {
- "id": "perplexity/r1-1776",
- "canonical_slug": "perplexity/r1-1776",
- "hugging_face_id": "perplexity-ai/r1-1776",
- "name": "Perplexity: R1 1776",
- "created": 1740004929,
- "description": "R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem.\n\nThe model was tested on a multilingual dataset of over 1,000 examples covering sensitive topics to measure its likelihood of refusal or overly filtered responses. [Evaluation Results](https://cdn-uploads.huggingface.co/production/uploads/675c8332d01f593dc90817f5/GiN2VqC5hawUgAGJ6oHla.png) Its performance on math and reasoning benchmarks remains similar to the base R1 model. [Reasoning Performance](https://cdn-uploads.huggingface.co/production/uploads/675c8332d01f593dc90817f5/n4Z9Byqp2S7sKUvCvI40R.png)\n\nRead more on the [Blog Post](https://perplexity.ai/hub/blog/open-sourcing-r1-1776)",
- "context_length": 128000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0.000002",
- "completion": "0.000008",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 128000,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "max_tokens",
- "presence_penalty",
- "reasoning",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "mistralai/mistral-saba",
@@ -10138,106 +12156,6 @@
"temperature": 0.3
}
},
- {
- "id": "cognitivecomputations/dolphin3.0-mistral-24b:free",
- "canonical_slug": "cognitivecomputations/dolphin3.0-mistral-24b",
- "hugging_face_id": "cognitivecomputations/Dolphin3.0-Mistral-24B",
- "name": "Dolphin3.0 Mistral 24B (free)",
- "created": 1739462019,
- "description": "Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.\n\nDolphin aims to be a general purpose instruct model, similar to the models behind ChatGPT, Claude, Gemini. \n\nPart of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3) Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "cognitivecomputations/dolphin3.0-mistral-24b",
- "canonical_slug": "cognitivecomputations/dolphin3.0-mistral-24b",
- "hugging_face_id": "cognitivecomputations/Dolphin3.0-Mistral-24B",
- "name": "Dolphin3.0 Mistral 24B",
- "created": 1739462019,
- "description": "Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.\n\nDolphin aims to be a general purpose instruct model, similar to the models behind ChatGPT, Claude, Gemini. \n\nPart of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3) Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.00000004",
- "completion": "0.00000017",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": 32768,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "meta-llama/llama-guard-3-8b",
"canonical_slug": "meta-llama/llama-guard-3-8b",
@@ -10274,7 +12192,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -10284,7 +12201,6 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -10348,7 +12264,8 @@
"text",
"image",
"file",
- "audio"
+ "audio",
+ "video"
],
"output_modalities": [
"text"
@@ -10384,7 +12301,11 @@
"tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "qwen/qwen-vl-plus",
@@ -10534,8 +12455,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.0000002",
- "completion": "0.0000002",
+ "prompt": "0.0000008",
+ "completion": "0.0000016",
"request": "0",
"image": "0",
"web_search": "0",
@@ -10561,7 +12482,7 @@
"name": "Qwen: Qwen VL Max",
"created": 1738434304,
"description": "Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.\n",
- "context_length": 7500,
+ "context_length": 131072,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
@@ -10583,8 +12504,8 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 7500,
- "max_completion_tokens": 1500,
+ "context_length": 131072,
+ "max_completion_tokens": 8192,
"is_moderated": false
},
"per_request_limits": null,
@@ -10594,9 +12515,15 @@
"response_format",
"seed",
"temperature",
+ "tool_choice",
+ "tools",
"top_p"
],
- "default_parameters": {}
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
},
{
"id": "qwen/qwen-turbo",
@@ -10644,50 +12571,6 @@
],
"default_parameters": {}
},
- {
- "id": "qwen/qwen2.5-vl-72b-instruct:free",
- "canonical_slug": "qwen/qwen2.5-vl-72b-instruct",
- "hugging_face_id": "Qwen/Qwen2.5-VL-72B-Instruct",
- "name": "Qwen: Qwen2.5 VL 72B Instruct (free)",
- "created": 1738410311,
- "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.",
- "context_length": 131072,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 2048,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "presence_penalty",
- "response_format",
- "seed",
- "temperature",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "qwen/qwen2.5-vl-72b-instruct",
"canonical_slug": "qwen/qwen2.5-vl-72b-instruct",
@@ -10709,8 +12592,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000008",
- "completion": "0.00000033",
+ "prompt": "0.00000007",
+ "completion": "0.00000026",
"request": "0",
"image": "0",
"web_search": "0",
@@ -10725,16 +12608,16 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -10876,58 +12759,6 @@
],
"default_parameters": {}
},
- {
- "id": "mistralai/mistral-small-24b-instruct-2501:free",
- "canonical_slug": "mistralai/mistral-small-24b-instruct-2501",
- "hugging_face_id": "mistralai/Mistral-Small-24B-Instruct-2501",
- "name": "Mistral: Mistral Small 3 (free)",
- "created": 1738255409,
- "description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.\n\nThe model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "mistralai/mistral-small-24b-instruct-2501",
"canonical_slug": "mistralai/mistral-small-24b-instruct-2501",
@@ -10948,8 +12779,8 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.00000005",
- "completion": "0.00000008",
+ "prompt": "0.00000003",
+ "completion": "0.00000011",
"request": "0",
"image": "0",
"web_search": "0",
@@ -10957,14 +12788,13 @@
},
"top_provider": {
"context_length": 32768,
- "max_completion_tokens": 16384,
+ "max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -10977,11 +12807,12 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
- "temperature": 0.3
+ "temperature": 0.3,
+ "top_p": null,
+ "frequency_penalty": null
}
},
{
@@ -10991,7 +12822,7 @@
"name": "DeepSeek: R1 Distill Qwen 32B",
"created": 1738194830,
"description": "DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\\n\\nOther benchmark results include:\\n\\n- AIME 2024 pass@1: 72.6\\n- MATH-500 pass@1: 94.3\\n- CodeForces Rating: 1691\\n\\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.",
- "context_length": 131072,
+ "context_length": 64000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -11004,16 +12835,16 @@
"instruct_type": "deepseek-r1"
},
"pricing": {
- "prompt": "0.00000027",
- "completion": "0.00000027",
+ "prompt": "0.00000024",
+ "completion": "0.00000024",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 16384,
+ "context_length": 64000,
+ "max_completion_tokens": 32000,
"is_moderated": false
},
"per_request_limits": null,
@@ -11055,8 +12886,8 @@
"instruct_type": "deepseek-r1"
},
"pricing": {
- "prompt": "0.00000015",
- "completion": "0.00000015",
+ "prompt": "0.00000012",
+ "completion": "0.00000012",
"request": "0",
"image": "0",
"web_search": "0",
@@ -11071,14 +12902,14 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
"top_p"
@@ -11176,152 +13007,6 @@
],
"default_parameters": {}
},
- {
- "id": "liquid/lfm-7b",
- "canonical_slug": "liquid/lfm-7b",
- "hugging_face_id": "",
- "name": "Liquid: LFM 7B",
- "created": 1737806883,
- "description": "LFM-7B, a new best-in-class language model. LFM-7B is designed for exceptional chat capabilities, including languages like Arabic and Japanese. Powered by the Liquid Foundation Model (LFM) architecture, it exhibits unique features like low memory footprint and fast inference speed. \n\nLFM-7B is the world’s best-in-class multilingual language model in English, Arabic, and Japanese.\n\nSee the [launch announcement](https://www.liquid.ai/lfm-7b) for benchmarks and more info.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": "chatml"
- },
- "pricing": {
- "prompt": "0.00000001",
- "completion": "0.00000001",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "liquid/lfm-3b",
- "canonical_slug": "liquid/lfm-3b",
- "hugging_face_id": "",
- "name": "Liquid: LFM 3B",
- "created": 1737806501,
- "description": "Liquid's LFM 3B delivers incredible performance for its size. It positions itself as first place among 3B parameter transformers, hybrids, and RNN models It is also on par with Phi-3.5-mini on multiple benchmarks, while being 18.4% smaller.\n\nLFM-3B is the ideal choice for mobile and other edge text-based applications.\n\nSee the [launch announcement](https://www.liquid.ai/liquid-foundation-models) for benchmarks and more info.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Other",
- "instruct_type": "chatml"
- },
- "pricing": {
- "prompt": "0.00000002",
- "completion": "0.00000002",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "deepseek/deepseek-r1-distill-llama-70b:free",
- "canonical_slug": "deepseek/deepseek-r1-distill-llama-70b",
- "hugging_face_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
- "name": "DeepSeek: R1 Distill Llama 70B (free)",
- "created": 1737663169,
- "description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:\n\n- AIME 2024 pass@1: 70.0\n- MATH-500 pass@1: 94.5\n- CodeForces Rating: 1633\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.",
- "context_length": 8192,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 8192,
- "max_completion_tokens": 4096,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "deepseek/deepseek-r1-distill-llama-70b",
"canonical_slug": "deepseek/deepseek-r1-distill-llama-70b",
@@ -11343,7 +13028,7 @@
},
"pricing": {
"prompt": "0.00000003",
- "completion": "0.00000013",
+ "completion": "0.00000011",
"request": "0",
"image": "0",
"web_search": "0",
@@ -11359,7 +13044,6 @@
"frequency_penalty",
"include_reasoning",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -11368,54 +13052,15 @@
"response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
},
- {
- "id": "deepseek/deepseek-r1:free",
- "canonical_slug": "deepseek/deepseek-r1",
- "hugging_face_id": "deepseek-ai/DeepSeek-R1",
- "name": "DeepSeek: R1 (free)",
- "created": 1737381095,
- "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nFully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120).\n\nMIT licensed: Distill & commercialize freely!",
- "context_length": 163840,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "DeepSeek",
- "instruct_type": "deepseek-r1"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 163840,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "temperature"
- ],
- "default_parameters": {}
- },
{
"id": "deepseek/deepseek-r1",
"canonical_slug": "deepseek/deepseek-r1",
@@ -11436,8 +13081,8 @@
"instruct_type": "deepseek-r1"
},
"pricing": {
- "prompt": "0.0000004",
- "completion": "0.000002",
+ "prompt": "0.0000003",
+ "completion": "0.0000012",
"request": "0",
"image": "0",
"web_search": "0",
@@ -11445,15 +13090,13 @@
},
"top_provider": {
"context_length": 163840,
- "max_completion_tokens": 163840,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -11467,7 +13110,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -11513,56 +13155,6 @@
],
"default_parameters": {}
},
- {
- "id": "mistralai/codestral-2501",
- "canonical_slug": "mistralai/codestral-2501",
- "hugging_face_id": "",
- "name": "Mistral: Codestral 2501",
- "created": 1736895522,
- "description": "[Mistral](/mistralai)'s cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. \n\nLearn more on their blog post: https://mistral.ai/news/codestral-2501/",
- "context_length": 262144,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000003",
- "completion": "0.0000009",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 262144,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "max_tokens",
- "presence_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "microsoft/phi-4",
"canonical_slug": "microsoft/phi-4",
@@ -11681,7 +13273,7 @@
},
"pricing": {
"prompt": "0.0000003",
- "completion": "0.00000085",
+ "completion": "0.0000012",
"request": "0",
"image": "0",
"web_search": "0",
@@ -11695,8 +13287,6 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -11709,7 +13299,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -11909,7 +13498,7 @@
"name": "Meta: Llama 3.3 70B Instruct (free)",
"created": 1733506137,
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.\n\n[Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)",
- "context_length": 65536,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -11930,18 +13519,17 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 65536,
+ "context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
+ "seed",
"stop",
"temperature",
"tool_choice",
@@ -11971,8 +13559,8 @@
"instruct_type": "llama3"
},
"pricing": {
- "prompt": "0.00000013",
- "completion": "0.00000039",
+ "prompt": "0.0000001",
+ "completion": "0.00000032",
"request": "0",
"image": "0",
"web_search": "0",
@@ -11980,7 +13568,7 @@
},
"top_provider": {
"context_length": 131072,
- "max_completion_tokens": 120000,
+ "max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null,
@@ -12342,56 +13930,6 @@
"temperature": 0.3
}
},
- {
- "id": "qwen/qwen-2.5-coder-32b-instruct:free",
- "canonical_slug": "qwen/qwen-2.5-coder-32b-instruct",
- "hugging_face_id": "Qwen/Qwen2.5-Coder-32B-Instruct",
- "name": "Qwen2.5 Coder 32B Instruct (free)",
- "created": 1731368400,
- "description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:\n\n- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. \n- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.\n\nTo read more about its evaluation results, check out [Qwen 2.5 Coder's blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen",
- "instruct_type": "chatml"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "qwen/qwen-2.5-coder-32b-instruct",
"canonical_slug": "qwen/qwen-2.5-coder-32b-instruct",
@@ -12412,8 +13950,8 @@
"instruct_type": "chatml"
},
"pricing": {
- "prompt": "0.00000004",
- "completion": "0.00000016",
+ "prompt": "0.00000003",
+ "completion": "0.00000011",
"request": "0",
"image": "0",
"web_search": "0",
@@ -12428,7 +13966,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -12436,9 +13973,9 @@
"response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -12538,53 +14075,6 @@
],
"default_parameters": {}
},
- {
- "id": "anthropic/claude-3.5-haiku",
- "canonical_slug": "anthropic/claude-3-5-haiku",
- "hugging_face_id": null,
- "name": "Anthropic: Claude 3.5 Haiku",
- "created": 1730678400,
- "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).",
- "context_length": 200000,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Claude",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000008",
- "completion": "0.000004",
- "request": "0",
- "image": "0",
- "web_search": "0.01",
- "internal_reasoning": "0",
- "input_cache_read": "0.00000008",
- "input_cache_write": "0.000001"
- },
- "top_provider": {
- "context_length": 200000,
- "max_completion_tokens": 8192,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "stop",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "anthropic/claude-3.5-haiku-20241022",
"canonical_slug": "anthropic/claude-3-5-haiku-20241022",
@@ -12633,6 +14123,57 @@
],
"default_parameters": {}
},
+ {
+ "id": "anthropic/claude-3.5-haiku",
+ "canonical_slug": "anthropic/claude-3-5-haiku",
+ "hugging_face_id": null,
+ "name": "Anthropic: Claude 3.5 Haiku",
+ "created": 1730678400,
+ "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).",
+ "context_length": 200000,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Claude",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000008",
+ "completion": "0.000004",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0",
+ "input_cache_read": "0.00000008",
+ "input_cache_write": "0.000001"
+ },
+ "top_provider": {
+ "context_length": 200000,
+ "max_completion_tokens": 8192,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "max_tokens",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": null,
+ "top_p": null,
+ "frequency_penalty": null
+ }
+ },
{
"id": "anthropic/claude-3.5-sonnet",
"canonical_slug": "anthropic/claude-3.5-sonnet",
@@ -12655,14 +14196,12 @@
"instruct_type": null
},
"pricing": {
- "prompt": "0.000003",
- "completion": "0.000015",
+ "prompt": "0.000006",
+ "completion": "0.00003",
"request": "0",
- "image": "0.0048",
+ "image": "0",
"web_search": "0",
- "internal_reasoning": "0",
- "input_cache_read": "0.0000003",
- "input_cache_write": "0.00000375"
+ "internal_reasoning": "0"
},
"top_provider": {
"context_length": 200000,
@@ -12701,7 +14240,7 @@
"instruct_type": "chatml"
},
"pricing": {
- "prompt": "0.0000025",
+ "prompt": "0.000003",
"completion": "0.000005",
"request": "0",
"image": "0",
@@ -12725,7 +14264,6 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"top_a",
"top_k",
@@ -12741,7 +14279,7 @@
"name": "Mistral: Ministral 8B",
"created": 1729123200,
"description": "Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.",
- "context_length": 128000,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -12762,7 +14300,7 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 128000,
+ "context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
@@ -12791,7 +14329,7 @@
"name": "Mistral: Ministral 3B",
"created": 1729123200,
"description": "Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it’s ideal for orchestrating agentic workflows and specialist tasks with efficient inference.",
- "context_length": 32768,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -12812,7 +14350,7 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 32768,
+ "context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
@@ -12826,6 +14364,8 @@
"stop",
"structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_p"
],
"default_parameters": {
@@ -12839,7 +14379,7 @@
"name": "Qwen: Qwen2.5 7B Instruct",
"created": 1729036800,
"description": "Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n\n- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n\n- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n\n- Long-context Support up to 128K tokens and can generate up to 8K tokens.\n\n- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).",
- "context_length": 65536,
+ "context_length": 32768,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -12860,7 +14400,7 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 65536,
+ "context_length": 32768,
"max_completion_tokens": null,
"is_moderated": false
},
@@ -12872,10 +14412,8 @@
"min_p",
"presence_penalty",
"repetition_penalty",
- "response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"top_k",
"top_p"
@@ -12906,8 +14444,8 @@
"instruct_type": "llama3"
},
"pricing": {
- "prompt": "0.0000006",
- "completion": "0.0000006",
+ "prompt": "0.0000012",
+ "completion": "0.0000012",
"request": "0",
"image": "0",
"web_search": "0",
@@ -12921,7 +14459,6 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
"max_tokens",
"min_p",
"presence_penalty",
@@ -12938,12 +14475,12 @@
"default_parameters": {}
},
{
- "id": "inflection/inflection-3-productivity",
- "canonical_slug": "inflection/inflection-3-productivity",
+ "id": "inflection/inflection-3-pi",
+ "canonical_slug": "inflection/inflection-3-pi",
"hugging_face_id": null,
- "name": "Inflection: Inflection 3 Productivity",
+ "name": "Inflection: Inflection 3 Pi",
"created": 1728604800,
- "description": "Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news.\n\nFor emotional intelligence similar to Pi, see [Inflect 3 Pi](/inflection/inflection-3-pi)\n\nSee [Inflection's announcement](https://inflection.ai/blog/enterprise) for more details.",
+ "description": "Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay.\n\nPi has been trained to mirror your tone and style, if you use more emojis, so will Pi! Try experimenting with various prompts and conversation styles.",
"context_length": 8000,
"architecture": {
"modality": "text->text",
@@ -12979,12 +14516,12 @@
"default_parameters": {}
},
{
- "id": "inflection/inflection-3-pi",
- "canonical_slug": "inflection/inflection-3-pi",
+ "id": "inflection/inflection-3-productivity",
+ "canonical_slug": "inflection/inflection-3-productivity",
"hugging_face_id": null,
- "name": "Inflection: Inflection 3 Pi",
+ "name": "Inflection: Inflection 3 Productivity",
"created": 1728604800,
- "description": "Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay.\n\nPi has been trained to mirror your tone and style, if you use more emojis, so will Pi! Try experimenting with various prompts and conversation styles.",
+ "description": "Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news.\n\nFor emotional intelligence similar to Pi, see [Inflect 3 Pi](/inflection/inflection-3-pi)\n\nSee [Inflection's announcement](https://inflection.ai/blog/enterprise) for more details.",
"context_length": 8000,
"architecture": {
"modality": "text->text",
@@ -13071,54 +14608,6 @@
],
"default_parameters": {}
},
- {
- "id": "anthracite-org/magnum-v2-72b",
- "canonical_slug": "anthracite-org/magnum-v2-72b",
- "hugging_face_id": "anthracite-org/magnum-v2-72b",
- "name": "Magnum v2 72B",
- "created": 1727654400,
- "description": "From the maker of [Goliath](https://openrouter.ai/models/alpindale/goliath-120b), Magnum 72B is the seventh in a family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet.\n\nThe model is based on [Qwen2 72B](https://openrouter.ai/models/qwen/qwen-2-72b-instruct) and trained with 55 million tokens of highly curated roleplay (RP) data.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Qwen",
- "instruct_type": "chatml"
- },
- "pricing": {
- "prompt": "0.000003",
- "completion": "0.000003",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "meta-llama/llama-3.2-3b-instruct:free",
"canonical_slug": "meta-llama/llama-3.2-3b-instruct",
@@ -13170,7 +14659,7 @@
"name": "Meta: Llama 3.2 3B Instruct",
"created": 1727222400,
"description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.\n\nTrained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).",
- "context_length": 16384,
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -13191,7 +14680,7 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 16384,
+ "context_length": 131072,
"max_completion_tokens": 16384,
"is_moderated": false
},
@@ -13199,7 +14688,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -13207,12 +14695,10 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -13224,7 +14710,7 @@
"name": "Meta: Llama 3.2 1B Instruct",
"created": 1727222400,
"description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance.\n\nSupporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).",
- "context_length": 131072,
+ "context_length": 60000,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -13237,85 +14723,27 @@
"instruct_type": "llama3"
},
"pricing": {
- "prompt": "0.000000005",
- "completion": "0.00000001",
+ "prompt": "0.000000027",
+ "completion": "0.0000002",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 16384,
+ "context_length": 60000,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
- "response_format",
"seed",
- "stop",
- "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "meta-llama/llama-3.2-11b-vision-instruct",
- "canonical_slug": "meta-llama/llama-3.2-11b-vision-instruct",
- "hugging_face_id": "meta-llama/Llama-3.2-11B-Vision-Instruct",
- "name": "Meta: Llama 3.2 11B Vision Instruct",
- "created": 1727222400,
- "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-accuracy image analysis.\n\nIts ability to integrate visual understanding with language processing makes it an ideal solution for industries requiring comprehensive visual-linguistic AI applications, such as content creation, AI-driven customer service, and research.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).",
- "context_length": 131072,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": "llama3"
- },
- "pricing": {
- "prompt": "0.000000049",
- "completion": "0.000000049",
- "request": "0",
- "image": "0.00007948",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 16384,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -13370,51 +14798,51 @@
"default_parameters": {}
},
{
- "id": "qwen/qwen-2.5-72b-instruct:free",
- "canonical_slug": "qwen/qwen-2.5-72b-instruct",
- "hugging_face_id": "Qwen/Qwen2.5-72B-Instruct",
- "name": "Qwen2.5 72B Instruct (free)",
- "created": 1726704000,
- "description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n\n- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n\n- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n\n- Long-context Support up to 128K tokens and can generate up to 8K tokens.\n\n- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).",
- "context_length": 32768,
+ "id": "meta-llama/llama-3.2-11b-vision-instruct",
+ "canonical_slug": "meta-llama/llama-3.2-11b-vision-instruct",
+ "hugging_face_id": "meta-llama/Llama-3.2-11B-Vision-Instruct",
+ "name": "Meta: Llama 3.2 11B Vision Instruct",
+ "created": 1727222400,
+ "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-accuracy image analysis.\n\nIts ability to integrate visual understanding with language processing makes it an ideal solution for industries requiring comprehensive visual-linguistic AI applications, such as content creation, AI-driven customer service, and research.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).",
+ "context_length": 131072,
"architecture": {
- "modality": "text->text",
+ "modality": "text+image->text",
"input_modalities": [
- "text"
+ "text",
+ "image"
],
"output_modalities": [
"text"
],
- "tokenizer": "Qwen",
- "instruct_type": "chatml"
+ "tokenizer": "Llama3",
+ "instruct_type": "llama3"
},
"pricing": {
- "prompt": "0",
- "completion": "0",
+ "prompt": "0.000000049",
+ "completion": "0.000000049",
"request": "0",
- "image": "0",
+ "image": "0.00007948",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
+ "context_length": 131072,
+ "max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -13439,8 +14867,8 @@
"instruct_type": "chatml"
},
"pricing": {
- "prompt": "0.00000007",
- "completion": "0.00000026",
+ "prompt": "0.00000012",
+ "completion": "0.00000039",
"request": "0",
"image": "0",
"web_search": "0",
@@ -13448,14 +14876,13 @@
},
"top_provider": {
"context_length": 32768,
- "max_completion_tokens": 32768,
+ "max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -13463,11 +14890,11 @@
"response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -13507,104 +14934,16 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
- "repetition_penalty",
"response_format",
- "seed",
"stop",
"structured_outputs",
"temperature",
- "top_a",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
},
- {
- "id": "openai/o1-mini",
- "canonical_slug": "openai/o1-mini",
- "hugging_face_id": null,
- "name": "OpenAI: o1-mini",
- "created": 1726099200,
- "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.\n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n\nNote: This model is currently experimental and not suitable for production use-cases, and may be heavily rate-limited.",
- "context_length": 128000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "GPT",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000011",
- "completion": "0.0000044",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0",
- "input_cache_read": "0.00000055"
- },
- "top_provider": {
- "context_length": 128000,
- "max_completion_tokens": 65536,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "seed"
- ],
- "default_parameters": {}
- },
- {
- "id": "openai/o1-mini-2024-09-12",
- "canonical_slug": "openai/o1-mini-2024-09-12",
- "hugging_face_id": null,
- "name": "OpenAI: o1-mini (2024-09-12)",
- "created": 1726099200,
- "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.\n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n\nNote: This model is currently experimental and not suitable for production use-cases, and may be heavily rate-limited.",
- "context_length": 128000,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "GPT",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000011",
- "completion": "0.0000044",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0",
- "input_cache_read": "0.00000055"
- },
- "top_provider": {
- "context_length": 128000,
- "max_completion_tokens": 65536,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "seed"
- ],
- "default_parameters": {}
- },
{
"id": "mistralai/pixtral-12b",
"canonical_slug": "mistralai/pixtral-12b",
@@ -13642,7 +14981,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -13655,7 +14993,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -13704,6 +15041,7 @@
"stop",
"structured_outputs",
"temperature",
+ "tool_choice",
"tools",
"top_k",
"top_p"
@@ -13752,12 +15090,56 @@
"stop",
"structured_outputs",
"temperature",
+ "tool_choice",
"tools",
"top_k",
"top_p"
],
"default_parameters": {}
},
+ {
+ "id": "qwen/qwen-2.5-vl-7b-instruct:free",
+ "canonical_slug": "qwen/qwen-2-vl-7b-instruct",
+ "hugging_face_id": "Qwen/Qwen2.5-VL-7B-Instruct",
+ "name": "Qwen: Qwen2.5-VL 7B Instruct (free)",
+ "created": 1724803200,
+ "description": "Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\n- SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\n- Understanding videos of 20min+: Qwen2.5-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.\n\n- Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\n- Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.\n\nFor more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL).\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text+image->text",
+ "input_modalities": [
+ "text",
+ "image"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Qwen",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "temperature"
+ ],
+ "default_parameters": {}
+ },
{
"id": "qwen/qwen-2.5-vl-7b-instruct",
"canonical_slug": "qwen/qwen-2-vl-7b-instruct",
@@ -13795,18 +15177,14 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
- "response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -13855,6 +15233,8 @@
"stop",
"structured_outputs",
"temperature",
+ "tool_choice",
+ "tools",
"top_k",
"top_p"
],
@@ -13909,7 +15289,7 @@
"name": "Nous: Hermes 3 70B Instruct",
"created": 1723939200,
"description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 70B is a competitive, if not superior finetune of the [Llama-3.1 70B foundation model](/models/meta-llama/llama-3.1-70b-instruct), focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.",
- "context_length": 65000,
+ "context_length": 65536,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -13930,15 +15310,13 @@
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 65000,
+ "context_length": 65536,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -13948,10 +15326,51 @@
"stop",
"structured_outputs",
"temperature",
- "tool_choice",
- "tools",
"top_k",
- "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
+ {
+ "id": "nousresearch/hermes-3-llama-3.1-405b:free",
+ "canonical_slug": "nousresearch/hermes-3-llama-3.1-405b",
+ "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-405B",
+ "name": "Nous: Hermes 3 405B Instruct (free)",
+ "created": 1723766400,
+ "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 405B is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.\n\nHermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.",
+ "context_length": 131072,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Llama3",
+ "instruct_type": "chatml"
+ },
+ "pricing": {
+ "prompt": "0",
+ "completion": "0",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 131072,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "stop",
+ "temperature",
+ "top_k",
"top_p"
],
"default_parameters": {}
@@ -13991,8 +15410,6 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -14002,7 +15419,6 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -14099,6 +15515,7 @@
"response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
"top_p"
@@ -14196,7 +15613,6 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -14205,19 +15621,18 @@
"stop",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
},
{
- "id": "meta-llama/llama-3.1-405b-instruct",
- "canonical_slug": "meta-llama/llama-3.1-405b-instruct",
- "hugging_face_id": "meta-llama/Meta-Llama-3.1-405B-Instruct",
- "name": "Meta: Llama 3.1 405B Instruct",
+ "id": "meta-llama/llama-3.1-70b-instruct",
+ "canonical_slug": "meta-llama/llama-3.1-70b-instruct",
+ "hugging_face_id": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+ "name": "Meta: Llama 3.1 70B Instruct",
"created": 1721692800,
- "description": "The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs.\n\nMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 405B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models including GPT-4o and Claude 3.5 Sonnet in evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
- "context_length": 32768,
+ "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+ "context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
@@ -14230,23 +15645,22 @@
"instruct_type": "llama3"
},
"pricing": {
- "prompt": "0.0000008",
- "completion": "0.0000008",
+ "prompt": "0.0000004",
+ "completion": "0.0000004",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
- "context_length": 32768,
- "max_completion_tokens": 16384,
+ "context_length": 131072,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -14254,12 +15668,10 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
@@ -14319,12 +15731,12 @@
"default_parameters": {}
},
{
- "id": "meta-llama/llama-3.1-70b-instruct",
- "canonical_slug": "meta-llama/llama-3.1-70b-instruct",
- "hugging_face_id": "meta-llama/Meta-Llama-3.1-70B-Instruct",
- "name": "Meta: Llama 3.1 70B Instruct",
+ "id": "meta-llama/llama-3.1-405b-instruct:free",
+ "canonical_slug": "meta-llama/llama-3.1-405b-instruct",
+ "hugging_face_id": "meta-llama/Meta-Llama-3.1-405B-Instruct",
+ "name": "Meta: Llama 3.1 405B Instruct (free)",
"created": 1721692800,
- "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+ "description": "The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs.\n\nMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 405B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models including GPT-4o and Claude 3.5 Sonnet in evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
"context_length": 131072,
"architecture": {
"modality": "text->text",
@@ -14338,8 +15750,8 @@
"instruct_type": "llama3"
},
"pricing": {
- "prompt": "0.0000004",
- "completion": "0.0000004",
+ "prompt": "0",
+ "completion": "0",
"request": "0",
"image": "0",
"web_search": "0",
@@ -14351,10 +15763,51 @@
"is_moderated": false
},
"per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "temperature"
+ ],
+ "default_parameters": {}
+ },
+ {
+ "id": "meta-llama/llama-3.1-405b-instruct",
+ "canonical_slug": "meta-llama/llama-3.1-405b-instruct",
+ "hugging_face_id": "meta-llama/Meta-Llama-3.1-405B-Instruct",
+ "name": "Meta: Llama 3.1 405B Instruct",
+ "created": 1721692800,
+ "description": "The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs.\n\nMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 405B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models including GPT-4o and Claude 3.5 Sonnet in evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+ "context_length": 10000,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Llama3",
+ "instruct_type": "llama3"
+ },
+ "pricing": {
+ "prompt": "0.0000035",
+ "completion": "0.0000035",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 10000,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -14367,63 +15820,10 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {}
},
- {
- "id": "mistralai/mistral-nemo:free",
- "canonical_slug": "mistralai/mistral-nemo",
- "hugging_face_id": "mistralai/Mistral-Nemo-Instruct-2407",
- "name": "Mistral: Mistral Nemo (free)",
- "created": 1721347200,
- "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.\n\nThe model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.\n\nIt supports function calling and is released under the Apache 2.0 license.",
- "context_length": 131072,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": "mistral"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 131072,
- "max_completion_tokens": 128000,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "mistralai/mistral-nemo",
"canonical_slug": "mistralai/mistral-nemo",
@@ -14459,8 +15859,6 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -14473,7 +15871,6 @@
"tool_choice",
"tools",
"top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -14635,56 +16032,6 @@
],
"default_parameters": {}
},
- {
- "id": "google/gemma-2-9b-it:free",
- "canonical_slug": "google/gemma-2-9b-it",
- "hugging_face_id": "google/gemma-2-9b-it",
- "name": "Google: Gemma 2 9B (free)",
- "created": 1719532800,
- "description": "Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class.\n\nDesigned for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness.\n\nSee the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).",
- "context_length": 8192,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Gemini",
- "instruct_type": "gemma"
- },
- "pricing": {
- "prompt": "0",
- "completion": "0",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 8192,
- "max_completion_tokens": 8192,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "google/gemma-2-9b-it",
"canonical_slug": "google/gemma-2-9b-it",
@@ -14705,8 +16052,8 @@
"instruct_type": "gemma"
},
"pricing": {
- "prompt": "0.00000001",
- "completion": "0.00000003",
+ "prompt": "0.00000003",
+ "completion": "0.00000009",
"request": "0",
"image": "0",
"web_search": "0",
@@ -14714,73 +16061,17 @@
},
"top_provider": {
"context_length": 8192,
- "max_completion_tokens": 8192,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "anthropic/claude-3.5-sonnet-20240620",
- "canonical_slug": "anthropic/claude-3.5-sonnet-20240620",
- "hugging_face_id": null,
- "name": "Anthropic: Claude 3.5 Sonnet (2024-06-20)",
- "created": 1718841600,
- "description": "Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\nFor the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).\n\n#multimodal",
- "context_length": 200000,
- "architecture": {
- "modality": "text+image->text",
- "input_modalities": [
- "text",
- "image",
- "file"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Claude",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.000003",
- "completion": "0.000015",
- "request": "0",
- "image": "0.0048",
- "web_search": "0",
- "internal_reasoning": "0",
- "input_cache_read": "0.0000003",
- "input_cache_write": "0.00000375"
- },
- "top_provider": {
- "context_length": 200000,
- "max_completion_tokens": 8192,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "max_tokens",
- "stop",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
"top_p"
],
"default_parameters": {}
@@ -14826,110 +16117,11 @@
"seed",
"stop",
"temperature",
- "top_k",
- "top_p"
- ],
- "default_parameters": {}
- },
- {
- "id": "mistralai/mistral-7b-instruct-v0.3",
- "canonical_slug": "mistralai/mistral-7b-instruct-v0.3",
- "hugging_face_id": "mistralai/Mistral-7B-Instruct-v0.3",
- "name": "Mistral: Mistral 7B Instruct v0.3",
- "created": 1716768000,
- "description": "A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length.\n\nAn improved version of [Mistral 7B Instruct v0.2](/models/mistralai/mistral-7b-instruct-v0.2), with the following changes:\n\n- Extended vocabulary to 32768\n- Supports v3 Tokenizer\n- Supports function calling\n\nNOTE: Support for function calling depends on the provider.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": "mistral"
- },
- "pricing": {
- "prompt": "0.000000028",
- "completion": "0.000000054",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": 16384,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "temperature",
"tool_choice",
"tools",
"top_k",
"top_p"
],
- "default_parameters": {
- "temperature": 0.3
- }
- },
- {
- "id": "nousresearch/hermes-2-pro-llama-3-8b",
- "canonical_slug": "nousresearch/hermes-2-pro-llama-3-8b",
- "hugging_face_id": "NousResearch/Hermes-2-Pro-Llama-3-8B",
- "name": "NousResearch: Hermes 2 Pro - Llama-3 8B",
- "created": 1716768000,
- "description": "Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": "chatml"
- },
- "pricing": {
- "prompt": "0.000000025",
- "completion": "0.00000008",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "max_tokens",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "top_k",
- "top_p"
- ],
"default_parameters": {}
},
{
@@ -15037,6 +16229,103 @@
"temperature": 0.3
}
},
+ {
+ "id": "mistralai/mistral-7b-instruct-v0.3",
+ "canonical_slug": "mistralai/mistral-7b-instruct-v0.3",
+ "hugging_face_id": "mistralai/Mistral-7B-Instruct-v0.3",
+ "name": "Mistral: Mistral 7B Instruct v0.3",
+ "created": 1716768000,
+ "description": "A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length.\n\nAn improved version of [Mistral 7B Instruct v0.2](/models/mistralai/mistral-7b-instruct-v0.2), with the following changes:\n\n- Extended vocabulary to 32768\n- Supports v3 Tokenizer\n- Supports function calling\n\nNOTE: Support for function calling depends on the provider.",
+ "context_length": 32768,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": "mistral"
+ },
+ "pricing": {
+ "prompt": "0.0000002",
+ "completion": "0.0000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 32768,
+ "max_completion_tokens": 4096,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "stop",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3
+ }
+ },
+ {
+ "id": "nousresearch/hermes-2-pro-llama-3-8b",
+ "canonical_slug": "nousresearch/hermes-2-pro-llama-3-8b",
+ "hugging_face_id": "NousResearch/Hermes-2-Pro-Llama-3-8B",
+ "name": "NousResearch: Hermes 2 Pro - Llama-3 8B",
+ "created": 1716768000,
+ "description": "Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.",
+ "context_length": 8192,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Llama3",
+ "instruct_type": "chatml"
+ },
+ "pricing": {
+ "prompt": "0.000000025",
+ "completion": "0.00000008",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 8192,
+ "max_completion_tokens": 2048,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
{
"id": "microsoft/phi-3-mini-128k-instruct",
"canonical_slug": "microsoft/phi-3-mini-128k-instruct",
@@ -15331,6 +16620,58 @@
],
"default_parameters": {}
},
+ {
+ "id": "meta-llama/llama-3-70b-instruct",
+ "canonical_slug": "meta-llama/llama-3-70b-instruct",
+ "hugging_face_id": "meta-llama/Meta-Llama-3-70B-Instruct",
+ "name": "Meta: Llama 3 70B Instruct",
+ "created": 1713398400,
+ "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+ "context_length": 8192,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Llama3",
+ "instruct_type": "llama3"
+ },
+ "pricing": {
+ "prompt": "0.0000003",
+ "completion": "0.0000004",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 8192,
+ "max_completion_tokens": 16384,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "max_tokens",
+ "min_p",
+ "presence_penalty",
+ "repetition_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
{
"id": "meta-llama/llama-3-8b-instruct",
"canonical_slug": "meta-llama/llama-3-8b-instruct",
@@ -15382,59 +16723,6 @@
],
"default_parameters": {}
},
- {
- "id": "meta-llama/llama-3-70b-instruct",
- "canonical_slug": "meta-llama/llama-3-70b-instruct",
- "hugging_face_id": "meta-llama/Meta-Llama-3-70B-Instruct",
- "name": "Meta: Llama 3 70B Instruct",
- "created": 1713398400,
- "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
- "context_length": 8192,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Llama3",
- "instruct_type": "llama3"
- },
- "pricing": {
- "prompt": "0.0000003",
- "completion": "0.0000004",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 8192,
- "max_completion_tokens": 16384,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "seed",
- "stop",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "mistralai/mixtral-8x22b-instruct",
"canonical_slug": "mistralai/mixtral-8x22b-instruct",
@@ -15455,8 +16743,8 @@
"instruct_type": "mistral"
},
"pricing": {
- "prompt": "0.0000009",
- "completion": "0.0000009",
+ "prompt": "0.000002",
+ "completion": "0.000006",
"request": "0",
"image": "0",
"web_search": "0",
@@ -15470,11 +16758,8 @@
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
- "logprobs",
"max_tokens",
"presence_penalty",
- "repetition_penalty",
"response_format",
"seed",
"stop",
@@ -15482,8 +16767,6 @@
"temperature",
"tool_choice",
"tools",
- "top_k",
- "top_logprobs",
"top_p"
],
"default_parameters": {
@@ -15734,57 +17017,6 @@
"temperature": 0.3
}
},
- {
- "id": "openai/gpt-3.5-turbo-0613",
- "canonical_slug": "openai/gpt-3.5-turbo-0613",
- "hugging_face_id": null,
- "name": "OpenAI: GPT-3.5 Turbo (older v0613)",
- "created": 1706140800,
- "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.",
- "context_length": 4095,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "GPT",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.000001",
- "completion": "0.000002",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 4095,
- "max_completion_tokens": 4096,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "presence_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "openai/gpt-4-turbo-preview",
"canonical_slug": "openai/gpt-4-turbo-preview",
@@ -15836,6 +17068,57 @@
],
"default_parameters": {}
},
+ {
+ "id": "openai/gpt-3.5-turbo-0613",
+ "canonical_slug": "openai/gpt-3.5-turbo-0613",
+ "hugging_face_id": null,
+ "name": "OpenAI: GPT-3.5 Turbo (older v0613)",
+ "created": 1706140800,
+ "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.",
+ "context_length": 4095,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.000001",
+ "completion": "0.000002",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 4095,
+ "max_completion_tokens": 4096,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {}
+ },
{
"id": "mistralai/mistral-tiny",
"canonical_slug": "mistralai/mistral-tiny",
@@ -15886,56 +17169,6 @@
"temperature": 0.3
}
},
- {
- "id": "mistralai/mistral-small",
- "canonical_slug": "mistralai/mistral-small",
- "hugging_face_id": null,
- "name": "Mistral Small",
- "created": 1704844800,
- "description": "With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between (Mistral NeMo 12B)[/mistralai/mistral-nemo] and (Mistral Large 2)[/mistralai/mistral-large], providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.",
- "context_length": 32768,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000002",
- "completion": "0.0000006",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 32768,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "max_tokens",
- "presence_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "mistralai/mistral-7b-instruct-v0.2",
"canonical_slug": "mistralai/mistral-7b-instruct-v0.2",
@@ -16111,8 +17344,8 @@
"instruct_type": "airoboros"
},
"pricing": {
- "prompt": "0.000004",
- "completion": "0.0000055",
+ "prompt": "0.000006",
+ "completion": "0.000008",
"request": "0",
"image": "0",
"web_search": "0",
@@ -16120,7 +17353,7 @@
},
"top_provider": {
"context_length": 6144,
- "max_completion_tokens": 512,
+ "max_completion_tokens": 1024,
"is_moderated": false
},
"per_request_limits": null,
@@ -16135,7 +17368,6 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"top_a",
"top_k",
@@ -16150,7 +17382,7 @@
"hugging_face_id": null,
"name": "Auto Router",
"created": 1699401600,
- "description": "Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.\n\nTo see which model was used, visit [Activity](/activity), or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model.\n\nThe meta-model is powered by [Not Diamond](https://docs.notdiamond.ai/docs/how-not-diamond-works). Learn more in our [docs](/docs/model-routing).\n\nRequests will be routed to the following models:\n- [openai/gpt-5](/openai/gpt-5)\n- [openai/gpt-5-mini](/openai/gpt-5-mini)\n- [openai/gpt-5-nano](/openai/gpt-5-nano)\n- [openai/gpt-4.1-nano](/openai/gpt-4.1-nano)\n- [openai/gpt-4.1](/openai/gpt-4.1)\n- [openai/gpt-4.1-mini](/openai/gpt-4.1-mini)\n- [openai/gpt-4.1](/openai/gpt-4.1)\n- [openai/gpt-4o-mini](/openai/gpt-4o-mini)\n- [openai/chatgpt-4o-latest](/openai/chatgpt-4o-latest)\n- [anthropic/claude-3.5-haiku](/anthropic/claude-3.5-haiku)\n- [anthropic/claude-opus-4-1](/anthropic/claude-opus-4-1)\n- [anthropic/claude-sonnet-4-0](/anthropic/claude-sonnet-4-0)\n- [anthropic/claude-3-7-sonnet-latest](/anthropic/claude-3-7-sonnet-latest)\n- [google/gemini-2.5-pro](/google/gemini-2.5-pro)\n- [google/gemini-2.5-flash](/google/gemini-2.5-flash)\n- [mistral/mistral-large-latest](/mistral/mistral-large-latest)\n- [mistral/mistral-medium-latest](/mistral/mistral-medium-latest)\n- [mistral/mistral-small-latest](/mistral/mistral-small-latest)\n- [mistralai/mistral-nemo](/mistralai/mistral-nemo)\n- [x-ai/grok-3](/x-ai/grok-3)\n- [x-ai/grok-3-mini](/x-ai/grok-3-mini)\n- [x-ai/grok-4](/x-ai/grok-4)\n- [deepseek/deepseek-r1](/deepseek/deepseek-r1)\n- [meta-llama/llama-3.1-70b-instruct](/meta-llama/llama-3.1-70b-instruct)\n- [meta-llama/llama-3.1-405b-instruct](/meta-llama/llama-3.1-405b-instruct)\n- [mistralai/mixtral-8x22b-instruct](/mistralai/mixtral-8x22b-instruct)\n- [perplexity/sonar](/perplexity/sonar)\n- [cohere/command-r-plus](/cohere/command-r-plus)\n- [cohere/command-r](/cohere/command-r)",
+ "description": "Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.\n\nTo see which model was used, visit [Activity](/activity), or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model.\n\nThe meta-model is powered by [Not Diamond](https://docs.notdiamond.ai/docs/how-not-diamond-works). Learn more in our [docs](/docs/model-routing).\n\nRequests will be routed to the following models:\n- [openai/gpt-5.1](/openai/gpt-5.1)\n- [openai/gpt-5](/openai/gpt-5)\n- [openai/gpt-5-mini](/openai/gpt-5-mini)\n- [openai/gpt-5-nano](/openai/gpt-5-nano)\n- [openai/gpt-4.1](/openai/gpt-4.1)\n- [openai/gpt-4.1-mini](/openai/gpt-4.1-mini)\n- [openai/gpt-4.1-nano](/openai/gpt-4.1-nano)\n- [openai/gpt-4o](/openai/gpt-4o)\n- [openai/gpt-4o-2024-05-13](/openai/gpt-4o-2024-05-13)\n- [openai/gpt-4o-2024-08-06](/openai/gpt-4o-2024-08-06)\n- [openai/gpt-4o-2024-11-20](/openai/gpt-4o-2024-11-20)\n- [openai/gpt-4o-mini](/openai/gpt-4o-mini)\n- [openai/gpt-4o-mini-2024-07-18](/openai/gpt-4o-mini-2024-07-18)\n- [openai/gpt-4-turbo](/openai/gpt-4-turbo)\n- [openai/gpt-4-turbo-preview](/openai/gpt-4-turbo-preview)\n- [openai/gpt-4-1106-preview](/openai/gpt-4-1106-preview)\n- [openai/gpt-4](/openai/gpt-4)\n- [openai/gpt-3.5-turbo](/openai/gpt-3.5-turbo)\n- [openai/gpt-oss-120b](/openai/gpt-oss-120b)\n- [anthropic/claude-opus-4.5](/anthropic/claude-opus-4.5)\n- [anthropic/claude-opus-4.1](/anthropic/claude-opus-4.1)\n- [anthropic/claude-opus-4](/anthropic/claude-opus-4)\n- [anthropic/claude-sonnet-4.5](/anthropic/claude-sonnet-4.5)\n- [anthropic/claude-sonnet-4](/anthropic/claude-sonnet-4)\n- [anthropic/claude-3.7-sonnet](/anthropic/claude-3.7-sonnet)\n- [anthropic/claude-haiku-4.5](/anthropic/claude-haiku-4.5)\n- [anthropic/claude-3.5-haiku](/anthropic/claude-3.5-haiku)\n- [anthropic/claude-3-haiku](/anthropic/claude-3-haiku)\n- [google/gemini-3-pro-preview](/google/gemini-3-pro-preview)\n- [google/gemini-2.5-pro](/google/gemini-2.5-pro)\n- [google/gemini-2.0-flash-001](/google/gemini-2.0-flash-001)\n- [google/gemini-2.5-flash](/google/gemini-2.5-flash)\n- [mistralai/mistral-large](/mistralai/mistral-large)\n- [mistralai/mistral-large-2407](/mistralai/mistral-large-2407)\n- [mistralai/mistral-large-2411](/mistralai/mistral-large-2411)\n- [mistralai/mistral-medium-3.1](/mistralai/mistral-medium-3.1)\n- [mistralai/mistral-nemo](/mistralai/mistral-nemo)\n- [mistralai/mistral-7b-instruct](/mistralai/mistral-7b-instruct)\n- [mistralai/mixtral-8x7b-instruct](/mistralai/mixtral-8x7b-instruct)\n- [mistralai/mixtral-8x22b-instruct](/mistralai/mixtral-8x22b-instruct)\n- [mistralai/codestral-2508](/mistralai/codestral-2508)\n- [x-ai/grok-4](/x-ai/grok-4)\n- [x-ai/grok-3](/x-ai/grok-3)\n- [x-ai/grok-3-mini](/x-ai/grok-3-mini)\n- [deepseek/deepseek-r1](/deepseek/deepseek-r1)\n- [meta-llama/llama-3.3-70b-instruct](/meta-llama/llama-3.3-70b-instruct)\n- [meta-llama/llama-3.1-405b-instruct](/meta-llama/llama-3.1-405b-instruct)\n- [meta-llama/llama-3.1-70b-instruct](/meta-llama/llama-3.1-70b-instruct)\n- [meta-llama/llama-3.1-8b-instruct](/meta-llama/llama-3.1-8b-instruct)\n- [meta-llama/llama-3-70b-instruct](/meta-llama/llama-3-70b-instruct)\n- [meta-llama/llama-3-8b-instruct](/meta-llama/llama-3-8b-instruct)\n- [qwen/qwen3-235b-a22b](/qwen/qwen3-235b-a22b)\n- [qwen/qwen3-32b](/qwen/qwen3-32b)\n- [qwen/qwen3-14b](/qwen/qwen3-14b)\n- [cohere/command-r-plus-08-2024](/cohere/command-r-plus-08-2024)\n- [cohere/command-r-08-2024](/cohere/command-r-08-2024)\n- [moonshotai/kimi-k2-thinking](/moonshotai/kimi-k2-thinking)\n- [perplexity/sonar](/perplexity/sonar)",
"context_length": 2000000,
"architecture": {
"modality": "text->text",
@@ -16227,58 +17459,6 @@
],
"default_parameters": {}
},
- {
- "id": "mistralai/mistral-7b-instruct-v0.1",
- "canonical_slug": "mistralai/mistral-7b-instruct-v0.1",
- "hugging_face_id": "mistralai/Mistral-7B-Instruct-v0.1",
- "name": "Mistral: Mistral 7B Instruct v0.1",
- "created": 1695859200,
- "description": "A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.",
- "context_length": 2824,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "Mistral",
- "instruct_type": "mistral"
- },
- "pricing": {
- "prompt": "0.00000011",
- "completion": "0.00000019",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 2824,
- "max_completion_tokens": null,
- "is_moderated": false
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "seed",
- "stop",
- "temperature",
- "tool_choice",
- "tools",
- "top_k",
- "top_p"
- ],
- "default_parameters": {
- "temperature": 0.3
- }
- },
{
"id": "openai/gpt-3.5-turbo-instruct",
"canonical_slug": "openai/gpt-3.5-turbo-instruct",
@@ -16328,6 +17508,53 @@
],
"default_parameters": {}
},
+ {
+ "id": "mistralai/mistral-7b-instruct-v0.1",
+ "canonical_slug": "mistralai/mistral-7b-instruct-v0.1",
+ "hugging_face_id": "mistralai/Mistral-7B-Instruct-v0.1",
+ "name": "Mistral: Mistral 7B Instruct v0.1",
+ "created": 1695859200,
+ "description": "A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.",
+ "context_length": 2824,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "Mistral",
+ "instruct_type": "mistral"
+ },
+ "pricing": {
+ "prompt": "0.00000011",
+ "completion": "0.00000019",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 2824,
+ "max_completion_tokens": null,
+ "is_moderated": false
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "repetition_penalty",
+ "seed",
+ "temperature",
+ "top_k",
+ "top_p"
+ ],
+ "default_parameters": {
+ "temperature": 0.3
+ }
+ },
{
"id": "openai/gpt-3.5-turbo-16k",
"canonical_slug": "openai/gpt-3.5-turbo-16k",
@@ -16399,8 +17626,8 @@
"instruct_type": "alpaca"
},
"pricing": {
- "prompt": "0.000001125",
- "completion": "0.000001125",
+ "prompt": "0.00000075",
+ "completion": "0.000001",
"request": "0",
"image": "0",
"web_search": "0",
@@ -16423,7 +17650,6 @@
"response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"top_a",
"top_k",
@@ -16505,8 +17731,8 @@
"instruct_type": "alpaca"
},
"pricing": {
- "prompt": "0.00000005",
- "completion": "0.00000009",
+ "prompt": "0.00000006",
+ "completion": "0.00000006",
"request": "0",
"image": "0",
"web_search": "0",
@@ -16514,7 +17740,7 @@
},
"top_provider": {
"context_length": 4096,
- "max_completion_tokens": 4096,
+ "max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
@@ -16538,57 +17764,6 @@
],
"default_parameters": {}
},
- {
- "id": "openai/gpt-3.5-turbo",
- "canonical_slug": "openai/gpt-3.5-turbo",
- "hugging_face_id": null,
- "name": "OpenAI: GPT-3.5 Turbo",
- "created": 1685232000,
- "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.",
- "context_length": 16385,
- "architecture": {
- "modality": "text->text",
- "input_modalities": [
- "text"
- ],
- "output_modalities": [
- "text"
- ],
- "tokenizer": "GPT",
- "instruct_type": null
- },
- "pricing": {
- "prompt": "0.0000005",
- "completion": "0.0000015",
- "request": "0",
- "image": "0",
- "web_search": "0",
- "internal_reasoning": "0"
- },
- "top_provider": {
- "context_length": 16385,
- "max_completion_tokens": 4096,
- "is_moderated": true
- },
- "per_request_limits": null,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "logprobs",
- "max_tokens",
- "presence_penalty",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_logprobs",
- "top_p"
- ],
- "default_parameters": {}
- },
{
"id": "openai/gpt-4-0314",
"canonical_slug": "openai/gpt-4-0314",
@@ -16690,6 +17865,57 @@
"top_p"
],
"default_parameters": {}
+ },
+ {
+ "id": "openai/gpt-3.5-turbo",
+ "canonical_slug": "openai/gpt-3.5-turbo",
+ "hugging_face_id": null,
+ "name": "OpenAI: GPT-3.5 Turbo",
+ "created": 1685232000,
+ "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.",
+ "context_length": 16385,
+ "architecture": {
+ "modality": "text->text",
+ "input_modalities": [
+ "text"
+ ],
+ "output_modalities": [
+ "text"
+ ],
+ "tokenizer": "GPT",
+ "instruct_type": null
+ },
+ "pricing": {
+ "prompt": "0.0000005",
+ "completion": "0.0000015",
+ "request": "0",
+ "image": "0",
+ "web_search": "0",
+ "internal_reasoning": "0"
+ },
+ "top_provider": {
+ "context_length": 16385,
+ "max_completion_tokens": 4096,
+ "is_moderated": true
+ },
+ "per_request_limits": null,
+ "supported_parameters": [
+ "frequency_penalty",
+ "logit_bias",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_logprobs",
+ "top_p"
+ ],
+ "default_parameters": {}
}
]
}
\ No newline at end of file
diff --git a/packages/kbot/dist-in/src/models/cache/openai.ts b/packages/kbot/dist-in/src/models/cache/openai.ts
index 5c8b82e1..903d9e9c 100644
--- a/packages/kbot/dist-in/src/models/cache/openai.ts
+++ b/packages/kbot/dist-in/src/models/cache/openai.ts
@@ -1 +1 @@
-export const models = [{"id":"gpt-4-0613","object":"model","created":1686588896,"owned_by":"openai"},{"id":"gpt-4","object":"model","created":1687882411,"owned_by":"openai"},{"id":"gpt-3.5-turbo","object":"model","created":1677610602,"owned_by":"openai"},{"id":"sora-2-pro","object":"model","created":1759708663,"owned_by":"system"},{"id":"gpt-audio-mini-2025-10-06","object":"model","created":1759512137,"owned_by":"system"},{"id":"gpt-realtime-mini","object":"model","created":1759517133,"owned_by":"system"},{"id":"gpt-realtime-mini-2025-10-06","object":"model","created":1759517175,"owned_by":"system"},{"id":"sora-2","object":"model","created":1759708615,"owned_by":"system"},{"id":"davinci-002","object":"model","created":1692634301,"owned_by":"system"},{"id":"babbage-002","object":"model","created":1692634615,"owned_by":"system"},{"id":"gpt-3.5-turbo-instruct","object":"model","created":1692901427,"owned_by":"system"},{"id":"gpt-3.5-turbo-instruct-0914","object":"model","created":1694122472,"owned_by":"system"},{"id":"dall-e-3","object":"model","created":1698785189,"owned_by":"system"},{"id":"dall-e-2","object":"model","created":1698798177,"owned_by":"system"},{"id":"gpt-4-1106-preview","object":"model","created":1698957206,"owned_by":"system"},{"id":"gpt-3.5-turbo-1106","object":"model","created":1698959748,"owned_by":"system"},{"id":"tts-1-hd","object":"model","created":1699046015,"owned_by":"system"},{"id":"tts-1-1106","object":"model","created":1699053241,"owned_by":"system"},{"id":"tts-1-hd-1106","object":"model","created":1699053533,"owned_by":"system"},{"id":"text-embedding-3-small","object":"model","created":1705948997,"owned_by":"system"},{"id":"text-embedding-3-large","object":"model","created":1705953180,"owned_by":"system"},{"id":"gpt-4-0125-preview","object":"model","created":1706037612,"owned_by":"system"},{"id":"gpt-4-turbo-preview","object":"model","created":1706037777,"owned_by":"system"},{"id":"gpt-3.5-turbo-0125","object":"model","created":1706048358,"owned_by":"system"},{"id":"gpt-4-turbo","object":"model","created":1712361441,"owned_by":"system"},{"id":"gpt-4-turbo-2024-04-09","object":"model","created":1712601677,"owned_by":"system"},{"id":"gpt-4o","object":"model","created":1715367049,"owned_by":"system"},{"id":"gpt-4o-2024-05-13","object":"model","created":1715368132,"owned_by":"system"},{"id":"gpt-4o-mini-2024-07-18","object":"model","created":1721172717,"owned_by":"system"},{"id":"gpt-4o-mini","object":"model","created":1721172741,"owned_by":"system"},{"id":"gpt-4o-2024-08-06","object":"model","created":1722814719,"owned_by":"system"},{"id":"chatgpt-4o-latest","object":"model","created":1723515131,"owned_by":"system"},{"id":"o1-mini-2024-09-12","object":"model","created":1725648979,"owned_by":"system"},{"id":"o1-mini","object":"model","created":1725649008,"owned_by":"system"},{"id":"gpt-4o-realtime-preview-2024-10-01","object":"model","created":1727131766,"owned_by":"system"},{"id":"gpt-4o-audio-preview-2024-10-01","object":"model","created":1727389042,"owned_by":"system"},{"id":"gpt-4o-audio-preview","object":"model","created":1727460443,"owned_by":"system"},{"id":"gpt-4o-realtime-preview","object":"model","created":1727659998,"owned_by":"system"},{"id":"omni-moderation-latest","object":"model","created":1731689265,"owned_by":"system"},{"id":"omni-moderation-2024-09-26","object":"model","created":1732734466,"owned_by":"system"},{"id":"gpt-4o-realtime-preview-2024-12-17","object":"model","created":1733945430,"owned_by":"system"},{"id":"gpt-4o-audio-preview-2024-12-17","object":"model","created":1734034239,"owned_by":"system"},{"id":"gpt-4o-mini-realtime-preview-2024-12-17","object":"model","created":1734112601,"owned_by":"system"},{"id":"gpt-4o-mini-audio-preview-2024-12-17","object":"model","created":1734115920,"owned_by":"system"},{"id":"o1-2024-12-17","object":"model","created":1734326976,"owned_by":"system"},{"id":"o1","object":"model","created":1734375816,"owned_by":"system"},{"id":"gpt-4o-mini-realtime-preview","object":"model","created":1734387380,"owned_by":"system"},{"id":"gpt-4o-mini-audio-preview","object":"model","created":1734387424,"owned_by":"system"},{"id":"o3-mini","object":"model","created":1737146383,"owned_by":"system"},{"id":"o3-mini-2025-01-31","object":"model","created":1738010200,"owned_by":"system"},{"id":"gpt-4o-2024-11-20","object":"model","created":1739331543,"owned_by":"system"},{"id":"gpt-4o-search-preview-2025-03-11","object":"model","created":1741388170,"owned_by":"system"},{"id":"gpt-4o-search-preview","object":"model","created":1741388720,"owned_by":"system"},{"id":"gpt-4o-mini-search-preview-2025-03-11","object":"model","created":1741390858,"owned_by":"system"},{"id":"gpt-4o-mini-search-preview","object":"model","created":1741391161,"owned_by":"system"},{"id":"gpt-4o-transcribe","object":"model","created":1742068463,"owned_by":"system"},{"id":"gpt-4o-mini-transcribe","object":"model","created":1742068596,"owned_by":"system"},{"id":"o1-pro-2025-03-19","object":"model","created":1742251504,"owned_by":"system"},{"id":"o1-pro","object":"model","created":1742251791,"owned_by":"system"},{"id":"gpt-4o-mini-tts","object":"model","created":1742403959,"owned_by":"system"},{"id":"o3-2025-04-16","object":"model","created":1744133301,"owned_by":"system"},{"id":"o4-mini-2025-04-16","object":"model","created":1744133506,"owned_by":"system"},{"id":"o3","object":"model","created":1744225308,"owned_by":"system"},{"id":"o4-mini","object":"model","created":1744225351,"owned_by":"system"},{"id":"gpt-4.1-2025-04-14","object":"model","created":1744315746,"owned_by":"system"},{"id":"gpt-4.1","object":"model","created":1744316542,"owned_by":"system"},{"id":"gpt-4.1-mini-2025-04-14","object":"model","created":1744317547,"owned_by":"system"},{"id":"gpt-4.1-mini","object":"model","created":1744318173,"owned_by":"system"},{"id":"gpt-4.1-nano-2025-04-14","object":"model","created":1744321025,"owned_by":"system"},{"id":"gpt-4.1-nano","object":"model","created":1744321707,"owned_by":"system"},{"id":"gpt-image-1","object":"model","created":1745517030,"owned_by":"system"},{"id":"codex-mini-latest","object":"model","created":1746673257,"owned_by":"system"},{"id":"gpt-4o-realtime-preview-2025-06-03","object":"model","created":1748907838,"owned_by":"system"},{"id":"gpt-4o-audio-preview-2025-06-03","object":"model","created":1748908498,"owned_by":"system"},{"id":"o4-mini-deep-research","object":"model","created":1749685485,"owned_by":"system"},{"id":"o4-mini-deep-research-2025-06-26","object":"model","created":1750866121,"owned_by":"system"},{"id":"gpt-5-chat-latest","object":"model","created":1754073306,"owned_by":"system"},{"id":"gpt-5-2025-08-07","object":"model","created":1754075360,"owned_by":"system"},{"id":"gpt-5","object":"model","created":1754425777,"owned_by":"system"},{"id":"gpt-5-mini-2025-08-07","object":"model","created":1754425867,"owned_by":"system"},{"id":"gpt-5-mini","object":"model","created":1754425928,"owned_by":"system"},{"id":"gpt-5-nano-2025-08-07","object":"model","created":1754426303,"owned_by":"system"},{"id":"gpt-5-nano","object":"model","created":1754426384,"owned_by":"system"},{"id":"gpt-audio-2025-08-28","object":"model","created":1756256146,"owned_by":"system"},{"id":"gpt-realtime","object":"model","created":1756271701,"owned_by":"system"},{"id":"gpt-realtime-2025-08-28","object":"model","created":1756271773,"owned_by":"system"},{"id":"gpt-audio","object":"model","created":1756339249,"owned_by":"system"},{"id":"gpt-5-codex","object":"model","created":1757527818,"owned_by":"system"},{"id":"gpt-image-1-mini","object":"model","created":1758845821,"owned_by":"system"},{"id":"gpt-5-pro-2025-10-06","object":"model","created":1759469707,"owned_by":"system"},{"id":"gpt-5-pro","object":"model","created":1759469822,"owned_by":"system"},{"id":"gpt-audio-mini","object":"model","created":1759512027,"owned_by":"system"},{"id":"gpt-3.5-turbo-16k","object":"model","created":1683758102,"owned_by":"openai-internal"},{"id":"tts-1","object":"model","created":1681940951,"owned_by":"openai-internal"},{"id":"whisper-1","object":"model","created":1677532384,"owned_by":"openai-internal"},{"id":"text-embedding-ada-002","object":"model","created":1671217299,"owned_by":"openai-internal"}]
\ No newline at end of file
+export const models = [{"id":"gpt-4-0613","object":"model","created":1686588896,"owned_by":"openai"},{"id":"gpt-4","object":"model","created":1687882411,"owned_by":"openai"},{"id":"gpt-3.5-turbo","object":"model","created":1677610602,"owned_by":"openai"},{"id":"chatgpt-image-latest","object":"model","created":1765925279,"owned_by":"system"},{"id":"gpt-4o-mini-tts-2025-03-20","object":"model","created":1765610731,"owned_by":"system"},{"id":"gpt-4o-mini-tts-2025-12-15","object":"model","created":1765610837,"owned_by":"system"},{"id":"gpt-realtime-mini-2025-12-15","object":"model","created":1765612007,"owned_by":"system"},{"id":"gpt-audio-mini-2025-12-15","object":"model","created":1765760008,"owned_by":"system"},{"id":"davinci-002","object":"model","created":1692634301,"owned_by":"system"},{"id":"babbage-002","object":"model","created":1692634615,"owned_by":"system"},{"id":"gpt-3.5-turbo-instruct","object":"model","created":1692901427,"owned_by":"system"},{"id":"gpt-3.5-turbo-instruct-0914","object":"model","created":1694122472,"owned_by":"system"},{"id":"dall-e-3","object":"model","created":1698785189,"owned_by":"system"},{"id":"dall-e-2","object":"model","created":1698798177,"owned_by":"system"},{"id":"gpt-4-1106-preview","object":"model","created":1698957206,"owned_by":"system"},{"id":"gpt-3.5-turbo-1106","object":"model","created":1698959748,"owned_by":"system"},{"id":"tts-1-hd","object":"model","created":1699046015,"owned_by":"system"},{"id":"tts-1-1106","object":"model","created":1699053241,"owned_by":"system"},{"id":"tts-1-hd-1106","object":"model","created":1699053533,"owned_by":"system"},{"id":"text-embedding-3-small","object":"model","created":1705948997,"owned_by":"system"},{"id":"text-embedding-3-large","object":"model","created":1705953180,"owned_by":"system"},{"id":"gpt-4-0125-preview","object":"model","created":1706037612,"owned_by":"system"},{"id":"gpt-4-turbo-preview","object":"model","created":1706037777,"owned_by":"system"},{"id":"gpt-3.5-turbo-0125","object":"model","created":1706048358,"owned_by":"system"},{"id":"gpt-4-turbo","object":"model","created":1712361441,"owned_by":"system"},{"id":"gpt-4-turbo-2024-04-09","object":"model","created":1712601677,"owned_by":"system"},{"id":"gpt-4o","object":"model","created":1715367049,"owned_by":"system"},{"id":"gpt-4o-2024-05-13","object":"model","created":1715368132,"owned_by":"system"},{"id":"gpt-4o-mini-2024-07-18","object":"model","created":1721172717,"owned_by":"system"},{"id":"gpt-4o-mini","object":"model","created":1721172741,"owned_by":"system"},{"id":"gpt-4o-2024-08-06","object":"model","created":1722814719,"owned_by":"system"},{"id":"chatgpt-4o-latest","object":"model","created":1723515131,"owned_by":"system"},{"id":"gpt-4o-audio-preview","object":"model","created":1727460443,"owned_by":"system"},{"id":"gpt-4o-realtime-preview","object":"model","created":1727659998,"owned_by":"system"},{"id":"omni-moderation-latest","object":"model","created":1731689265,"owned_by":"system"},{"id":"omni-moderation-2024-09-26","object":"model","created":1732734466,"owned_by":"system"},{"id":"gpt-4o-realtime-preview-2024-12-17","object":"model","created":1733945430,"owned_by":"system"},{"id":"gpt-4o-audio-preview-2024-12-17","object":"model","created":1734034239,"owned_by":"system"},{"id":"gpt-4o-mini-realtime-preview-2024-12-17","object":"model","created":1734112601,"owned_by":"system"},{"id":"gpt-4o-mini-audio-preview-2024-12-17","object":"model","created":1734115920,"owned_by":"system"},{"id":"o1-2024-12-17","object":"model","created":1734326976,"owned_by":"system"},{"id":"o1","object":"model","created":1734375816,"owned_by":"system"},{"id":"gpt-4o-mini-realtime-preview","object":"model","created":1734387380,"owned_by":"system"},{"id":"gpt-4o-mini-audio-preview","object":"model","created":1734387424,"owned_by":"system"},{"id":"o3-mini","object":"model","created":1737146383,"owned_by":"system"},{"id":"o3-mini-2025-01-31","object":"model","created":1738010200,"owned_by":"system"},{"id":"gpt-4o-2024-11-20","object":"model","created":1739331543,"owned_by":"system"},{"id":"gpt-4o-search-preview-2025-03-11","object":"model","created":1741388170,"owned_by":"system"},{"id":"gpt-4o-search-preview","object":"model","created":1741388720,"owned_by":"system"},{"id":"gpt-4o-mini-search-preview-2025-03-11","object":"model","created":1741390858,"owned_by":"system"},{"id":"gpt-4o-mini-search-preview","object":"model","created":1741391161,"owned_by":"system"},{"id":"gpt-4o-transcribe","object":"model","created":1742068463,"owned_by":"system"},{"id":"gpt-4o-mini-transcribe","object":"model","created":1742068596,"owned_by":"system"},{"id":"o1-pro-2025-03-19","object":"model","created":1742251504,"owned_by":"system"},{"id":"o1-pro","object":"model","created":1742251791,"owned_by":"system"},{"id":"gpt-4o-mini-tts","object":"model","created":1742403959,"owned_by":"system"},{"id":"o3-2025-04-16","object":"model","created":1744133301,"owned_by":"system"},{"id":"o4-mini-2025-04-16","object":"model","created":1744133506,"owned_by":"system"},{"id":"o3","object":"model","created":1744225308,"owned_by":"system"},{"id":"o4-mini","object":"model","created":1744225351,"owned_by":"system"},{"id":"gpt-4.1-2025-04-14","object":"model","created":1744315746,"owned_by":"system"},{"id":"gpt-4.1","object":"model","created":1744316542,"owned_by":"system"},{"id":"gpt-4.1-mini-2025-04-14","object":"model","created":1744317547,"owned_by":"system"},{"id":"gpt-4.1-mini","object":"model","created":1744318173,"owned_by":"system"},{"id":"gpt-4.1-nano-2025-04-14","object":"model","created":1744321025,"owned_by":"system"},{"id":"gpt-4.1-nano","object":"model","created":1744321707,"owned_by":"system"},{"id":"gpt-image-1","object":"model","created":1745517030,"owned_by":"system"},{"id":"codex-mini-latest","object":"model","created":1746673257,"owned_by":"system"},{"id":"gpt-4o-realtime-preview-2025-06-03","object":"model","created":1748907838,"owned_by":"system"},{"id":"gpt-4o-audio-preview-2025-06-03","object":"model","created":1748908498,"owned_by":"system"},{"id":"o4-mini-deep-research","object":"model","created":1749685485,"owned_by":"system"},{"id":"gpt-4o-transcribe-diarize","object":"model","created":1750798887,"owned_by":"system"},{"id":"o4-mini-deep-research-2025-06-26","object":"model","created":1750866121,"owned_by":"system"},{"id":"gpt-5-chat-latest","object":"model","created":1754073306,"owned_by":"system"},{"id":"gpt-5-2025-08-07","object":"model","created":1754075360,"owned_by":"system"},{"id":"gpt-5","object":"model","created":1754425777,"owned_by":"system"},{"id":"gpt-5-mini-2025-08-07","object":"model","created":1754425867,"owned_by":"system"},{"id":"gpt-5-mini","object":"model","created":1754425928,"owned_by":"system"},{"id":"gpt-5-nano-2025-08-07","object":"model","created":1754426303,"owned_by":"system"},{"id":"gpt-5-nano","object":"model","created":1754426384,"owned_by":"system"},{"id":"gpt-audio-2025-08-28","object":"model","created":1756256146,"owned_by":"system"},{"id":"gpt-realtime","object":"model","created":1756271701,"owned_by":"system"},{"id":"gpt-realtime-2025-08-28","object":"model","created":1756271773,"owned_by":"system"},{"id":"gpt-audio","object":"model","created":1756339249,"owned_by":"system"},{"id":"gpt-5-codex","object":"model","created":1757527818,"owned_by":"system"},{"id":"gpt-image-1-mini","object":"model","created":1758845821,"owned_by":"system"},{"id":"gpt-5-pro-2025-10-06","object":"model","created":1759469707,"owned_by":"system"},{"id":"gpt-5-pro","object":"model","created":1759469822,"owned_by":"system"},{"id":"gpt-audio-mini","object":"model","created":1759512027,"owned_by":"system"},{"id":"gpt-audio-mini-2025-10-06","object":"model","created":1759512137,"owned_by":"system"},{"id":"gpt-5-search-api","object":"model","created":1759514629,"owned_by":"system"},{"id":"gpt-realtime-mini","object":"model","created":1759517133,"owned_by":"system"},{"id":"gpt-realtime-mini-2025-10-06","object":"model","created":1759517175,"owned_by":"system"},{"id":"sora-2","object":"model","created":1759708615,"owned_by":"system"},{"id":"sora-2-pro","object":"model","created":1759708663,"owned_by":"system"},{"id":"gpt-5-search-api-2025-10-14","object":"model","created":1760043960,"owned_by":"system"},{"id":"gpt-5.1-chat-latest","object":"model","created":1762547951,"owned_by":"system"},{"id":"gpt-5.1-2025-11-13","object":"model","created":1762800353,"owned_by":"system"},{"id":"gpt-5.1","object":"model","created":1762800673,"owned_by":"system"},{"id":"gpt-5.1-codex","object":"model","created":1762988221,"owned_by":"system"},{"id":"gpt-5.1-codex-mini","object":"model","created":1763007109,"owned_by":"system"},{"id":"gpt-5.1-codex-max","object":"model","created":1763671532,"owned_by":"system"},{"id":"gpt-image-1.5","object":"model","created":1764030620,"owned_by":"system"},{"id":"gpt-5.2-2025-12-11","object":"model","created":1765313028,"owned_by":"system"},{"id":"gpt-5.2","object":"model","created":1765313051,"owned_by":"system"},{"id":"gpt-5.2-pro-2025-12-11","object":"model","created":1765343959,"owned_by":"system"},{"id":"gpt-5.2-pro","object":"model","created":1765343983,"owned_by":"system"},{"id":"gpt-5.2-chat-latest","object":"model","created":1765344352,"owned_by":"system"},{"id":"gpt-4o-mini-transcribe-2025-12-15","object":"model","created":1765610407,"owned_by":"system"},{"id":"gpt-4o-mini-transcribe-2025-03-20","object":"model","created":1765610545,"owned_by":"system"},{"id":"gpt-3.5-turbo-16k","object":"model","created":1683758102,"owned_by":"openai-internal"},{"id":"tts-1","object":"model","created":1681940951,"owned_by":"openai-internal"},{"id":"whisper-1","object":"model","created":1677532384,"owned_by":"openai-internal"},{"id":"text-embedding-ada-002","object":"model","created":1671217299,"owned_by":"openai-internal"}]
\ No newline at end of file
diff --git a/packages/kbot/dist-in/src/models/cache/openrouter.ts b/packages/kbot/dist-in/src/models/cache/openrouter.ts
index 45fd73ba..05fd81c5 100644
--- a/packages/kbot/dist-in/src/models/cache/openrouter.ts
+++ b/packages/kbot/dist-in/src/models/cache/openrouter.ts
@@ -1 +1 @@
-export const models = [{"id":"inclusionai/ling-1t","name":"inclusionAI: Ling-1T","pricing":{"prompt":"0.000001","completion":"0.000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760316076,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"NVIDIA: Llama 3.3 Nemotron Super 49B V1.5","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760101395,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"baidu/ernie-4.5-21b-a3b-thinking","name":"Baidu: ERNIE 4.5 21B A3B Thinking","pricing":{"prompt":"0.00000007","completion":"0.00000028","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760048887,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false}},{"id":"google/gemini-2.5-flash-image","name":"Google: Gemini 2.5 Flash Image (Nano Banana)","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","web_search":"0","internal_reasoning":"0"},"created":1759870431,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","pricing":{"prompt":"0.00000029","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759794479,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","pricing":{"prompt":"0.00000029","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759794476,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","pricing":{"prompt":"0.000015","completion":"0.00012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759776663,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"z-ai/glm-4.6","name":"Z.AI: GLM 4.6","pricing":{"prompt":"0.0000005","completion":"0.00000175","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759235576,"top_provider":{"context_length":202752,"max_completion_tokens":202752,"is_moderated":false}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759161676,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","pricing":{"prompt":"0.00000027","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759150481,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","pricing":{"prompt":"0.0000003","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758931878,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","pricing":{"prompt":"0.00000085","completion":"0.00000125","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758891572,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false}},{"id":"google/gemini-2.5-flash-preview-09-2025","name":"Google: Gemini 2.5 Flash Preview 09-2025","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075","input_cache_write":"0.0000003833"},"created":1758820178,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"google/gemini-2.5-flash-lite-preview-09-2025","name":"Google: Gemini 2.5 Flash Lite Preview 09-2025","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758819686,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","pricing":{"prompt":"0.00000045","completion":"0.0000035","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758668690,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758668687,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-max","name":"Qwen: Qwen3 Max","pricing":{"prompt":"0.0000012","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000024"},"created":1758662808,"top_provider":{"context_length":256000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-coder-plus","name":"Qwen: Qwen3 Coder Plus","pricing":{"prompt":"0.000001","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000001"},"created":1758662707,"top_provider":{"context_length":128000,"max_completion_tokens":65536,"is_moderated":false}},{"id":"openai/gpt-5-codex","name":"OpenAI: GPT-5 Codex","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1758643403,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","pricing":{"prompt":"0.00000023","completion":"0.0000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758548275,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"x-ai/grok-4-fast","name":"xAI: Grok 4 Fast","pricing":{"prompt":"0.0000002","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000005"},"created":1758240090,"top_provider":{"context_length":2000000,"max_completion_tokens":30000,"is_moderated":false}},{"id":"alibaba/tongyi-deepresearch-30b-a3b:free","name":"Tongyi DeepResearch 30B A3B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758210804,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"alibaba/tongyi-deepresearch-30b-a3b","name":"Tongyi DeepResearch 30B A3B","pricing":{"prompt":"0.00000009","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758210804,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","pricing":{"prompt":"0.0000003","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000008"},"created":1758115536,"top_provider":{"context_length":128000,"max_completion_tokens":65536,"is_moderated":false}},{"id":"arcee-ai/afm-4.5b","name":"Arcee AI: AFM 4.5B","pricing":{"prompt":"0.000000048","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758040484,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":false}},{"id":"opengvlab/internvl3-78b","name":"OpenGVLab: InternVL3 78B","pricing":{"prompt":"0.00000007","completion":"0.00000026","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757962555,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","pricing":{"prompt":"0.00000014","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757612284,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","pricing":{"prompt":"0.0000001","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757612213,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"meituan/longcat-flash-chat:free","name":"Meituan: LongCat Flash Chat (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757427658,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"meituan/longcat-flash-chat","name":"Meituan: LongCat Flash Chat","pricing":{"prompt":"0.00000015","completion":"0.00000075","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757427658,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728","pricing":{"prompt":"0.0000004","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757347599,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen-plus-2025-07-28:thinking","name":"Qwen: Qwen Plus 0728 (thinking)","pricing":{"prompt":"0.0000004","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757347599,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"nvidia/nemotron-nano-9b-v2:free","name":"NVIDIA: Nemotron Nano 9B V2 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757106807,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/nemotron-nano-9b-v2","name":"NVIDIA: Nemotron Nano 9B V2","pricing":{"prompt":"0.00000004","completion":"0.00000016","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757106807,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","pricing":{"prompt":"0.00000039","completion":"0.0000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757021147,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"deepcogito/cogito-v2-preview-llama-109b-moe","name":"Cogito V2 Preview Llama 109B","pricing":{"prompt":"0.00000018","completion":"0.00000059","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756831568,"top_provider":{"context_length":32767,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepcogito/cogito-v2-preview-deepseek-671b","name":"Deep Cogito: Cogito V2 Preview Deepseek 671B","pricing":{"prompt":"0.00000125","completion":"0.00000125","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756830949,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"stepfun-ai/step3","name":"StepFun: Step3","pricing":{"prompt":"0.00000057","completion":"0.00000142","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756415375,"top_provider":{"context_length":65536,"max_completion_tokens":65536,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","pricing":{"prompt":"0.00000008","completion":"0.00000029","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756399192,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"x-ai/grok-code-fast-1","name":"xAI: Grok Code Fast 1","pricing":{"prompt":"0.0000002","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000002"},"created":1756238927,"top_provider":{"context_length":256000,"max_completion_tokens":10000,"is_moderated":false}},{"id":"nousresearch/hermes-4-70b","name":"Nous: Hermes 4 70B","pricing":{"prompt":"0.00000011","completion":"0.00000038","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756236182,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756235463,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"google/gemini-2.5-flash-image-preview","name":"Google: Gemini 2.5 Flash Image Preview (Nano Banana)","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","web_search":"0","internal_reasoning":"0"},"created":1756218977,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"deepseek/deepseek-chat-v3.1:free","name":"DeepSeek: DeepSeek V3.1 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755779628,"top_provider":{"context_length":163800,"max_completion_tokens":null,"is_moderated":true}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","pricing":{"prompt":"0.0000002","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755779628,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"openai/gpt-4o-audio-preview","name":"OpenAI: GPT-4o Audio","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","audio":"0.00004","web_search":"0","internal_reasoning":"0"},"created":1755233061,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755095639,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"baidu/ernie-4.5-21b-a3b","name":"Baidu: ERNIE 4.5 21B A3B","pricing":{"prompt":"0.00000007","completion":"0.00000028","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755034167,"top_provider":{"context_length":120000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"baidu/ernie-4.5-vl-28b-a3b","name":"Baidu: ERNIE 4.5 VL 28B A3B","pricing":{"prompt":"0.00000014","completion":"0.00000056","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755032836,"top_provider":{"context_length":30000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"z-ai/glm-4.5v","name":"Z.AI: GLM 4.5V","pricing":{"prompt":"0.0000006","completion":"0.0000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754922288,"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false}},{"id":"ai21/jamba-mini-1.7","name":"AI21: Jamba Mini 1.7","pricing":{"prompt":"0.0000002","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754670601,"top_provider":{"context_length":256000,"max_completion_tokens":4096,"is_moderated":false}},{"id":"ai21/jamba-large-1.7","name":"AI21: Jamba Large 1.7","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754669020,"top_provider":{"context_length":256000,"max_completion_tokens":4096,"is_moderated":false}},{"id":"openai/gpt-5-chat","name":"OpenAI: GPT-5 Chat","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1754587837,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1754587413,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","pricing":{"prompt":"0.00000025","completion":"0.000002","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000025"},"created":1754587407,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","pricing":{"prompt":"0.00000005","completion":"0.0000004","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000005"},"created":1754587402,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","pricing":{"prompt":"0.00000004","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414231,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"openai/gpt-oss-20b:free","name":"OpenAI: gpt-oss-20b (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414229,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","pricing":{"prompt":"0.00000003","completion":"0.00000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414229,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","pricing":{"prompt":"0.000015","completion":"0.000075","request":"0","image":"0.024","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000015","input_cache_write":"0.00001875"},"created":1754411591,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":false}},{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","pricing":{"prompt":"0.0000003","completion":"0.0000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754079630,"top_provider":{"context_length":256000,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","pricing":{"prompt":"0.00000006","completion":"0.00000025","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753972379,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","pricing":{"prompt":"0.00000008","completion":"0.00000033","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753806965,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"z-ai/glm-4.5","name":"Z.AI: GLM 4.5","pricing":{"prompt":"0.00000035","completion":"0.00000155","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753471347,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"z-ai/glm-4.5-air:free","name":"Z.AI: GLM 4.5 Air (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753471258,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"z-ai/glm-4.5-air","name":"Z.AI: GLM 4.5 Air","pricing":{"prompt":"0.00000014","completion":"0.00000086","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753471258,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","pricing":{"prompt":"0.00000011","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753449557,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"z-ai/glm-4-32b","name":"Z.AI: GLM 4 32B ","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753376617,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-coder:free","name":"Qwen: Qwen3 Coder 480B A35B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753230546,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","pricing":{"prompt":"0.00000022","completion":"0.00000095","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753230546,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","pricing":{"prompt":"0.0000001","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753205056,"top_provider":{"context_length":128000,"max_completion_tokens":2048,"is_moderated":false}},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000025","input_cache_write":"0.0000001833"},"created":1753200276,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","pricing":{"prompt":"0.00000008","completion":"0.00000055","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753119555,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"switchpoint/router","name":"Switchpoint Router","pricing":{"prompt":"0.00000085","completion":"0.0000034","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752272899,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"moonshotai/kimi-k2:free","name":"MoonshotAI: Kimi K2 0711 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752263252,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":true}},{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","pricing":{"prompt":"0.00000014","completion":"0.00000249","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752263252,"top_provider":{"context_length":63000,"max_completion_tokens":63000,"is_moderated":false}},{"id":"thudm/glm-4.1v-9b-thinking","name":"THUDM: GLM 4.1V 9B Thinking","pricing":{"prompt":"0.000000035","completion":"0.000000138","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752244385,"top_provider":{"context_length":65536,"max_completion_tokens":8000,"is_moderated":false}},{"id":"mistralai/devstral-medium","name":"Mistral: Devstral Medium","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752161321,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/devstral-small","name":"Mistral: Devstral Small 1.1","pricing":{"prompt":"0.00000007","completion":"0.00000028","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752160751,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition:free","name":"Venice: Uncensored (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752094966,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-4","name":"xAI: Grok 4","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000075"},"created":1752087689,"top_provider":{"context_length":256000,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3n-e2b-it:free","name":"Google: Gemma 3n 2B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752074904,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false}},{"id":"tencent/hunyuan-a13b-instruct:free","name":"Tencent: Hunyuan A13B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751987664,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","pricing":{"prompt":"0.00000003","completion":"0.00000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751987664,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"tngtech/deepseek-r1t2-chimera:free","name":"TNG: DeepSeek R1T2 Chimera (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751986985,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"tngtech/deepseek-r1t2-chimera","name":"TNG: DeepSeek R1T2 Chimera","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751986985,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","pricing":{"prompt":"0.0000009","completion":"0.0000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751910858,"top_provider":{"context_length":81920,"max_completion_tokens":38000,"is_moderated":false}},{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","pricing":{"prompt":"0.0000008","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751910002,"top_provider":{"context_length":81920,"max_completion_tokens":38000,"is_moderated":false}},{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"Baidu: ERNIE 4.5 VL 424B A47B ","pricing":{"prompt":"0.00000042","completion":"0.00000125","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751300903,"top_provider":{"context_length":123000,"max_completion_tokens":16000,"is_moderated":false}},{"id":"baidu/ernie-4.5-300b-a47b","name":"Baidu: ERNIE 4.5 300B A47B ","pricing":{"prompt":"0.00000028","completion":"0.0000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751300139,"top_provider":{"context_length":123000,"max_completion_tokens":12000,"is_moderated":false}},{"id":"thedrummer/anubis-70b-v1.1","name":"TheDrummer: Anubis 70B V1.1","pricing":{"prompt":"0.00000065","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751208347,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"inception/mercury","name":"Inception: Mercury","pricing":{"prompt":"0.00000025","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750973026,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mistral-small-3.2-24b-instruct:free","name":"Mistral: Mistral Small 3.2 24B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750443016,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","pricing":{"prompt":"0.00000006","completion":"0.00000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750443016,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","pricing":{"prompt":"0.0000004","completion":"0.0000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750200414,"top_provider":{"context_length":1000000,"max_completion_tokens":40000,"is_moderated":false}},{"id":"google/gemini-2.5-flash-lite-preview-06-17","name":"Google: Gemini 2.5 Flash Lite Preview 06-17","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","audio":"0.0000003","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000025","input_cache_write":"0.0000001833"},"created":1750173831,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075","input_cache_write":"0.0000003833"},"created":1750172488,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0.00516","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000031","input_cache_write":"0.000001625"},"created":1750169544,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"moonshotai/kimi-dev-72b:free","name":"MoonshotAI: Kimi Dev 72B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750115909,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"moonshotai/kimi-dev-72b","name":"MoonshotAI: Kimi Dev 72B","pricing":{"prompt":"0.00000029","completion":"0.00000115","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750115909,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","pricing":{"prompt":"0.00002","completion":"0.00008","request":"0","image":"0.0153","web_search":"0.01","internal_reasoning":"0"},"created":1749598352,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"x-ai/grok-3-mini","name":"xAI: Grok 3 Mini","pricing":{"prompt":"0.0000003","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1749583245,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-3","name":"xAI: Grok 3","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000075"},"created":1749582908,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/magistral-small-2506","name":"Mistral: Magistral Small 2506","pricing":{"prompt":"0.0000005","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1749569561,"top_provider":{"context_length":40000,"max_completion_tokens":40000,"is_moderated":false}},{"id":"mistralai/magistral-medium-2506","name":"Mistral: Magistral Medium 2506","pricing":{"prompt":"0.000002","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1749354054,"top_provider":{"context_length":40960,"max_completion_tokens":40000,"is_moderated":false}},{"id":"mistralai/magistral-medium-2506:thinking","name":"Mistral: Magistral Medium 2506 (thinking)","pricing":{"prompt":"0.000002","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1749354054,"top_provider":{"context_length":40960,"max_completion_tokens":40000,"is_moderated":false}},{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0.00516","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000031","input_cache_write":"0.000001625"},"created":1749137257,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528-qwen3-8b:free","name":"DeepSeek: Deepseek R1 0528 Qwen3 8B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748538543,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek: Deepseek R1 0528 Qwen3 8B","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748538543,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528:free","name":"DeepSeek: R1 0528 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748455170,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","pricing":{"prompt":"0.0000004","completion":"0.00000175","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748455170,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4","pricing":{"prompt":"0.000015","completion":"0.000075","request":"0","image":"0.024","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000015","input_cache_write":"0.00001875"},"created":1747931245,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":false}},{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1747930371,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"mistralai/devstral-small-2505:free","name":"Mistral: Devstral Small 2505 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747837379,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/devstral-small-2505","name":"Mistral: Devstral Small 2505","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747837379,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"google/gemma-3n-e4b-it:free","name":"Google: Gemma 3n 4B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747776824,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false}},{"id":"google/gemma-3n-e4b-it","name":"Google: Gemma 3n 4B","pricing":{"prompt":"0.00000002","completion":"0.00000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747776824,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/codex-mini","name":"OpenAI: Codex Mini","pricing":{"prompt":"0.0000015","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000375"},"created":1747409761,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"meta-llama/llama-3.3-8b-instruct:free","name":"Meta: Llama 3.3 8B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747230154,"top_provider":{"context_length":128000,"max_completion_tokens":4028,"is_moderated":true}},{"id":"nousresearch/deephermes-3-mistral-24b-preview","name":"Nous: DeepHermes 3 Mistral 24B Preview","pricing":{"prompt":"0.00000015","completion":"0.00000059","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746830904,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746627341,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemini-2.5-pro-preview-05-06","name":"Google: Gemini 2.5 Pro Preview 05-06","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0.00516","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000031","input_cache_write":"0.000001625"},"created":1746578513,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"arcee-ai/spotlight","name":"Arcee AI: Spotlight","pricing":{"prompt":"0.00000018","completion":"0.00000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746481552,"top_provider":{"context_length":131072,"max_completion_tokens":65537,"is_moderated":false}},{"id":"arcee-ai/maestro-reasoning","name":"Arcee AI: Maestro Reasoning","pricing":{"prompt":"0.0000009","completion":"0.0000033","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746481269,"top_provider":{"context_length":131072,"max_completion_tokens":32000,"is_moderated":false}},{"id":"arcee-ai/virtuoso-large","name":"Arcee AI: Virtuoso Large","pricing":{"prompt":"0.00000075","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746478885,"top_provider":{"context_length":131072,"max_completion_tokens":64000,"is_moderated":false}},{"id":"arcee-ai/coder-large","name":"Arcee AI: Coder Large","pricing":{"prompt":"0.0000005","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746478663,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-4-reasoning-plus","name":"Microsoft: Phi 4 Reasoning Plus","pricing":{"prompt":"0.00000007","completion":"0.00000035","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746130961,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"inception/mercury-coder","name":"Inception: Mercury Coder","pricing":{"prompt":"0.00000025","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746033880,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false}},{"id":"qwen/qwen3-4b:free","name":"Qwen: Qwen3 4B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746031104,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-prover-v2","name":"DeepSeek: DeepSeek Prover V2","pricing":{"prompt":"0.0000005","completion":"0.00000218","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746013094,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","pricing":{"prompt":"0.00000018","completion":"0.00000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745975193,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b:free","name":"Qwen: Qwen3 30B A3B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745878604,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","pricing":{"prompt":"0.00000006","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745878604,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-8b:free","name":"Qwen: Qwen3 8B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745876632,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-8b","name":"Qwen: Qwen3 8B","pricing":{"prompt":"0.000000035","completion":"0.000000138","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745876632,"top_provider":{"context_length":128000,"max_completion_tokens":20000,"is_moderated":false}},{"id":"qwen/qwen3-14b:free","name":"Qwen: Qwen3 14B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745876478,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745876478,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","pricing":{"prompt":"0.00000005","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745875945,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b:free","name":"Qwen: Qwen3 235B A22B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745875757,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b","name":"Qwen: Qwen3 235B A22B","pricing":{"prompt":"0.00000018","completion":"0.00000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745875757,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"tngtech/deepseek-r1t-chimera:free","name":"TNG: DeepSeek R1T Chimera (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745760875,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"tngtech/deepseek-r1t-chimera","name":"TNG: DeepSeek R1T Chimera","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745760875,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"microsoft/mai-ds-r1:free","name":"Microsoft: MAI DS R1 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745194100,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/mai-ds-r1","name":"Microsoft: MAI DS R1","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745194100,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"thudm/glm-z1-32b","name":"THUDM: GLM Z1 32B","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744924148,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0.0008415","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000275"},"created":1744824212,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"openai/o3","name":"OpenAI: o3","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0.00153","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000005"},"created":1744823457,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0.0008415","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000275"},"created":1744820942,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"shisa-ai/shisa-v2-llama3.3-70b:free","name":"Shisa AI: Shisa V2 Llama 3.3 70B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744754858,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"shisa-ai/shisa-v2-llama3.3-70b","name":"Shisa AI: Shisa V2 Llama 3.3 70B ","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744754858,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen2.5-coder-7b-instruct","name":"Qwen: Qwen2.5 Coder 7B Instruct","pricing":{"prompt":"0.00000003","completion":"0.00000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744734887,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000005"},"created":1744651385,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true}},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","pricing":{"prompt":"0.0000004","completion":"0.0000016","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000001"},"created":1744651381,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true}},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000025"},"created":1744651369,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true}},{"id":"eleutherai/llemma_7b","name":"EleutherAI: Llemma 7b","pricing":{"prompt":"0.0000008","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744643225,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"alfredpros/codellama-7b-instruct-solidity","name":"AlfredPros: CodeLLaMa 7B Instruct Solidity","pricing":{"prompt":"0.0000008","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744641874,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"arliai/qwq-32b-arliai-rpr-v1:free","name":"ArliAI: QwQ 32B RpR v1 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744555982,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"arliai/qwq-32b-arliai-rpr-v1","name":"ArliAI: QwQ 32B RpR v1","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744555982,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"agentica-org/deepcoder-14b-preview:free","name":"Agentica: Deepcoder 14B Preview (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744555395,"top_provider":{"context_length":96000,"max_completion_tokens":null,"is_moderated":false}},{"id":"agentica-org/deepcoder-14b-preview","name":"Agentica: Deepcoder 14B Preview","pricing":{"prompt":"0.000000015","completion":"0.000000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744555395,"top_provider":{"context_length":96000,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-3-mini-beta","name":"xAI: Grok 3 Mini Beta","pricing":{"prompt":"0.0000003","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1744240195,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-3-beta","name":"xAI: Grok 3 Beta","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000075"},"created":1744240068,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"NVIDIA: Llama 3.1 Nemotron Ultra 253B v1","pricing":{"prompt":"0.0000006","completion":"0.0000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744115059,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-4-maverick:free","name":"Meta: Llama 4 Maverick (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1743881822,"top_provider":{"context_length":128000,"max_completion_tokens":4028,"is_moderated":true}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0.0006684","web_search":"0","internal_reasoning":"0"},"created":1743881822,"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-4-scout:free","name":"Meta: Llama 4 Scout (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1743881519,"top_provider":{"context_length":128000,"max_completion_tokens":4028,"is_moderated":true}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","pricing":{"prompt":"0.00000008","completion":"0.0000003","request":"0","image":"0.0003342","web_search":"0","internal_reasoning":"0"},"created":1743881519,"top_provider":{"context_length":327680,"max_completion_tokens":16384,"is_moderated":false}},{"id":"allenai/molmo-7b-d","name":"AllenAI: Molmo 7B D","pricing":{"prompt":"0.0000001","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1743023247,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"qwen/qwen2.5-vl-32b-instruct:free","name":"Qwen: Qwen2.5 VL 32B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742839838,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen2.5-vl-32b-instruct","name":"Qwen: Qwen2.5 VL 32B Instruct","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742839838,"top_provider":{"context_length":16384,"max_completion_tokens":16384,"is_moderated":false}},{"id":"deepseek/deepseek-chat-v3-0324:free","name":"DeepSeek: DeepSeek V3 0324 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742824755,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","pricing":{"prompt":"0.00000024","completion":"0.00000084","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742824755,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"openai/o1-pro","name":"OpenAI: o1-pro","pricing":{"prompt":"0.00015","completion":"0.0006","request":"0","image":"0.21675","web_search":"0","internal_reasoning":"0"},"created":1742423211,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"mistralai/mistral-small-3.1-24b-instruct:free","name":"Mistral: Mistral Small 3.1 24B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742238937,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","pricing":{"prompt":"0.00000005","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742238937,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"allenai/olmo-2-0325-32b-instruct","name":"AllenAI: Olmo 2 32B Instruct","pricing":{"prompt":"0.0000002","completion":"0.00000035","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741988556,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"google/gemma-3-4b-it:free","name":"Google: Gemma 3 4B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741905510,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","pricing":{"prompt":"0.00000001703012","completion":"0.0000000681536","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741905510,"top_provider":{"context_length":96000,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3-12b-it:free","name":"Google: Gemma 3 12B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741902625,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","pricing":{"prompt":"0.00000003","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741902625,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"cohere/command-a","name":"Cohere: Command A","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741894342,"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"openai/gpt-4o-mini-search-preview","name":"OpenAI: GPT-4o-mini Search Preview","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0.0275","image":"0.000217","web_search":"0","internal_reasoning":"0"},"created":1741818122,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-4o-search-preview","name":"OpenAI: GPT-4o Search Preview","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0.035","image":"0.003613","web_search":"0","internal_reasoning":"0"},"created":1741817949,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"google/gemma-3-27b-it:free","name":"Google: Gemma 3 27B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741756359,"top_provider":{"context_length":96000,"max_completion_tokens":8192,"is_moderated":false}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","pricing":{"prompt":"0.00000009","completion":"0.00000016","request":"0","image":"0.0000256","web_search":"0","internal_reasoning":"0"},"created":1741756359,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","pricing":{"prompt":"0.00000008","completion":"0.00000033","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741636566,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"microsoft/phi-4-multimodal-instruct","name":"Microsoft: Phi 4 Multimodal Instruct","pricing":{"prompt":"0.00000005","completion":"0.0000001","request":"0","image":"0.00017685","web_search":"0","internal_reasoning":"0"},"created":1741396284,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0.005","internal_reasoning":"0"},"created":1741313308,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0.005","internal_reasoning":"0"},"created":1741312423,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0.005","internal_reasoning":"0.000003"},"created":1741311246,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwq-32b","name":"Qwen: QwQ 32B","pricing":{"prompt":"0.00000015","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741208814,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/deephermes-3-llama-3-8b-preview:free","name":"Nous: DeepHermes 3 Llama 3 8B Preview (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1740719372,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/deephermes-3-llama-3-8b-preview","name":"Nous: DeepHermes 3 Llama 3 8B Preview","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1740719372,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"google/gemini-2.0-flash-lite-001","name":"Google: Gemini 2.0 Flash Lite","pricing":{"prompt":"0.000000075","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1740506212,"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":false}},{"id":"anthropic/claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1740422110,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"anthropic/claude-3.7-sonnet:thinking","name":"Anthropic: Claude 3.7 Sonnet (thinking)","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1740422110,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"perplexity/r1-1776","name":"Perplexity: R1 1776","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1740004929,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-saba","name":"Mistral: Saba","pricing":{"prompt":"0.0000002","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1739803239,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"cognitivecomputations/dolphin3.0-mistral-24b:free","name":"Dolphin3.0 Mistral 24B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1739462019,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"cognitivecomputations/dolphin3.0-mistral-24b","name":"Dolphin3.0 Mistral 24B","pricing":{"prompt":"0.00000004","completion":"0.00000017","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1739462019,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"meta-llama/llama-guard-3-8b","name":"Llama Guard 3 8B","pricing":{"prompt":"0.00000002","completion":"0.00000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1739401318,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000055"},"created":1739372611,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"google/gemini-2.0-flash-001","name":"Google: Gemini 2.0 Flash","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0.0000258","audio":"0.0000007","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000025","input_cache_write":"0.0000001833"},"created":1738769413,"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen-vl-plus","name":"Qwen: Qwen VL Plus","pricing":{"prompt":"0.00000021","completion":"0.00000063","request":"0","image":"0.0002688","web_search":"0","internal_reasoning":"0"},"created":1738731255,"top_provider":{"context_length":7500,"max_completion_tokens":1500,"is_moderated":false}},{"id":"aion-labs/aion-1.0","name":"AionLabs: Aion-1.0","pricing":{"prompt":"0.000004","completion":"0.000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738697557,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"aion-labs/aion-1.0-mini","name":"AionLabs: Aion-1.0-Mini","pricing":{"prompt":"0.0000007","completion":"0.0000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738697107,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738696718,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen-vl-max","name":"Qwen: Qwen VL Max","pricing":{"prompt":"0.0000008","completion":"0.0000032","request":"0","image":"0.001024","web_search":"0","internal_reasoning":"0"},"created":1738434304,"top_provider":{"context_length":7500,"max_completion_tokens":1500,"is_moderated":false}},{"id":"qwen/qwen-turbo","name":"Qwen: Qwen-Turbo","pricing":{"prompt":"0.00000005","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000002"},"created":1738410974,"top_provider":{"context_length":1000000,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen2.5-vl-72b-instruct:free","name":"Qwen: Qwen2.5 VL 72B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738410311,"top_provider":{"context_length":131072,"max_completion_tokens":2048,"is_moderated":false}},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","pricing":{"prompt":"0.00000008","completion":"0.00000033","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738410311,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen-plus","name":"Qwen: Qwen-Plus","pricing":{"prompt":"0.0000004","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000016"},"created":1738409840,"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen-max","name":"Qwen: Qwen-Max ","pricing":{"prompt":"0.0000016","completion":"0.0000064","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000064"},"created":1738402289,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"openai/o3-mini","name":"OpenAI: o3 Mini","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000055"},"created":1738351721,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"mistralai/mistral-small-24b-instruct-2501:free","name":"Mistral: Mistral Small 3 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738255409,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","pricing":{"prompt":"0.00000005","completion":"0.00000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738255409,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek: R1 Distill Qwen 32B","pricing":{"prompt":"0.00000027","completion":"0.00000027","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738194830,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-qwen-14b","name":"DeepSeek: R1 Distill Qwen 14B","pricing":{"prompt":"0.00000015","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738193940,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"perplexity/sonar-reasoning","name":"Perplexity: Sonar Reasoning","pricing":{"prompt":"0.000001","completion":"0.000005","request":"0.005","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738131107,"top_provider":{"context_length":127000,"max_completion_tokens":null,"is_moderated":false}},{"id":"perplexity/sonar","name":"Perplexity: Sonar","pricing":{"prompt":"0.000001","completion":"0.000001","request":"0.005","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738013808,"top_provider":{"context_length":127072,"max_completion_tokens":null,"is_moderated":false}},{"id":"liquid/lfm-7b","name":"Liquid: LFM 7B","pricing":{"prompt":"0.00000001","completion":"0.00000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737806883,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"liquid/lfm-3b","name":"Liquid: LFM 3B","pricing":{"prompt":"0.00000002","completion":"0.00000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737806501,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-llama-70b:free","name":"DeepSeek: R1 Distill Llama 70B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737663169,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","pricing":{"prompt":"0.00000003","completion":"0.00000013","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737663169,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"deepseek/deepseek-r1:free","name":"DeepSeek: R1 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737381095,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737381095,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","pricing":{"prompt":"0.0000002","completion":"0.0000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736915462,"top_provider":{"context_length":1000192,"max_completion_tokens":1000192,"is_moderated":false}},{"id":"mistralai/codestral-2501","name":"Mistral: Codestral 2501","pricing":{"prompt":"0.0000003","completion":"0.0000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736895522,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-4","name":"Microsoft: Phi 4","pricing":{"prompt":"0.00000006","completion":"0.00000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736489872,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":false}},{"id":"sao10k/l3.1-70b-hanami-x1","name":"Sao10K: Llama 3.1 70B Hanami x1","pricing":{"prompt":"0.000003","completion":"0.000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736302854,"top_provider":{"context_length":16000,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","pricing":{"prompt":"0.0000003","completion":"0.00000085","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1735241320,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","pricing":{"prompt":"0.00000065","completion":"0.00000075","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1734535928,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/o1","name":"OpenAI: o1","pricing":{"prompt":"0.000015","completion":"0.00006","request":"0","image":"0.021675","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000075"},"created":1734459999,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","pricing":{"prompt":"0.0000000375","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1734158152,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true}},{"id":"google/gemini-2.0-flash-exp:free","name":"Google: Gemini 2.0 Flash Experimental (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733937523,"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":false}},{"id":"meta-llama/llama-3.3-70b-instruct:free","name":"Meta: Llama 3.3 70B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733506137,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","pricing":{"prompt":"0.00000013","completion":"0.00000039","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733506137,"top_provider":{"context_length":131072,"max_completion_tokens":120000,"is_moderated":false}},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","pricing":{"prompt":"0.00000006","completion":"0.00000024","request":"0","image":"0.00009","web_search":"0","internal_reasoning":"0"},"created":1733437363,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true}},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","pricing":{"prompt":"0.000000035","completion":"0.00000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733437237,"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true}},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","pricing":{"prompt":"0.0000008","completion":"0.0000032","request":"0","image":"0.0012","web_search":"0","internal_reasoning":"0"},"created":1733436303,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true}},{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0.003613","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1732127594,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"mistralai/mistral-large-2411","name":"Mistral Large 2411","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731978685,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731978415,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/pixtral-large-2411","name":"Mistral: Pixtral Large 2411","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0.002888","web_search":"0","internal_reasoning":"0"},"created":1731977388,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-coder-32b-instruct:free","name":"Qwen2.5 Coder 32B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731368400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","pricing":{"prompt":"0.00000004","completion":"0.00000016","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731368400,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"raifle/sorcererlm-8x22b","name":"SorcererLM 8x22B","pricing":{"prompt":"0.0000045","completion":"0.0000045","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731105083,"top_provider":{"context_length":16000,"max_completion_tokens":null,"is_moderated":false}},{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","pricing":{"prompt":"0.0000004","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731103448,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"anthropic/claude-3.5-haiku","name":"Anthropic: Claude 3.5 Haiku","pricing":{"prompt":"0.0000008","completion":"0.000004","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.00000008","input_cache_write":"0.000001"},"created":1730678400,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"anthropic/claude-3.5-haiku-20241022","name":"Anthropic: Claude 3.5 Haiku (2024-10-22)","pricing":{"prompt":"0.0000008","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000008","input_cache_write":"0.000001"},"created":1730678400,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":false}},{"id":"anthropic/claude-3.5-sonnet","name":"Anthropic: Claude 3.5 Sonnet","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1729555200,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","pricing":{"prompt":"0.0000025","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729555200,"top_provider":{"context_length":16384,"max_completion_tokens":2048,"is_moderated":false}},{"id":"mistralai/ministral-8b","name":"Mistral: Ministral 8B","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729123200,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/ministral-3b","name":"Mistral: Ministral 3B","pricing":{"prompt":"0.00000004","completion":"0.00000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729123200,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","pricing":{"prompt":"0.00000004","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729036800,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"NVIDIA: Llama 3.1 Nemotron 70B Instruct","pricing":{"prompt":"0.0000006","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1728950400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"inflection/inflection-3-productivity","name":"Inflection: Inflection 3 Productivity","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1728604800,"top_provider":{"context_length":8000,"max_completion_tokens":1024,"is_moderated":false}},{"id":"inflection/inflection-3-pi","name":"Inflection: Inflection 3 Pi","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1728604800,"top_provider":{"context_length":8000,"max_completion_tokens":1024,"is_moderated":false}},{"id":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","pricing":{"prompt":"0.00000017","completion":"0.00000043","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727654400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"anthracite-org/magnum-v2-72b","name":"Magnum v2 72B","pricing":{"prompt":"0.000003","completion":"0.000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727654400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.2-3b-instruct:free","name":"Meta: Llama 3.2 3B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","pricing":{"prompt":"0.00000002","completion":"0.00000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":16384,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","pricing":{"prompt":"0.000000005","completion":"0.00000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.2-11b-vision-instruct","name":"Meta: Llama 3.2 11B Vision Instruct","pricing":{"prompt":"0.000000049","completion":"0.000000049","request":"0","image":"0.00007948","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.2-90b-vision-instruct","name":"Meta: Llama 3.2 90B Vision Instruct","pricing":{"prompt":"0.00000035","completion":"0.0000004","request":"0","image":"0.0005058","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"qwen/qwen-2.5-72b-instruct:free","name":"Qwen2.5 72B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1726704000,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","pricing":{"prompt":"0.00000007","completion":"0.00000026","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1726704000,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"neversleep/llama-3.1-lumimaid-8b","name":"NeverSleep: Lumimaid v0.2 8B","pricing":{"prompt":"0.00000009","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1726358400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/o1-mini","name":"OpenAI: o1-mini","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000055"},"created":1726099200,"top_provider":{"context_length":128000,"max_completion_tokens":65536,"is_moderated":true}},{"id":"openai/o1-mini-2024-09-12","name":"OpenAI: o1-mini (2024-09-12)","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000055"},"created":1726099200,"top_provider":{"context_length":128000,"max_completion_tokens":65536,"is_moderated":true}},{"id":"mistralai/pixtral-12b","name":"Mistral: Pixtral 12B","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0.0001445","web_search":"0","internal_reasoning":"0"},"created":1725926400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724976000,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true}},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724976000,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true}},{"id":"qwen/qwen-2.5-vl-7b-instruct","name":"Qwen: Qwen2.5-VL 7B Instruct","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0.0001445","web_search":"0","internal_reasoning":"0"},"created":1724803200,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","pricing":{"prompt":"0.00000065","completion":"0.00000075","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724803200,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-3.5-mini-128k-instruct","name":"Microsoft: Phi-3.5 Mini 128K Instruct","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724198400,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","pricing":{"prompt":"0.0000003","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723939200,"top_provider":{"context_length":65000,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","pricing":{"prompt":"0.000001","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723766400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/chatgpt-4o-latest","name":"OpenAI: ChatGPT-4o","pricing":{"prompt":"0.000005","completion":"0.000015","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0"},"created":1723593600,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","pricing":{"prompt":"0.00000004","completion":"0.00000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723507200,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0.003613","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1722902400,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.1-405b","name":"Meta: Llama 3.1 405B (base)","pricing":{"prompt":"0.000004","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1722556800,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"meta-llama/llama-3.1-405b-instruct","name":"Meta: Llama 3.1 405B Instruct","pricing":{"prompt":"0.0000008","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","pricing":{"prompt":"0.00000002","completion":"0.00000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","pricing":{"prompt":"0.0000004","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-nemo:free","name":"Mistral: Mistral Nemo (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721347200,"top_provider":{"context_length":131072,"max_completion_tokens":128000,"is_moderated":false}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","pricing":{"prompt":"0.00000002","completion":"0.00000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721347200,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1721260800,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0.000217","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1721260800,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","pricing":{"prompt":"0.00000065","completion":"0.00000065","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1720828800,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-2-9b-it:free","name":"Google: Gemma 2 9B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1719532800,"top_provider":{"context_length":8192,"max_completion_tokens":8192,"is_moderated":false}},{"id":"google/gemma-2-9b-it","name":"Google: Gemma 2 9B","pricing":{"prompt":"0.00000001","completion":"0.00000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1719532800,"top_provider":{"context_length":8192,"max_completion_tokens":8192,"is_moderated":false}},{"id":"anthropic/claude-3.5-sonnet-20240620","name":"Anthropic: Claude 3.5 Sonnet (2024-06-20)","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1718841600,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"sao10k/l3-euryale-70b","name":"Sao10k: Llama 3 Euryale 70B v2.1","pricing":{"prompt":"0.00000148","completion":"0.00000148","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1718668800,"top_provider":{"context_length":8192,"max_completion_tokens":8192,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral: Mistral 7B Instruct v0.3","pricing":{"prompt":"0.000000028","completion":"0.000000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"nousresearch/hermes-2-pro-llama-3-8b","name":"NousResearch: Hermes 2 Pro - Llama-3 8B","pricing":{"prompt":"0.000000025","completion":"0.00000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct:free","name":"Mistral: Mistral 7B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct","name":"Mistral: Mistral 7B Instruct","pricing":{"prompt":"0.000000028","completion":"0.000000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"microsoft/phi-3-mini-128k-instruct","name":"Microsoft: Phi-3 Mini 128K Instruct","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716681600,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-3-medium-128k-instruct","name":"Microsoft: Phi-3 Medium 128K Instruct","pricing":{"prompt":"0.000001","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716508800,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4o","name":"OpenAI: GPT-4o","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0.003613","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1715558400,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-4o:extended","name":"OpenAI: GPT-4o (extended)","pricing":{"prompt":"0.000006","completion":"0.000018","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0"},"created":1715558400,"top_provider":{"context_length":128000,"max_completion_tokens":64000,"is_moderated":true}},{"id":"openai/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","pricing":{"prompt":"0.000005","completion":"0.000015","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0"},"created":1715558400,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"meta-llama/llama-guard-2-8b","name":"Meta: LlamaGuard 2 8B","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1715558400,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3-8b-instruct","name":"Meta: Llama 3 8B Instruct","pricing":{"prompt":"0.00000003","completion":"0.00000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713398400,"top_provider":{"context_length":8192,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3-70b-instruct","name":"Meta: Llama 3 70B Instruct","pricing":{"prompt":"0.0000003","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713398400,"top_provider":{"context_length":8192,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","pricing":{"prompt":"0.0000009","completion":"0.0000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713312000,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","pricing":{"prompt":"0.00000048","completion":"0.00000048","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713225600,"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","pricing":{"prompt":"0.00001","completion":"0.00003","request":"0","image":"0.01445","web_search":"0","internal_reasoning":"0"},"created":1712620800,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"anthropic/claude-3-haiku","name":"Anthropic: Claude 3 Haiku","pricing":{"prompt":"0.00000025","completion":"0.00000125","request":"0","image":"0.0004","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","input_cache_write":"0.0000003"},"created":1710288000,"top_provider":{"context_length":200000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"anthropic/claude-3-opus","name":"Anthropic: Claude 3 Opus","pricing":{"prompt":"0.000015","completion":"0.000075","request":"0","image":"0.024","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000015","input_cache_write":"0.00001875"},"created":1709596800,"top_provider":{"context_length":200000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mistralai/mistral-large","name":"Mistral Large","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1708905600,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","pricing":{"prompt":"0.000001","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1706140800,"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":false}},{"id":"openai/gpt-4-turbo-preview","name":"OpenAI: GPT-4 Turbo Preview","pricing":{"prompt":"0.00001","completion":"0.00003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1706140800,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mistralai/mistral-tiny","name":"Mistral Tiny","pricing":{"prompt":"0.00000025","completion":"0.00000025","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1704844800,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-small","name":"Mistral Small","pricing":{"prompt":"0.0000002","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1704844800,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct-v0.2","name":"Mistral: Mistral 7B Instruct v0.2","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1703721600,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mixtral-8x7b-instruct","name":"Mistral: Mixtral 8x7B Instruct","pricing":{"prompt":"0.00000054","completion":"0.00000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1702166400,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"neversleep/noromaid-20b","name":"Noromaid 20B","pricing":{"prompt":"0.000001","completion":"0.00000175","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1700956800,"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false}},{"id":"alpindale/goliath-120b","name":"Goliath 120B","pricing":{"prompt":"0.000004","completion":"0.0000055","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1699574400,"top_provider":{"context_length":6144,"max_completion_tokens":512,"is_moderated":false}},{"id":"openrouter/auto","name":"Auto Router","pricing":{"prompt":"-1","completion":"-1"},"created":1699401600,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4-1106-preview","name":"OpenAI: GPT-4 Turbo (older v1106)","pricing":{"prompt":"0.00001","completion":"0.00003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1699228800,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mistralai/mistral-7b-instruct-v0.1","name":"Mistral: Mistral 7B Instruct v0.1","pricing":{"prompt":"0.00000011","completion":"0.00000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1695859200,"top_provider":{"context_length":2824,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","pricing":{"prompt":"0.0000015","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1695859200,"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","pricing":{"prompt":"0.000003","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1693180800,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","pricing":{"prompt":"0.000001125","completion":"0.000001125","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1690934400,"top_provider":{"context_length":8000,"max_completion_tokens":2000,"is_moderated":false}},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","pricing":{"prompt":"0.00000045","completion":"0.00000065","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1689984000,"top_provider":{"context_length":6144,"max_completion_tokens":null,"is_moderated":false}},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","pricing":{"prompt":"0.00000005","completion":"0.00000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1688256000,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","pricing":{"prompt":"0.0000005","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1685232000,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-4-0314","name":"OpenAI: GPT-4 (older v0314)","pricing":{"prompt":"0.00003","completion":"0.00006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1685232000,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","pricing":{"prompt":"0.00003","completion":"0.00006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1685232000,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":true}}]
\ No newline at end of file
+export const models = [{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","pricing":{"prompt":"0.000000075","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1766505011,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false}},{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","pricing":{"prompt":"0.00000025","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1766504997,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false}},{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"created":1766454997,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false}},{"id":"z-ai/glm-4.7","name":"Z.AI: GLM 4.7","pricing":{"prompt":"0.0000004","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1766378014,"top_provider":{"context_length":202752,"max_completion_tokens":65535,"is_moderated":false}},{"id":"google/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","pricing":{"prompt":"0.0000005","completion":"0.000003","request":"0","image":"0","audio":"0.000001","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000005"},"created":1765987078,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"mistralai/mistral-small-creative","name":"Mistral: Mistral Small Creative","pricing":{"prompt":"0.0000001","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765908653,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"allenai/olmo-3.1-32b-think:free","name":"AllenAI: Olmo 3.1 32B Think (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765907719,"top_provider":{"context_length":65536,"max_completion_tokens":65536,"is_moderated":false}},{"id":"xiaomi/mimo-v2-flash:free","name":"Xiaomi: MiMo-V2-Flash (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765731308,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false}},{"id":"nvidia/nemotron-3-nano-30b-a3b:free","name":"NVIDIA: Nemotron 3 Nano 30B A3B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765731275,"top_provider":{"context_length":256000,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","pricing":{"prompt":"0.00000006","completion":"0.00000024","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765731275,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","pricing":{"prompt":"0.00000175","completion":"0.000014","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000175"},"created":1765389783,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","pricing":{"prompt":"0.000021","completion":"0.000168","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0"},"created":1765389780,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","pricing":{"prompt":"0.00000175","completion":"0.000014","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000175"},"created":1765389775,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"mistralai/devstral-2512:free","name":"Mistral: Devstral 2 2512 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765285419,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/devstral-2512","name":"Mistral: Devstral 2 2512","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765285419,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false}},{"id":"relace/relace-search","name":"Relace: Relace Search","pricing":{"prompt":"0.000001","completion":"0.000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0"},"created":1765213560,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false}},{"id":"z-ai/glm-4.6v","name":"Z.AI: GLM 4.6V","pricing":{"prompt":"0.0000003","completion":"0.0000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000005"},"created":1765207462,"top_provider":{"context_length":131072,"max_completion_tokens":24000,"is_moderated":false}},{"id":"nex-agi/deepseek-v3.1-nex-n1:free","name":"Nex AGI: DeepSeek V3.1 Nex N1 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0","input_cache_write":"0"},"created":1765204393,"top_provider":{"context_length":131072,"max_completion_tokens":163840,"is_moderated":false}},{"id":"essentialai/rnj-1-instruct","name":"EssentialAI: Rnj 1 Instruct","pricing":{"prompt":"0.00000015","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1765094847,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","pricing":{"prompt":"-1","completion":"-1"},"created":1764903653,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1764878934,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764696672,"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true}},{"id":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764681735,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","pricing":{"prompt":"0.00000015","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764681654,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764681560,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","pricing":{"prompt":"0.0000005","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764624472,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"arcee-ai/trinity-mini:free","name":"Arcee AI: Trinity Mini (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764601720,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"arcee-ai/trinity-mini","name":"Arcee AI: Trinity Mini","pricing":{"prompt":"0.000000045","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0"},"created":1764601720,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"deepseek/deepseek-v3.2-speciale","name":"DeepSeek: DeepSeek V3.2 Speciale","pricing":{"prompt":"0.00000027","completion":"0.00000041","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764594837,"top_provider":{"context_length":163840,"max_completion_tokens":65536,"is_moderated":false}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","pricing":{"prompt":"0.000000224","completion":"0.00000032","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764594642,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"prime-intellect/intellect-3","name":"Prime Intellect: INTELLECT-3","pricing":{"prompt":"0.0000002","completion":"0.0000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764212534,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"tngtech/tng-r1t-chimera:free","name":"TNG: R1T Chimera (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764184161,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"tngtech/tng-r1t-chimera","name":"TNG: R1T Chimera","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1764184161,"top_provider":{"context_length":163840,"max_completion_tokens":65536,"is_moderated":false}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","pricing":{"prompt":"0.000005","completion":"0.000025","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000005","input_cache_write":"0.00000625"},"created":1764010580,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true}},{"id":"allenai/olmo-3-32b-think:free","name":"AllenAI: Olmo 3 32B Think (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1763758276,"top_provider":{"context_length":65536,"max_completion_tokens":65536,"is_moderated":false}},{"id":"allenai/olmo-3-7b-instruct","name":"AllenAI: Olmo 3 7B Instruct","pricing":{"prompt":"0.0000001","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1763758273,"top_provider":{"context_length":65536,"max_completion_tokens":65536,"is_moderated":false}},{"id":"allenai/olmo-3-7b-think","name":"AllenAI: Olmo 3 7B Think","pricing":{"prompt":"0.00000012","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1763758270,"top_provider":{"context_length":65536,"max_completion_tokens":65536,"is_moderated":false}},{"id":"google/gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","pricing":{"prompt":"0.000002","completion":"0.000012","request":"0","image":"0.067","web_search":"0","internal_reasoning":"0"},"created":1763653797,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false}},{"id":"x-ai/grok-4.1-fast","name":"xAI: Grok 4.1 Fast","pricing":{"prompt":"0.0000002","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000005"},"created":1763587502,"top_provider":{"context_length":2000000,"max_completion_tokens":30000,"is_moderated":false}},{"id":"google/gemini-3-pro-preview","name":"Google: Gemini 3 Pro Preview","pricing":{"prompt":"0.000002","completion":"0.000012","request":"0","image":"0.008256","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000002","input_cache_write":"0.000002375"},"created":1763474668,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"deepcogito/cogito-v2.1-671b","name":"Deep Cogito: Cogito v2.1 671B","pricing":{"prompt":"0.00000125","completion":"0.00000125","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1763071233,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1763060305,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5.1-chat","name":"OpenAI: GPT-5.1 Chat","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1763060302,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1763060298,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","pricing":{"prompt":"0.00000025","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000025"},"created":1763057820,"top_provider":{"context_length":400000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"kwaipilot/kat-coder-pro:free","name":"Kwaipilot: KAT-Coder-Pro V1 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1762745912,"top_provider":{"context_length":256000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","pricing":{"prompt":"0.0000004","completion":"0.00000175","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1762440622,"top_provider":{"context_length":262144,"max_completion_tokens":65535,"is_moderated":false}},{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","pricing":{"prompt":"0.0000025","completion":"0.0000125","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000625"},"created":1761950332,"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":true}},{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0.018","image":"0","web_search":"0","internal_reasoning":"0"},"created":1761854366,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","pricing":{"prompt":"0.0000001","completion":"0.0000003","request":"0","image":"0","audio":"0.0001","web_search":"0","internal_reasoning":"0"},"created":1761835144,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","pricing":{"prompt":"0.000000075","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000037"},"created":1761752836,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false}},{"id":"nvidia/nemotron-nano-12b-v2-vl:free","name":"NVIDIA: Nemotron Nano 12B 2 VL (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1761675565,"top_provider":{"context_length":128000,"max_completion_tokens":128000,"is_moderated":false}},{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"NVIDIA: Nemotron Nano 12B 2 VL","pricing":{"prompt":"0.0000002","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1761675565,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","pricing":{"prompt":"0.0000002","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003"},"created":1761252093,"top_provider":{"context_length":196608,"max_completion_tokens":131072,"is_moderated":false}},{"id":"qwen/qwen3-vl-32b-instruct","name":"Qwen: Qwen3 VL 32B Instruct","pricing":{"prompt":"0.0000005","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1761231332,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"liquid/lfm2-8b-a1b","name":"LiquidAI/LFM2-8B-A1B","pricing":{"prompt":"0.00000005","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760970984,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"liquid/lfm-2.2-6b","name":"LiquidAI/LFM2-2.6B","pricing":{"prompt":"0.00000005","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760970889,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","pricing":{"prompt":"0.000000017","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760927695,"top_provider":{"context_length":131000,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepcogito/cogito-v2-preview-llama-405b","name":"Deep Cogito: Cogito V2 Preview Llama 405B","pricing":{"prompt":"0.0000035","completion":"0.0000035","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760709933,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","pricing":{"prompt":"0.0000025","completion":"0.000002","request":"0","image":"0.0000025","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.00000025"},"created":1760624583,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","pricing":{"prompt":"0.000001","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000001","input_cache_write":"0.00000125"},"created":1760547638,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true}},{"id":"qwen/qwen3-vl-8b-thinking","name":"Qwen: Qwen3 VL 8B Thinking","pricing":{"prompt":"0.00000018","completion":"0.0000021","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760463746,"top_provider":{"context_length":256000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","pricing":{"prompt":"0.000000064","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0"},"created":1760463308,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"openai/gpt-5-image","name":"OpenAI: GPT-5 Image","pricing":{"prompt":"0.00001","completion":"0.00001","request":"0","image":"0.00001","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1760447986,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/o3-deep-research","name":"OpenAI: o3 Deep Research","pricing":{"prompt":"0.00001","completion":"0.00004","request":"0","image":"0.00765","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000025"},"created":1760129661,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"openai/o4-mini-deep-research","name":"OpenAI: o4 Mini Deep Research","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0.00153","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000005"},"created":1760129642,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"NVIDIA: Llama 3.3 Nemotron Super 49B V1.5","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760101395,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"baidu/ernie-4.5-21b-a3b-thinking","name":"Baidu: ERNIE 4.5 21B A3B Thinking","pricing":{"prompt":"0.000000056","completion":"0.000000224","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1760048887,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false}},{"id":"google/gemini-2.5-flash-image","name":"Google: Gemini 2.5 Flash Image (Nano Banana)","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","web_search":"0","internal_reasoning":"0"},"created":1759870431,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","pricing":{"prompt":"0.00000016","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0"},"created":1759794479,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759794476,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","pricing":{"prompt":"0.000015","completion":"0.00012","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0"},"created":1759776663,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"z-ai/glm-4.6","name":"Z.AI: GLM 4.6","pricing":{"prompt":"0.00000039","completion":"0.0000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759235576,"top_provider":{"context_length":204800,"max_completion_tokens":204800,"is_moderated":false}},{"id":"z-ai/glm-4.6:exacto","name":"Z.AI: GLM 4.6 (exacto)","pricing":{"prompt":"0.00000044","completion":"0.00000176","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759235576,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1759161676,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","pricing":{"prompt":"0.00000021","completion":"0.00000032","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1759150481,"top_provider":{"context_length":163840,"max_completion_tokens":65536,"is_moderated":false}},{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","pricing":{"prompt":"0.0000003","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758931878,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","pricing":{"prompt":"0.00000085","completion":"0.00000125","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758891572,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false}},{"id":"google/gemini-2.5-flash-preview-09-2025","name":"Google: Gemini 2.5 Flash Preview 09-2025","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","audio":"0.000001","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075","input_cache_write":"0.0000003833"},"created":1758820178,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"google/gemini-2.5-flash-lite-preview-09-2025","name":"Google: Gemini 2.5 Flash Lite Preview 09-2025","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758819686,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758668690,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","pricing":{"prompt":"0.0000002","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758668687,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-max","name":"Qwen: Qwen3 Max","pricing":{"prompt":"0.0000012","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000024"},"created":1758662808,"top_provider":{"context_length":256000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-coder-plus","name":"Qwen: Qwen3 Coder Plus","pricing":{"prompt":"0.000001","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000001"},"created":1758662707,"top_provider":{"context_length":128000,"max_completion_tokens":65536,"is_moderated":false}},{"id":"openai/gpt-5-codex","name":"OpenAI: GPT-5 Codex","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1758643403,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"deepseek/deepseek-v3.1-terminus:exacto","name":"DeepSeek: DeepSeek V3.1 Terminus (exacto)","pricing":{"prompt":"0.00000021","completion":"0.00000079","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000168"},"created":1758548275,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","pricing":{"prompt":"0.00000021","completion":"0.00000079","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000168"},"created":1758548275,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-4-fast","name":"xAI: Grok 4 Fast","pricing":{"prompt":"0.0000002","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000005"},"created":1758240090,"top_provider":{"context_length":2000000,"max_completion_tokens":30000,"is_moderated":false}},{"id":"alibaba/tongyi-deepresearch-30b-a3b:free","name":"Tongyi DeepResearch 30B A3B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758210804,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"alibaba/tongyi-deepresearch-30b-a3b","name":"Tongyi DeepResearch 30B A3B","pricing":{"prompt":"0.00000009","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1758210804,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","pricing":{"prompt":"0.0000003","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000008"},"created":1758115536,"top_provider":{"context_length":128000,"max_completion_tokens":65536,"is_moderated":false}},{"id":"opengvlab/internvl3-78b","name":"OpenGVLab: InternVL3 78B","pricing":{"prompt":"0.0000001","completion":"0.00000039","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757962555,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","pricing":{"prompt":"0.00000012","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757612284,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","pricing":{"prompt":"0.00000009","completion":"0.0000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757612213,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"meituan/longcat-flash-chat","name":"Meituan: LongCat Flash Chat","pricing":{"prompt":"0.0000002","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757427658,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728","pricing":{"prompt":"0.0000004","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757347599,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen-plus-2025-07-28:thinking","name":"Qwen: Qwen Plus 0728 (thinking)","pricing":{"prompt":"0.0000004","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757347599,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"nvidia/nemotron-nano-9b-v2:free","name":"NVIDIA: Nemotron Nano 9B V2 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757106807,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/nemotron-nano-9b-v2","name":"NVIDIA: Nemotron Nano 9B V2","pricing":{"prompt":"0.00000004","completion":"0.00000016","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757106807,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","pricing":{"prompt":"0.00000039","completion":"0.0000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757021147,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"moonshotai/kimi-k2-0905:exacto","name":"MoonshotAI: Kimi K2 0905 (exacto)","pricing":{"prompt":"0.0000006","completion":"0.0000025","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1757021147,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepcogito/cogito-v2-preview-llama-70b","name":"Deep Cogito: Cogito V2 Preview Llama 70B","pricing":{"prompt":"0.00000088","completion":"0.00000088","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756831784,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepcogito/cogito-v2-preview-llama-109b-moe","name":"Cogito V2 Preview Llama 109B","pricing":{"prompt":"0.00000018","completion":"0.00000059","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756831568,"top_provider":{"context_length":32767,"max_completion_tokens":null,"is_moderated":false}},{"id":"stepfun-ai/step3","name":"StepFun: Step3","pricing":{"prompt":"0.00000057","completion":"0.00000142","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756415375,"top_provider":{"context_length":65536,"max_completion_tokens":65536,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","pricing":{"prompt":"0.000000051","completion":"0.00000034","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756399192,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-code-fast-1","name":"xAI: Grok Code Fast 1","pricing":{"prompt":"0.0000002","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000002"},"created":1756238927,"top_provider":{"context_length":256000,"max_completion_tokens":10000,"is_moderated":false}},{"id":"nousresearch/hermes-4-70b","name":"Nous: Hermes 4 70B","pricing":{"prompt":"0.00000011","completion":"0.00000038","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756236182,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1756235463,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"google/gemini-2.5-flash-image-preview","name":"Google: Gemini 2.5 Flash Image Preview (Nano Banana)","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","web_search":"0","internal_reasoning":"0"},"created":1756218977,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","pricing":{"prompt":"0.00000015","completion":"0.00000075","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755779628,"top_provider":{"context_length":32768,"max_completion_tokens":7168,"is_moderated":false}},{"id":"openai/gpt-4o-audio-preview","name":"OpenAI: GPT-4o Audio","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","audio":"0.00004","web_search":"0","internal_reasoning":"0"},"created":1755233061,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755095639,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"baidu/ernie-4.5-21b-a3b","name":"Baidu: ERNIE 4.5 21B A3B","pricing":{"prompt":"0.000000056","completion":"0.000000224","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755034167,"top_provider":{"context_length":120000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"baidu/ernie-4.5-vl-28b-a3b","name":"Baidu: ERNIE 4.5 VL 28B A3B","pricing":{"prompt":"0.000000112","completion":"0.000000448","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1755032836,"top_provider":{"context_length":30000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"z-ai/glm-4.5v","name":"Z.AI: GLM 4.5V","pricing":{"prompt":"0.00000048","completion":"0.00000144","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000088","input_cache_write":"0"},"created":1754922288,"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false}},{"id":"ai21/jamba-mini-1.7","name":"AI21: Jamba Mini 1.7","pricing":{"prompt":"0.0000002","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754670601,"top_provider":{"context_length":256000,"max_completion_tokens":4096,"is_moderated":false}},{"id":"ai21/jamba-large-1.7","name":"AI21: Jamba Large 1.7","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754669020,"top_provider":{"context_length":256000,"max_completion_tokens":4096,"is_moderated":false}},{"id":"openai/gpt-5-chat","name":"OpenAI: GPT-5 Chat","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1754587837,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000125"},"created":1754587413,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","pricing":{"prompt":"0.00000025","completion":"0.000002","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000025"},"created":1754587407,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","pricing":{"prompt":"0.00000005","completion":"0.0000004","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000005"},"created":1754587402,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true}},{"id":"openai/gpt-oss-120b:free","name":"OpenAI: gpt-oss-120b (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414231,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":true}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","pricing":{"prompt":"0.000000039","completion":"0.00000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414231,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-oss-120b:exacto","name":"OpenAI: gpt-oss-120b (exacto)","pricing":{"prompt":"0.000000039","completion":"0.00000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414231,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-oss-20b:free","name":"OpenAI: gpt-oss-20b (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414229,"top_provider":{"context_length":131072,"max_completion_tokens":128000,"is_moderated":false}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","pricing":{"prompt":"0.00000003","completion":"0.00000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754414229,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","pricing":{"prompt":"0.000015","completion":"0.000075","request":"0","image":"0.024","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000015","input_cache_write":"0.00001875"},"created":1754411591,"top_provider":{"context_length":200000,"max_completion_tokens":null,"is_moderated":true}},{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","pricing":{"prompt":"0.0000003","completion":"0.0000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1754079630,"top_provider":{"context_length":256000,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","pricing":{"prompt":"0.00000007","completion":"0.00000027","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753972379,"top_provider":{"context_length":160000,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","pricing":{"prompt":"0.00000008","completion":"0.00000033","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753806965,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"z-ai/glm-4.5","name":"Z.AI: GLM 4.5","pricing":{"prompt":"0.00000035","completion":"0.00000155","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753471347,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false}},{"id":"z-ai/glm-4.5-air:free","name":"Z.AI: GLM 4.5 Air (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753471258,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"z-ai/glm-4.5-air","name":"Z.AI: GLM 4.5 Air","pricing":{"prompt":"0.000000104","completion":"0.00000068","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0"},"created":1753471258,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","pricing":{"prompt":"0.00000011","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753449557,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"z-ai/glm-4-32b","name":"Z.AI: GLM 4 32B ","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753376617,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-coder:free","name":"Qwen: Qwen3 Coder 480B A35B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753230546,"top_provider":{"context_length":262000,"max_completion_tokens":262000,"is_moderated":false}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","pricing":{"prompt":"0.00000022","completion":"0.00000095","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753230546,"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false}},{"id":"qwen/qwen3-coder:exacto","name":"Qwen: Qwen3 Coder 480B A35B (exacto)","pricing":{"prompt":"0.00000022","completion":"0.0000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753230546,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false}},{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","pricing":{"prompt":"0.0000001","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753205056,"top_provider":{"context_length":128000,"max_completion_tokens":2048,"is_moderated":false}},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000001","input_cache_write":"0.0000001833"},"created":1753200276,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","pricing":{"prompt":"0.000000071","completion":"0.000000463","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1753119555,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false}},{"id":"switchpoint/router","name":"Switchpoint Router","pricing":{"prompt":"0.00000085","completion":"0.0000034","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752272899,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"moonshotai/kimi-k2:free","name":"MoonshotAI: Kimi K2 0711 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752263252,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":true}},{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","pricing":{"prompt":"0.000000456","completion":"0.00000184","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752263252,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"thudm/glm-4.1v-9b-thinking","name":"THUDM: GLM 4.1V 9B Thinking","pricing":{"prompt":"0.000000028","completion":"0.0000001104","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752244385,"top_provider":{"context_length":65536,"max_completion_tokens":8000,"is_moderated":false}},{"id":"mistralai/devstral-medium","name":"Mistral: Devstral Medium","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752161321,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/devstral-small","name":"Mistral: Devstral Small 1.1","pricing":{"prompt":"0.00000007","completion":"0.00000028","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752160751,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition:free","name":"Venice: Uncensored (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752094966,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-4","name":"xAI: Grok 4","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000075"},"created":1752087689,"top_provider":{"context_length":256000,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3n-e2b-it:free","name":"Google: Gemma 3n 2B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1752074904,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false}},{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","pricing":{"prompt":"0.00000014","completion":"0.00000057","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751987664,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"tngtech/deepseek-r1t2-chimera:free","name":"TNG: DeepSeek R1T2 Chimera (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751986985,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"tngtech/deepseek-r1t2-chimera","name":"TNG: DeepSeek R1T2 Chimera","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751986985,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","pricing":{"prompt":"0.0000009","completion":"0.0000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751910858,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false}},{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","pricing":{"prompt":"0.0000008","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751910002,"top_provider":{"context_length":81920,"max_completion_tokens":38000,"is_moderated":false}},{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"Baidu: ERNIE 4.5 VL 424B A47B ","pricing":{"prompt":"0.000000336","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751300903,"top_provider":{"context_length":123000,"max_completion_tokens":16000,"is_moderated":false}},{"id":"baidu/ernie-4.5-300b-a47b","name":"Baidu: ERNIE 4.5 300B A47B ","pricing":{"prompt":"0.000000224","completion":"0.00000088","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1751300139,"top_provider":{"context_length":123000,"max_completion_tokens":12000,"is_moderated":false}},{"id":"inception/mercury","name":"Inception: Mercury","pricing":{"prompt":"0.00000025","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750973026,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","pricing":{"prompt":"0.00000006","completion":"0.00000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750443016,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","pricing":{"prompt":"0.0000004","completion":"0.0000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750200414,"top_provider":{"context_length":1000000,"max_completion_tokens":40000,"is_moderated":false}},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","pricing":{"prompt":"0.0000003","completion":"0.0000025","request":"0","image":"0.001238","audio":"0.000001","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","input_cache_write":"0.0000003833"},"created":1750172488,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0.00516","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125","input_cache_write":"0.000001625"},"created":1750169544,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"moonshotai/kimi-dev-72b","name":"MoonshotAI: Kimi Dev 72B","pricing":{"prompt":"0.00000029","completion":"0.00000115","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1750115909,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","pricing":{"prompt":"0.00002","completion":"0.00008","request":"0","image":"0.0153","web_search":"0.01","internal_reasoning":"0"},"created":1749598352,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"x-ai/grok-3-mini","name":"xAI: Grok 3 Mini","pricing":{"prompt":"0.0000003","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1749583245,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-3","name":"xAI: Grok 3","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000075"},"created":1749582908,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0.00516","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000031","input_cache_write":"0.000001625"},"created":1749137257,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek: DeepSeek R1 0528 Qwen3 8B","pricing":{"prompt":"0.00000002","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748538543,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528:free","name":"DeepSeek: R1 0528 (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748455170,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","pricing":{"prompt":"0.0000004","completion":"0.00000175","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1748455170,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4","pricing":{"prompt":"0.000015","completion":"0.000075","request":"0","image":"0.024","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000015","input_cache_write":"0.00001875"},"created":1747931245,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true}},{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1747930371,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"mistralai/devstral-small-2505","name":"Mistral: Devstral Small 2505","pricing":{"prompt":"0.00000006","completion":"0.00000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747837379,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3n-e4b-it:free","name":"Google: Gemma 3n 4B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747776824,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false}},{"id":"google/gemma-3n-e4b-it","name":"Google: Gemma 3n 4B","pricing":{"prompt":"0.00000002","completion":"0.00000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1747776824,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/codex-mini","name":"OpenAI: Codex Mini","pricing":{"prompt":"0.0000015","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000375"},"created":1747409761,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"nousresearch/deephermes-3-mistral-24b-preview","name":"Nous: DeepHermes 3 Mistral 24B Preview","pricing":{"prompt":"0.00000002","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746830904,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","pricing":{"prompt":"0.0000004","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746627341,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemini-2.5-pro-preview-05-06","name":"Google: Gemini 2.5 Pro Preview 05-06","pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0.00516","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000031","input_cache_write":"0.000001625"},"created":1746578513,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false}},{"id":"arcee-ai/spotlight","name":"Arcee AI: Spotlight","pricing":{"prompt":"0.00000018","completion":"0.00000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746481552,"top_provider":{"context_length":131072,"max_completion_tokens":65537,"is_moderated":false}},{"id":"arcee-ai/maestro-reasoning","name":"Arcee AI: Maestro Reasoning","pricing":{"prompt":"0.0000009","completion":"0.0000033","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746481269,"top_provider":{"context_length":131072,"max_completion_tokens":32000,"is_moderated":false}},{"id":"arcee-ai/virtuoso-large","name":"Arcee AI: Virtuoso Large","pricing":{"prompt":"0.00000075","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746478885,"top_provider":{"context_length":131072,"max_completion_tokens":64000,"is_moderated":false}},{"id":"arcee-ai/coder-large","name":"Arcee AI: Coder Large","pricing":{"prompt":"0.0000005","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746478663,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-4-reasoning-plus","name":"Microsoft: Phi 4 Reasoning Plus","pricing":{"prompt":"0.00000007","completion":"0.00000035","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746130961,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"inception/mercury-coder","name":"Inception: Mercury Coder","pricing":{"prompt":"0.00000025","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746033880,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false}},{"id":"qwen/qwen3-4b:free","name":"Qwen: Qwen3 4B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746031104,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-prover-v2","name":"DeepSeek: DeepSeek Prover V2","pricing":{"prompt":"0.0000005","completion":"0.00000218","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1746013094,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","pricing":{"prompt":"0.00000018","completion":"0.00000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745975193,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","pricing":{"prompt":"0.00000006","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745878604,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-8b","name":"Qwen: Qwen3 8B","pricing":{"prompt":"0.000000028","completion":"0.0000001104","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745876632,"top_provider":{"context_length":128000,"max_completion_tokens":20000,"is_moderated":false}},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745876478,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","pricing":{"prompt":"0.00000008","completion":"0.00000024","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745875945,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"qwen/qwen3-235b-a22b","name":"Qwen: Qwen3 235B A22B","pricing":{"prompt":"0.00000018","completion":"0.00000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745875757,"top_provider":{"context_length":40960,"max_completion_tokens":40960,"is_moderated":false}},{"id":"tngtech/deepseek-r1t-chimera:free","name":"TNG: DeepSeek R1T Chimera (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745760875,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"tngtech/deepseek-r1t-chimera","name":"TNG: DeepSeek R1T Chimera","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1745760875,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0.0008415","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000275"},"created":1744824212,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"openai/o3","name":"OpenAI: o3","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0.00153","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000005"},"created":1744823457,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0.0008415","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000275"},"created":1744820942,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"qwen/qwen2.5-coder-7b-instruct","name":"Qwen: Qwen2.5 Coder 7B Instruct","pricing":{"prompt":"0.00000003","completion":"0.00000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744734887,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000005"},"created":1744651385,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true}},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","pricing":{"prompt":"0.0000004","completion":"0.0000016","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.0000001"},"created":1744651381,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true}},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0","web_search":"0.01","internal_reasoning":"0","input_cache_read":"0.000000025"},"created":1744651369,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true}},{"id":"eleutherai/llemma_7b","name":"EleutherAI: Llemma 7b","pricing":{"prompt":"0.0000008","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744643225,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"alfredpros/codellama-7b-instruct-solidity","name":"AlfredPros: CodeLLaMa 7B Instruct Solidity","pricing":{"prompt":"0.0000008","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744641874,"top_provider":{"context_length":4096,"max_completion_tokens":4096,"is_moderated":false}},{"id":"arliai/qwq-32b-arliai-rpr-v1","name":"ArliAI: QwQ 32B RpR v1","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744555982,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"x-ai/grok-3-mini-beta","name":"xAI: Grok 3 Mini Beta","pricing":{"prompt":"0.0000003","completion":"0.0000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1744240195,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"x-ai/grok-3-beta","name":"xAI: Grok 3 Beta","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000075"},"created":1744240068,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"NVIDIA: Llama 3.1 Nemotron Ultra 253B v1","pricing":{"prompt":"0.0000006","completion":"0.0000018","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1744115059,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0.0006684","web_search":"0","internal_reasoning":"0"},"created":1743881822,"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","pricing":{"prompt":"0.00000008","completion":"0.0000003","request":"0","image":"0.0003342","web_search":"0","internal_reasoning":"0"},"created":1743881519,"top_provider":{"context_length":327680,"max_completion_tokens":16384,"is_moderated":false}},{"id":"qwen/qwen2.5-vl-32b-instruct","name":"Qwen: Qwen2.5 VL 32B Instruct","pricing":{"prompt":"0.00000005","completion":"0.00000022","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742839838,"top_provider":{"context_length":16384,"max_completion_tokens":16384,"is_moderated":false}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","pricing":{"prompt":"0.0000002","completion":"0.00000088","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000106"},"created":1742824755,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/o1-pro","name":"OpenAI: o1-pro","pricing":{"prompt":"0.00015","completion":"0.0006","request":"0","image":"0.21675","web_search":"0","internal_reasoning":"0"},"created":1742423211,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"mistralai/mistral-small-3.1-24b-instruct:free","name":"Mistral: Mistral Small 3.1 24B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742238937,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1742238937,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"allenai/olmo-2-0325-32b-instruct","name":"AllenAI: Olmo 2 32B Instruct","pricing":{"prompt":"0.00000005","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741988556,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3-4b-it:free","name":"Google: Gemma 3 4B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741905510,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","pricing":{"prompt":"0.00000001703012","completion":"0.0000000681536","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741905510,"top_provider":{"context_length":96000,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3-12b-it:free","name":"Google: Gemma 3 12B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741902625,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","pricing":{"prompt":"0.00000003","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741902625,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"cohere/command-a","name":"Cohere: Command A","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741894342,"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"openai/gpt-4o-mini-search-preview","name":"OpenAI: GPT-4o-mini Search Preview","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0.0275","image":"0.000217","web_search":"0","internal_reasoning":"0"},"created":1741818122,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-4o-search-preview","name":"OpenAI: GPT-4o Search Preview","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0.035","image":"0.003613","web_search":"0","internal_reasoning":"0"},"created":1741817949,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"google/gemma-3-27b-it:free","name":"Google: Gemma 3 27B (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741756359,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","pricing":{"prompt":"0.00000004","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741756359,"top_provider":{"context_length":96000,"max_completion_tokens":96000,"is_moderated":false}},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","pricing":{"prompt":"0.00000055","completion":"0.0000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741636566,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"microsoft/phi-4-multimodal-instruct","name":"Microsoft: Phi 4 Multimodal Instruct","pricing":{"prompt":"0.00000005","completion":"0.0000001","request":"0","image":"0.00017685","web_search":"0","internal_reasoning":"0"},"created":1741396284,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0.005","internal_reasoning":"0"},"created":1741313308,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0","web_search":"0.005","internal_reasoning":"0"},"created":1741312423,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false}},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","pricing":{"prompt":"0.000002","completion":"0.000008","request":"0","image":"0","web_search":"0.005","internal_reasoning":"0.000003"},"created":1741311246,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwq-32b","name":"Qwen: QwQ 32B","pricing":{"prompt":"0.00000015","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1741208814,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemini-2.0-flash-lite-001","name":"Google: Gemini 2.0 Flash Lite","pricing":{"prompt":"0.000000075","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1740506212,"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":false}},{"id":"anthropic/claude-3.7-sonnet:thinking","name":"Anthropic: Claude 3.7 Sonnet (thinking)","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1740422110,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"anthropic/claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","pricing":{"prompt":"0.000003","completion":"0.000015","request":"0","image":"0.0048","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000003","input_cache_write":"0.00000375"},"created":1740422110,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":false}},{"id":"mistralai/mistral-saba","name":"Mistral: Saba","pricing":{"prompt":"0.0000002","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1739803239,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-guard-3-8b","name":"Llama Guard 3 8B","pricing":{"prompt":"0.00000002","completion":"0.00000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1739401318,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000055"},"created":1739372611,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"google/gemini-2.0-flash-001","name":"Google: Gemini 2.0 Flash","pricing":{"prompt":"0.0000001","completion":"0.0000004","request":"0","image":"0.0000258","audio":"0.0000007","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000025","input_cache_write":"0.0000001833"},"created":1738769413,"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen-vl-plus","name":"Qwen: Qwen VL Plus","pricing":{"prompt":"0.00000021","completion":"0.00000063","request":"0","image":"0.0002688","web_search":"0","internal_reasoning":"0"},"created":1738731255,"top_provider":{"context_length":7500,"max_completion_tokens":1500,"is_moderated":false}},{"id":"aion-labs/aion-1.0","name":"AionLabs: Aion-1.0","pricing":{"prompt":"0.000004","completion":"0.000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738697557,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"aion-labs/aion-1.0-mini","name":"AionLabs: Aion-1.0-Mini","pricing":{"prompt":"0.0000007","completion":"0.0000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738697107,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false}},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","pricing":{"prompt":"0.0000008","completion":"0.0000016","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738696718,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen-vl-max","name":"Qwen: Qwen VL Max","pricing":{"prompt":"0.0000008","completion":"0.0000032","request":"0","image":"0.001024","web_search":"0","internal_reasoning":"0"},"created":1738434304,"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen-turbo","name":"Qwen: Qwen-Turbo","pricing":{"prompt":"0.00000005","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000002"},"created":1738410974,"top_provider":{"context_length":1000000,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","pricing":{"prompt":"0.00000007","completion":"0.00000026","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738410311,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"qwen/qwen-plus","name":"Qwen: Qwen-Plus","pricing":{"prompt":"0.0000004","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000016"},"created":1738409840,"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false}},{"id":"qwen/qwen-max","name":"Qwen: Qwen-Max ","pricing":{"prompt":"0.0000016","completion":"0.0000064","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000064"},"created":1738402289,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false}},{"id":"openai/o3-mini","name":"OpenAI: o3 Mini","pricing":{"prompt":"0.0000011","completion":"0.0000044","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000055"},"created":1738351721,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738255409,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek: R1 Distill Qwen 32B","pricing":{"prompt":"0.00000024","completion":"0.00000024","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738194830,"top_provider":{"context_length":64000,"max_completion_tokens":32000,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-qwen-14b","name":"DeepSeek: R1 Distill Qwen 14B","pricing":{"prompt":"0.00000012","completion":"0.00000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738193940,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"perplexity/sonar-reasoning","name":"Perplexity: Sonar Reasoning","pricing":{"prompt":"0.000001","completion":"0.000005","request":"0.005","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738131107,"top_provider":{"context_length":127000,"max_completion_tokens":null,"is_moderated":false}},{"id":"perplexity/sonar","name":"Perplexity: Sonar","pricing":{"prompt":"0.000001","completion":"0.000001","request":"0.005","image":"0","web_search":"0","internal_reasoning":"0"},"created":1738013808,"top_provider":{"context_length":127072,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737663169,"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false}},{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1737381095,"top_provider":{"context_length":163840,"max_completion_tokens":null,"is_moderated":false}},{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","pricing":{"prompt":"0.0000002","completion":"0.0000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736915462,"top_provider":{"context_length":1000192,"max_completion_tokens":1000192,"is_moderated":false}},{"id":"microsoft/phi-4","name":"Microsoft: Phi 4","pricing":{"prompt":"0.00000006","completion":"0.00000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736489872,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":false}},{"id":"sao10k/l3.1-70b-hanami-x1","name":"Sao10K: Llama 3.1 70B Hanami x1","pricing":{"prompt":"0.000003","completion":"0.000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1736302854,"top_provider":{"context_length":16000,"max_completion_tokens":null,"is_moderated":false}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","pricing":{"prompt":"0.0000003","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1735241320,"top_provider":{"context_length":163840,"max_completion_tokens":163840,"is_moderated":false}},{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","pricing":{"prompt":"0.00000065","completion":"0.00000075","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1734535928,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/o1","name":"OpenAI: o1","pricing":{"prompt":"0.000015","completion":"0.00006","request":"0","image":"0.021675","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000075"},"created":1734459999,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true}},{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","pricing":{"prompt":"0.0000000375","completion":"0.00000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1734158152,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true}},{"id":"google/gemini-2.0-flash-exp:free","name":"Google: Gemini 2.0 Flash Experimental (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733937523,"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":false}},{"id":"meta-llama/llama-3.3-70b-instruct:free","name":"Meta: Llama 3.3 70B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733506137,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","pricing":{"prompt":"0.0000001","completion":"0.00000032","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733506137,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","pricing":{"prompt":"0.00000006","completion":"0.00000024","request":"0","image":"0.00009","web_search":"0","internal_reasoning":"0"},"created":1733437363,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true}},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","pricing":{"prompt":"0.000000035","completion":"0.00000014","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1733437237,"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true}},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","pricing":{"prompt":"0.0000008","completion":"0.0000032","request":"0","image":"0.0012","web_search":"0","internal_reasoning":"0"},"created":1733436303,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true}},{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0.003613","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1732127594,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"mistralai/mistral-large-2411","name":"Mistral Large 2411","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731978685,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731978415,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/pixtral-large-2411","name":"Mistral: Pixtral Large 2411","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0.002888","web_search":"0","internal_reasoning":"0"},"created":1731977388,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","pricing":{"prompt":"0.00000003","completion":"0.00000011","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731368400,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"raifle/sorcererlm-8x22b","name":"SorcererLM 8x22B","pricing":{"prompt":"0.0000045","completion":"0.0000045","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731105083,"top_provider":{"context_length":16000,"max_completion_tokens":null,"is_moderated":false}},{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","pricing":{"prompt":"0.0000004","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1731103448,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"anthropic/claude-3.5-haiku-20241022","name":"Anthropic: Claude 3.5 Haiku (2024-10-22)","pricing":{"prompt":"0.0000008","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000008","input_cache_write":"0.000001"},"created":1730678400,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":false}},{"id":"anthropic/claude-3.5-haiku","name":"Anthropic: Claude 3.5 Haiku","pricing":{"prompt":"0.0000008","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000008","input_cache_write":"0.000001"},"created":1730678400,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"anthropic/claude-3.5-sonnet","name":"Anthropic: Claude 3.5 Sonnet","pricing":{"prompt":"0.000006","completion":"0.00003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729555200,"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":true}},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","pricing":{"prompt":"0.000003","completion":"0.000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729555200,"top_provider":{"context_length":16384,"max_completion_tokens":2048,"is_moderated":false}},{"id":"mistralai/ministral-8b","name":"Mistral: Ministral 8B","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729123200,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/ministral-3b","name":"Mistral: Ministral 3B","pricing":{"prompt":"0.00000004","completion":"0.00000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729123200,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","pricing":{"prompt":"0.00000004","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1729036800,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"NVIDIA: Llama 3.1 Nemotron 70B Instruct","pricing":{"prompt":"0.0000012","completion":"0.0000012","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1728950400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"inflection/inflection-3-pi","name":"Inflection: Inflection 3 Pi","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1728604800,"top_provider":{"context_length":8000,"max_completion_tokens":1024,"is_moderated":false}},{"id":"inflection/inflection-3-productivity","name":"Inflection: Inflection 3 Productivity","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1728604800,"top_provider":{"context_length":8000,"max_completion_tokens":1024,"is_moderated":false}},{"id":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","pricing":{"prompt":"0.00000017","completion":"0.00000043","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727654400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.2-3b-instruct:free","name":"Meta: Llama 3.2 3B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","pricing":{"prompt":"0.00000002","completion":"0.00000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","pricing":{"prompt":"0.000000027","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":60000,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.2-90b-vision-instruct","name":"Meta: Llama 3.2 90B Vision Instruct","pricing":{"prompt":"0.00000035","completion":"0.0000004","request":"0","image":"0.0005058","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.2-11b-vision-instruct","name":"Meta: Llama 3.2 11B Vision Instruct","pricing":{"prompt":"0.000000049","completion":"0.000000049","request":"0","image":"0.00007948","web_search":"0","internal_reasoning":"0"},"created":1727222400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","pricing":{"prompt":"0.00000012","completion":"0.00000039","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1726704000,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"neversleep/llama-3.1-lumimaid-8b","name":"NeverSleep: Lumimaid v0.2 8B","pricing":{"prompt":"0.00000009","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1726358400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/pixtral-12b","name":"Mistral: Pixtral 12B","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0.0001445","web_search":"0","internal_reasoning":"0"},"created":1725926400,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724976000,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true}},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724976000,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true}},{"id":"qwen/qwen-2.5-vl-7b-instruct:free","name":"Qwen: Qwen2.5-VL 7B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724803200,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"qwen/qwen-2.5-vl-7b-instruct","name":"Qwen: Qwen2.5-VL 7B Instruct","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0.0001445","web_search":"0","internal_reasoning":"0"},"created":1724803200,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","pricing":{"prompt":"0.00000065","completion":"0.00000075","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724803200,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-3.5-mini-128k-instruct","name":"Microsoft: Phi-3.5 Mini 128K Instruct","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1724198400,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","pricing":{"prompt":"0.0000003","completion":"0.0000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723939200,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/hermes-3-llama-3.1-405b:free","name":"Nous: Hermes 3 405B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723766400,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","pricing":{"prompt":"0.000001","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723766400,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/chatgpt-4o-latest","name":"OpenAI: ChatGPT-4o","pricing":{"prompt":"0.000005","completion":"0.000015","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0"},"created":1723593600,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","pricing":{"prompt":"0.00000004","completion":"0.00000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1723507200,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0.003613","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1722902400,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.1-405b","name":"Meta: Llama 3.1 405B (base)","pricing":{"prompt":"0.000004","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1722556800,"top_provider":{"context_length":32768,"max_completion_tokens":32768,"is_moderated":false}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","pricing":{"prompt":"0.0000004","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","pricing":{"prompt":"0.00000002","completion":"0.00000003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3.1-405b-instruct:free","name":"Meta: Llama 3.1 405B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3.1-405b-instruct","name":"Meta: Llama 3.1 405B Instruct","pricing":{"prompt":"0.0000035","completion":"0.0000035","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721692800,"top_provider":{"context_length":10000,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","pricing":{"prompt":"0.00000002","completion":"0.00000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1721347200,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1721260800,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","pricing":{"prompt":"0.00000015","completion":"0.0000006","request":"0","image":"0.000217","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000075"},"created":1721260800,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","pricing":{"prompt":"0.00000065","completion":"0.00000065","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1720828800,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"google/gemma-2-9b-it","name":"Google: Gemma 2 9B","pricing":{"prompt":"0.00000003","completion":"0.00000009","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1719532800,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"sao10k/l3-euryale-70b","name":"Sao10k: Llama 3 Euryale 70B v2.1","pricing":{"prompt":"0.00000148","completion":"0.00000148","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1718668800,"top_provider":{"context_length":8192,"max_completion_tokens":8192,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct:free","name":"Mistral: Mistral 7B Instruct (free)","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct","name":"Mistral: Mistral 7B Instruct","pricing":{"prompt":"0.000000028","completion":"0.000000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral: Mistral 7B Instruct v0.3","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":32768,"max_completion_tokens":4096,"is_moderated":false}},{"id":"nousresearch/hermes-2-pro-llama-3-8b","name":"NousResearch: Hermes 2 Pro - Llama-3 8B","pricing":{"prompt":"0.000000025","completion":"0.00000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716768000,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false}},{"id":"microsoft/phi-3-mini-128k-instruct","name":"Microsoft: Phi-3 Mini 128K Instruct","pricing":{"prompt":"0.0000001","completion":"0.0000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716681600,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/phi-3-medium-128k-instruct","name":"Microsoft: Phi-3 Medium 128K Instruct","pricing":{"prompt":"0.000001","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1716508800,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4o","name":"OpenAI: GPT-4o","pricing":{"prompt":"0.0000025","completion":"0.00001","request":"0","image":"0.003613","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000125"},"created":1715558400,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true}},{"id":"openai/gpt-4o:extended","name":"OpenAI: GPT-4o (extended)","pricing":{"prompt":"0.000006","completion":"0.000018","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0"},"created":1715558400,"top_provider":{"context_length":128000,"max_completion_tokens":64000,"is_moderated":true}},{"id":"openai/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","pricing":{"prompt":"0.000005","completion":"0.000015","request":"0","image":"0.007225","web_search":"0","internal_reasoning":"0"},"created":1715558400,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"meta-llama/llama-guard-2-8b","name":"Meta: LlamaGuard 2 8B","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1715558400,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false}},{"id":"meta-llama/llama-3-70b-instruct","name":"Meta: Llama 3 70B Instruct","pricing":{"prompt":"0.0000003","completion":"0.0000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713398400,"top_provider":{"context_length":8192,"max_completion_tokens":16384,"is_moderated":false}},{"id":"meta-llama/llama-3-8b-instruct","name":"Meta: Llama 3 8B Instruct","pricing":{"prompt":"0.00000003","completion":"0.00000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713398400,"top_provider":{"context_length":8192,"max_completion_tokens":16384,"is_moderated":false}},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713312000,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":false}},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","pricing":{"prompt":"0.00000048","completion":"0.00000048","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1713225600,"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false}},{"id":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","pricing":{"prompt":"0.00001","completion":"0.00003","request":"0","image":"0.01445","web_search":"0","internal_reasoning":"0"},"created":1712620800,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"anthropic/claude-3-haiku","name":"Anthropic: Claude 3 Haiku","pricing":{"prompt":"0.00000025","completion":"0.00000125","request":"0","image":"0.0004","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","input_cache_write":"0.0000003"},"created":1710288000,"top_provider":{"context_length":200000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"anthropic/claude-3-opus","name":"Anthropic: Claude 3 Opus","pricing":{"prompt":"0.000015","completion":"0.000075","request":"0","image":"0.024","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000015","input_cache_write":"0.00001875"},"created":1709596800,"top_provider":{"context_length":200000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mistralai/mistral-large","name":"Mistral Large","pricing":{"prompt":"0.000002","completion":"0.000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1708905600,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4-turbo-preview","name":"OpenAI: GPT-4 Turbo Preview","pricing":{"prompt":"0.00001","completion":"0.00003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1706140800,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","pricing":{"prompt":"0.000001","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1706140800,"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":false}},{"id":"mistralai/mistral-tiny","name":"Mistral Tiny","pricing":{"prompt":"0.00000025","completion":"0.00000025","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1704844800,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mistral-7b-instruct-v0.2","name":"Mistral: Mistral 7B Instruct v0.2","pricing":{"prompt":"0.0000002","completion":"0.0000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1703721600,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false}},{"id":"mistralai/mixtral-8x7b-instruct","name":"Mistral: Mixtral 8x7B Instruct","pricing":{"prompt":"0.00000054","completion":"0.00000054","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1702166400,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false}},{"id":"neversleep/noromaid-20b","name":"Noromaid 20B","pricing":{"prompt":"0.000001","completion":"0.00000175","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1700956800,"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false}},{"id":"alpindale/goliath-120b","name":"Goliath 120B","pricing":{"prompt":"0.000006","completion":"0.000008","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1699574400,"top_provider":{"context_length":6144,"max_completion_tokens":1024,"is_moderated":false}},{"id":"openrouter/auto","name":"Auto Router","pricing":{"prompt":"-1","completion":"-1"},"created":1699401600,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4-1106-preview","name":"OpenAI: GPT-4 Turbo (older v1106)","pricing":{"prompt":"0.00001","completion":"0.00003","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1699228800,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","pricing":{"prompt":"0.0000015","completion":"0.000002","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1695859200,"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mistralai/mistral-7b-instruct-v0.1","name":"Mistral: Mistral 7B Instruct v0.1","pricing":{"prompt":"0.00000011","completion":"0.00000019","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1695859200,"top_provider":{"context_length":2824,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","pricing":{"prompt":"0.000003","completion":"0.000004","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1693180800,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true}},{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","pricing":{"prompt":"0.00000075","completion":"0.000001","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1690934400,"top_provider":{"context_length":8000,"max_completion_tokens":2000,"is_moderated":false}},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","pricing":{"prompt":"0.00000045","completion":"0.00000065","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1689984000,"top_provider":{"context_length":6144,"max_completion_tokens":null,"is_moderated":false}},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","pricing":{"prompt":"0.00000006","completion":"0.00000006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1688256000,"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false}},{"id":"openai/gpt-4-0314","name":"OpenAI: GPT-4 (older v0314)","pricing":{"prompt":"0.00003","completion":"0.00006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1685232000,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","pricing":{"prompt":"0.00003","completion":"0.00006","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1685232000,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":true}},{"id":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","pricing":{"prompt":"0.0000005","completion":"0.0000015","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"created":1685232000,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true}}]
\ No newline at end of file
diff --git a/packages/kbot/dist/package-lock.json b/packages/kbot/dist/package-lock.json
index a86fc6d0..c61820cf 100644
--- a/packages/kbot/dist/package-lock.json
+++ b/packages/kbot/dist/package-lock.json
@@ -1,12 +1,12 @@
{
"name": "@plastichub/kbot",
- "version": "1.1.55",
+ "version": "1.1.56",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@plastichub/kbot",
- "version": "1.1.55",
+ "version": "1.1.56",
"license": "ISC",
"dependencies": {
"node-emoji": "^2.2.0"
diff --git a/packages/kbot/dist/package.json b/packages/kbot/dist/package.json
index 2016812c..76884751 100644
--- a/packages/kbot/dist/package.json
+++ b/packages/kbot/dist/package.json
@@ -1,6 +1,6 @@
{
"name": "@plastichub/kbot",
- "version": "1.1.55",
+ "version": "1.1.56",
"main": "main_node.js",
"author": "",
"license": "ISC",
diff --git a/packages/kbot/schema.json b/packages/kbot/schema.json
index 1679f713..e29d7c82 100644
--- a/packages/kbot/schema.json
+++ b/packages/kbot/schema.json
@@ -119,7 +119,7 @@
},
"model": {
"type": "string",
- "description": "AI model to use for processing. Available models:\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenRouter models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nagentica-org/deepcoder-14b-preview | paid\nagentica-org/deepcoder-14b-preview:free | free\nai21/jamba-large-1.7 | paid\nai21/jamba-mini-1.7 | paid\naion-labs/aion-1.0 | paid\naion-labs/aion-1.0-mini | paid\naion-labs/aion-rp-llama-3.1-8b | paid\nalfredpros/codellama-7b-instruct-solidity | paid\nallenai/molmo-7b-d | paid\nallenai/olmo-2-0325-32b-instruct | paid\namazon/nova-lite-v1 | paid\namazon/nova-micro-v1 | paid\namazon/nova-pro-v1 | paid\nanthropic/claude-3-haiku | paid\nanthropic/claude-3-opus | paid\nanthropic/claude-3.5-haiku | paid\nanthropic/claude-3.5-haiku-20241022 | paid\nanthropic/claude-3.5-sonnet | paid\nanthropic/claude-3.5-sonnet-20240620 | paid\nanthropic/claude-3.7-sonnet | paid\nanthropic/claude-3.7-sonnet:thinking | paid\nanthropic/claude-opus-4 | paid\nanthropic/claude-opus-4.1 | paid\nanthropic/claude-sonnet-4 | paid\narcee-ai/afm-4.5b | paid\narcee-ai/coder-large | paid\narcee-ai/maestro-reasoning | paid\narcee-ai/spotlight | paid\narcee-ai/virtuoso-large | paid\narliai/qwq-32b-arliai-rpr-v1 | paid\narliai/qwq-32b-arliai-rpr-v1:free | free\nopenrouter/auto | paid\nbaidu/ernie-4.5-21b-a3b | paid\nbaidu/ernie-4.5-300b-a47b | paid\nbaidu/ernie-4.5-vl-28b-a3b | paid\nbaidu/ernie-4.5-vl-424b-a47b | paid\nbytedance/seed-oss-36b-instruct | paid\nbytedance/ui-tars-1.5-7b | paid\ndeepcogito/cogito-v2-preview-llama-109b-moe | paid\ncohere/command | paid\ncohere/command-a | paid\ncohere/command-r | paid\ncohere/command-r-03-2024 | paid\ncohere/command-r-08-2024 | paid\ncohere/command-r-plus | paid\ncohere/command-r-plus-04-2024 | paid\ncohere/command-r-plus-08-2024 | paid\ncohere/command-r7b-12-2024 | paid\ndeepcogito/cogito-v2-preview-deepseek-671b | paid\ndeepseek/deepseek-prover-v2 | paid\ndeepseek/deepseek-r1-0528-qwen3-8b | paid\ndeepseek/deepseek-r1-0528-qwen3-8b:free | free\ndeepseek/deepseek-chat | paid\ndeepseek/deepseek-chat-v3-0324 | paid\ndeepseek/deepseek-chat-v3-0324:free | free\ndeepseek/deepseek-chat-v3.1 | paid\ndeepseek/deepseek-chat-v3.1:free | free\ndeepseek/deepseek-v3.1-base | paid\ndeepseek/deepseek-r1 | paid\ndeepseek/deepseek-r1:free | free\ndeepseek/deepseek-r1-0528 | paid\ndeepseek/deepseek-r1-0528:free | free\ndeepseek/deepseek-r1-distill-llama-70b | paid\ndeepseek/deepseek-r1-distill-llama-70b:free | free\ndeepseek/deepseek-r1-distill-llama-8b | paid\ndeepseek/deepseek-r1-distill-qwen-14b | paid\ndeepseek/deepseek-r1-distill-qwen-32b | paid\ncognitivecomputations/dolphin3.0-mistral-24b | paid\ncognitivecomputations/dolphin3.0-mistral-24b:free | free\ncognitivecomputations/dolphin3.0-r1-mistral-24b | paid\ncognitivecomputations/dolphin3.0-r1-mistral-24b:free | free\neleutherai/llemma_7b | paid\nalpindale/goliath-120b | paid\ngoogle/gemini-flash-1.5 | paid\ngoogle/gemini-flash-1.5-8b | paid\ngoogle/gemini-pro-1.5 | paid\ngoogle/gemini-2.0-flash-001 | paid\ngoogle/gemini-2.0-flash-exp:free | free\ngoogle/gemini-2.0-flash-lite-001 | paid\ngoogle/gemini-2.5-flash | paid\ngoogle/gemini-2.5-flash-image-preview | paid\ngoogle/gemini-2.5-flash-lite | paid\ngoogle/gemini-2.5-flash-lite-preview-06-17 | paid\ngoogle/gemini-2.5-pro | paid\ngoogle/gemini-2.5-pro-preview-05-06 | paid\ngoogle/gemini-2.5-pro-preview | paid\ngoogle/gemma-2-27b-it | paid\ngoogle/gemma-2-9b-it | paid\ngoogle/gemma-2-9b-it:free | free\ngoogle/gemma-3-12b-it | paid\ngoogle/gemma-3-12b-it:free | free\ngoogle/gemma-3-27b-it | paid\ngoogle/gemma-3-27b-it:free | free\ngoogle/gemma-3-4b-it | paid\ngoogle/gemma-3-4b-it:free | free\ngoogle/gemma-3n-e2b-it:free | free\ngoogle/gemma-3n-e4b-it | paid\ngoogle/gemma-3n-e4b-it:free | free\ninception/mercury | paid\ninception/mercury-coder | paid\ninflection/inflection-3-pi | paid\ninflection/inflection-3-productivity | paid\nliquid/lfm-3b | paid\nliquid/lfm-7b | paid\nmeta-llama/llama-guard-3-8b | paid\nanthracite-org/magnum-v2-72b | paid\nanthracite-org/magnum-v4-72b | paid\nmancer/weaver | paid\nmeituan/longcat-flash-chat | paid\nmeta-llama/llama-3-70b-instruct | paid\nmeta-llama/llama-3-8b-instruct | paid\nmeta-llama/llama-3.1-405b | paid\nmeta-llama/llama-3.1-405b-instruct | paid\nmeta-llama/llama-3.1-405b-instruct:free | free\nmeta-llama/llama-3.1-70b-instruct | paid\nmeta-llama/llama-3.1-8b-instruct | paid\nmeta-llama/llama-3.2-11b-vision-instruct | paid\nmeta-llama/llama-3.2-1b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct:free | free\nmeta-llama/llama-3.2-90b-vision-instruct | paid\nmeta-llama/llama-3.3-70b-instruct | paid\nmeta-llama/llama-3.3-70b-instruct:free | free\nmeta-llama/llama-3.3-8b-instruct:free | free\nmeta-llama/llama-4-maverick | paid\nmeta-llama/llama-4-maverick:free | free\nmeta-llama/llama-4-scout | paid\nmeta-llama/llama-4-scout:free | free\nmeta-llama/llama-guard-4-12b | paid\nmeta-llama/llama-guard-2-8b | paid\nmicrosoft/mai-ds-r1 | paid\nmicrosoft/mai-ds-r1:free | free\nmicrosoft/phi-4 | paid\nmicrosoft/phi-4-multimodal-instruct | paid\nmicrosoft/phi-4-reasoning-plus | paid\nmicrosoft/phi-3-medium-128k-instruct | paid\nmicrosoft/phi-3-mini-128k-instruct | paid\nmicrosoft/phi-3.5-mini-128k-instruct | paid\nminimax/minimax-m1 | paid\nminimax/minimax-01 | paid\nmistralai/mistral-large | paid\nmistralai/mistral-large-2407 | paid\nmistralai/mistral-large-2411 | paid\nmistralai/mistral-small | paid\nmistralai/mistral-tiny | paid\nmistralai/codestral-2501 | paid\nmistralai/codestral-2508 | paid\nmistralai/devstral-medium | paid\nmistralai/devstral-small | paid\nmistralai/devstral-small-2505 | paid\nmistralai/devstral-small-2505:free | free\nmistralai/magistral-medium-2506 | paid\nmistralai/magistral-medium-2506:thinking | paid\nmistralai/magistral-small-2506 | paid\nmistralai/ministral-3b | paid\nmistralai/ministral-8b | paid\nmistralai/mistral-7b-instruct | paid\nmistralai/mistral-7b-instruct:free | free\nmistralai/mistral-7b-instruct-v0.1 | paid\nmistralai/mistral-7b-instruct-v0.3 | paid\nmistralai/mistral-medium-3 | paid\nmistralai/mistral-medium-3.1 | paid\nmistralai/mistral-nemo | paid\nmistralai/mistral-nemo:free | free\nmistralai/mistral-small-24b-instruct-2501 | paid\nmistralai/mistral-small-24b-instruct-2501:free | free\nmistralai/mistral-small-3.1-24b-instruct | paid\nmistralai/mistral-small-3.1-24b-instruct:free | free\nmistralai/mistral-small-3.2-24b-instruct | paid\nmistralai/mistral-small-3.2-24b-instruct:free | free\nmistralai/mixtral-8x22b-instruct | paid\nmistralai/mixtral-8x7b-instruct | paid\nmistralai/pixtral-12b | paid\nmistralai/pixtral-large-2411 | paid\nmistralai/mistral-saba | paid\nmoonshotai/kimi-dev-72b | paid\nmoonshotai/kimi-dev-72b:free | free\nmoonshotai/kimi-k2 | paid\nmoonshotai/kimi-k2:free | free\nmoonshotai/kimi-k2-0905 | paid\nmoonshotai/kimi-vl-a3b-thinking | paid\nmoonshotai/kimi-vl-a3b-thinking:free | free\nmorph/morph-v3-fast | paid\nmorph/morph-v3-large | paid\ngryphe/mythomax-l2-13b | paid\nneversleep/llama-3-lumimaid-70b | paid\nneversleep/llama-3.1-lumimaid-8b | paid\nneversleep/noromaid-20b | paid\nnousresearch/deephermes-3-llama-3-8b-preview:free | free\nnousresearch/deephermes-3-mistral-24b-preview | paid\nnousresearch/hermes-3-llama-3.1-405b | paid\nnousresearch/hermes-3-llama-3.1-70b | paid\nnousresearch/hermes-4-405b | paid\nnousresearch/hermes-4-70b | paid\nnousresearch/hermes-2-pro-llama-3-8b | paid\nnvidia/llama-3.1-nemotron-70b-instruct | paid\nnvidia/llama-3.1-nemotron-ultra-253b-v1 | paid\nnvidia/nemotron-nano-9b-v2 | paid\nnvidia/nemotron-nano-9b-v2:free | free\nopenai/chatgpt-4o-latest | paid\nopenai/codex-mini | paid\nopenai/gpt-3.5-turbo | paid\nopenai/gpt-3.5-turbo-0613 | paid\nopenai/gpt-3.5-turbo-16k | paid\nopenai/gpt-3.5-turbo-instruct | paid\nopenai/gpt-4 | paid\nopenai/gpt-4-0314 | paid\nopenai/gpt-4-turbo | paid\nopenai/gpt-4-1106-preview | paid\nopenai/gpt-4-turbo-preview | paid\nopenai/gpt-4.1 | paid\nopenai/gpt-4.1-mini | paid\nopenai/gpt-4.1-nano | paid\nopenai/gpt-4o | paid\nopenai/gpt-4o-2024-05-13 | paid\nopenai/gpt-4o-2024-08-06 | paid\nopenai/gpt-4o-2024-11-20 | paid\nopenai/gpt-4o:extended | paid\nopenai/gpt-4o-audio-preview | paid\nopenai/gpt-4o-search-preview | paid\nopenai/gpt-4o-mini | paid\nopenai/gpt-4o-mini-2024-07-18 | paid\nopenai/gpt-4o-mini-search-preview | paid\nopenai/gpt-5 | paid\nopenai/gpt-5-chat | paid\nopenai/gpt-5-mini | paid\nopenai/gpt-5-nano | paid\nopenai/gpt-oss-120b | paid\nopenai/gpt-oss-120b:free | free\nopenai/gpt-oss-20b | paid\nopenai/gpt-oss-20b:free | free\nopenai/o1 | paid\nopenai/o1-mini | paid\nopenai/o1-mini-2024-09-12 | paid\nopenai/o1-pro | paid\nopenai/o3 | paid\nopenai/o3-mini | paid\nopenai/o3-mini-high | paid\nopenai/o3-pro | paid\nopenai/o4-mini | paid\nopenai/o4-mini-high | paid\nopengvlab/internvl3-78b | paid\nperplexity/r1-1776 | paid\nperplexity/sonar | paid\nperplexity/sonar-deep-research | paid\nperplexity/sonar-pro | paid\nperplexity/sonar-reasoning | paid\nperplexity/sonar-reasoning-pro | paid\nqwen/qwen-plus-2025-07-28 | paid\nqwen/qwen-plus-2025-07-28:thinking | paid\nqwen/qwen-vl-max | paid\nqwen/qwen-vl-plus | paid\nqwen/qwen-max | paid\nqwen/qwen-plus | paid\nqwen/qwen-turbo | paid\nqwen/qwen2.5-vl-32b-instruct | paid\nqwen/qwen2.5-vl-32b-instruct:free | free\nqwen/qwen2.5-vl-72b-instruct | paid\nqwen/qwen2.5-vl-72b-instruct:free | free\nqwen/qwen-2.5-vl-7b-instruct | paid\nqwen/qwen3-14b | paid\nqwen/qwen3-14b:free | free\nqwen/qwen3-235b-a22b | paid\nqwen/qwen3-235b-a22b:free | free\nqwen/qwen3-235b-a22b-2507 | paid\nqwen/qwen3-235b-a22b-thinking-2507 | paid\nqwen/qwen3-30b-a3b | paid\nqwen/qwen3-30b-a3b:free | free\nqwen/qwen3-30b-a3b-instruct-2507 | paid\nqwen/qwen3-30b-a3b-thinking-2507 | paid\nqwen/qwen3-32b | paid\nqwen/qwen3-4b:free | free\nqwen/qwen3-8b | paid\nqwen/qwen3-8b:free | free\nqwen/qwen3-coder-30b-a3b-instruct | paid\nqwen/qwen3-coder | paid\nqwen/qwen3-coder:free | free\nqwen/qwen3-coder-flash | paid\nqwen/qwen3-coder-plus | paid\nqwen/qwen3-max | paid\nqwen/qwen3-next-80b-a3b-instruct | paid\nqwen/qwen3-next-80b-a3b-thinking | paid\nqwen/qwq-32b | paid\nqwen/qwq-32b:free | free\nqwen/qwq-32b-preview | paid\nqwen/qwen-2.5-72b-instruct | paid\nqwen/qwen-2.5-72b-instruct:free | free\nqwen/qwen-2.5-7b-instruct | paid\nqwen/qwen-2.5-coder-32b-instruct | paid\nqwen/qwen-2.5-coder-32b-instruct:free | free\nundi95/remm-slerp-l2-13b | paid\nsao10k/l3-lunaris-8b | paid\nsao10k/l3-euryale-70b | paid\nsao10k/l3.1-euryale-70b | paid\nsao10k/l3.3-euryale-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b:free | free\nraifle/sorcererlm-8x22b | paid\nstepfun-ai/step3 | paid\nswitchpoint/router | paid\ntencent/hunyuan-a13b-instruct | paid\ntencent/hunyuan-a13b-instruct:free | free\nthedrummer/anubis-70b-v1.1 | paid\nthedrummer/anubis-pro-105b-v1 | paid\nthedrummer/rocinante-12b | paid\nthedrummer/skyfall-36b-v2 | paid\nthedrummer/unslopnemo-12b | paid\nthudm/glm-4.1v-9b-thinking | paid\nthudm/glm-z1-32b | paid\ntngtech/deepseek-r1t-chimera | paid\ntngtech/deepseek-r1t-chimera:free | free\ntngtech/deepseek-r1t2-chimera:free | free\nalibaba/tongyi-deepresearch-30b-a3b | paid\ncognitivecomputations/dolphin-mistral-24b-venice-edition:free | free\nmicrosoft/wizardlm-2-8x22b | paid\nx-ai/grok-3 | paid\nx-ai/grok-3-beta | paid\nx-ai/grok-3-mini | paid\nx-ai/grok-3-mini-beta | paid\nx-ai/grok-4 | paid\nx-ai/grok-4-fast:free | free\nx-ai/grok-code-fast-1 | paid\nz-ai/glm-4-32b | paid\nz-ai/glm-4.5 | paid\nz-ai/glm-4.5-air | paid\nz-ai/glm-4.5-air:free | free\nz-ai/glm-4.5v | paid\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenAI models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nbabbage-002\nchatgpt-4o-latest\ncodex-mini-latest\ndall-e-2\ndall-e-3\ndavinci-002\ngpt-3.5-turbo\ngpt-3.5-turbo-0125\ngpt-3.5-turbo-1106\ngpt-3.5-turbo-16k\ngpt-3.5-turbo-instruct\ngpt-3.5-turbo-instruct-0914\ngpt-4\ngpt-4-0125-preview\ngpt-4-0613\ngpt-4-1106-preview\ngpt-4-turbo\ngpt-4-turbo-2024-04-09\ngpt-4-turbo-preview\ngpt-4.1\ngpt-4.1-2025-04-14\ngpt-4.1-mini\ngpt-4.1-mini-2025-04-14\ngpt-4.1-nano\ngpt-4.1-nano-2025-04-14\ngpt-4o\ngpt-4o-2024-05-13\ngpt-4o-2024-08-06\ngpt-4o-2024-11-20\ngpt-4o-audio-preview\ngpt-4o-audio-preview-2024-10-01\ngpt-4o-audio-preview-2024-12-17\ngpt-4o-audio-preview-2025-06-03\ngpt-4o-mini\ngpt-4o-mini-2024-07-18\ngpt-4o-mini-audio-preview\ngpt-4o-mini-audio-preview-2024-12-17\ngpt-4o-mini-realtime-preview\ngpt-4o-mini-realtime-preview-2024-12-17\ngpt-4o-mini-search-preview\ngpt-4o-mini-search-preview-2025-03-11\ngpt-4o-mini-transcribe\ngpt-4o-mini-tts\ngpt-4o-realtime-preview\ngpt-4o-realtime-preview-2024-10-01\ngpt-4o-realtime-preview-2024-12-17\ngpt-4o-realtime-preview-2025-06-03\ngpt-4o-search-preview\ngpt-4o-search-preview-2025-03-11\ngpt-4o-transcribe\ngpt-5\ngpt-5-2025-08-07\ngpt-5-chat-latest\ngpt-5-mini\ngpt-5-mini-2025-08-07\ngpt-5-nano\ngpt-5-nano-2025-08-07\ngpt-audio\ngpt-audio-2025-08-28\ngpt-image-1\ngpt-realtime\ngpt-realtime-2025-08-28\no1\no1-2024-12-17\no1-mini\no1-mini-2024-09-12\no1-pro\no1-pro-2025-03-19\no3\no3-2025-04-16\no3-mini\no3-mini-2025-01-31\no4-mini\no4-mini-2025-04-16\no4-mini-deep-research\no4-mini-deep-research-2025-06-26\nomni-moderation-2024-09-26\nomni-moderation-latest\ntext-embedding-3-large\ntext-embedding-3-small\ntext-embedding-ada-002\ntts-1\ntts-1-1106\ntts-1-hd\ntts-1-hd-1106\nwhisper-1\n-----\n\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m Deepseek models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\ndeepseek-chat\ndeepseek-reasoner\n-----\n"
+ "description": "AI model to use for processing. Available models:\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenRouter models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nagentica-org/deepcoder-14b-preview | paid\nagentica-org/deepcoder-14b-preview:free | free\nai21/jamba-large-1.7 | paid\nai21/jamba-mini-1.7 | paid\naion-labs/aion-1.0 | paid\naion-labs/aion-1.0-mini | paid\naion-labs/aion-rp-llama-3.1-8b | paid\nalfredpros/codellama-7b-instruct-solidity | paid\nallenai/molmo-7b-d | paid\nallenai/olmo-2-0325-32b-instruct | paid\namazon/nova-lite-v1 | paid\namazon/nova-micro-v1 | paid\namazon/nova-pro-v1 | paid\nanthropic/claude-3-haiku | paid\nanthropic/claude-3-opus | paid\nanthropic/claude-3.5-haiku | paid\nanthropic/claude-3.5-haiku-20241022 | paid\nanthropic/claude-3.5-sonnet | paid\nanthropic/claude-3.5-sonnet-20240620 | paid\nanthropic/claude-3.7-sonnet | paid\nanthropic/claude-3.7-sonnet:thinking | paid\nanthropic/claude-opus-4 | paid\nanthropic/claude-opus-4.1 | paid\nanthropic/claude-sonnet-4 | paid\nanthropic/claude-sonnet-4.5 | paid\narcee-ai/afm-4.5b | paid\narcee-ai/coder-large | paid\narcee-ai/maestro-reasoning | paid\narcee-ai/spotlight | paid\narcee-ai/virtuoso-large | paid\narliai/qwq-32b-arliai-rpr-v1 | paid\narliai/qwq-32b-arliai-rpr-v1:free | free\nopenrouter/auto | paid\nbaidu/ernie-4.5-21b-a3b | paid\nbaidu/ernie-4.5-21b-a3b-thinking | paid\nbaidu/ernie-4.5-300b-a47b | paid\nbaidu/ernie-4.5-vl-28b-a3b | paid\nbaidu/ernie-4.5-vl-424b-a47b | paid\nbytedance/ui-tars-1.5-7b | paid\ndeepcogito/cogito-v2-preview-llama-109b-moe | paid\ncohere/command-a | paid\ncohere/command-r-08-2024 | paid\ncohere/command-r-plus-08-2024 | paid\ncohere/command-r7b-12-2024 | paid\ndeepcogito/cogito-v2-preview-deepseek-671b | paid\ndeepseek/deepseek-prover-v2 | paid\ndeepseek/deepseek-r1-0528-qwen3-8b | paid\ndeepseek/deepseek-r1-0528-qwen3-8b:free | free\ndeepseek/deepseek-chat | paid\ndeepseek/deepseek-chat-v3-0324 | paid\ndeepseek/deepseek-chat-v3-0324:free | free\ndeepseek/deepseek-chat-v3.1 | paid\ndeepseek/deepseek-chat-v3.1:free | free\ndeepseek/deepseek-v3.1-terminus | paid\ndeepseek/deepseek-v3.2-exp | paid\ndeepseek/deepseek-r1 | paid\ndeepseek/deepseek-r1:free | free\ndeepseek/deepseek-r1-0528 | paid\ndeepseek/deepseek-r1-0528:free | free\ndeepseek/deepseek-r1-distill-llama-70b | paid\ndeepseek/deepseek-r1-distill-llama-70b:free | free\ndeepseek/deepseek-r1-distill-qwen-14b | paid\ndeepseek/deepseek-r1-distill-qwen-32b | paid\ncognitivecomputations/dolphin3.0-mistral-24b | paid\ncognitivecomputations/dolphin3.0-mistral-24b:free | free\neleutherai/llemma_7b | paid\nalpindale/goliath-120b | paid\ngoogle/gemini-2.0-flash-001 | paid\ngoogle/gemini-2.0-flash-exp:free | free\ngoogle/gemini-2.0-flash-lite-001 | paid\ngoogle/gemini-2.5-flash | paid\ngoogle/gemini-2.5-flash-image | paid\ngoogle/gemini-2.5-flash-image-preview | paid\ngoogle/gemini-2.5-flash-lite | paid\ngoogle/gemini-2.5-flash-lite-preview-06-17 | paid\ngoogle/gemini-2.5-flash-lite-preview-09-2025 | paid\ngoogle/gemini-2.5-flash-preview-09-2025 | paid\ngoogle/gemini-2.5-pro | paid\ngoogle/gemini-2.5-pro-preview-05-06 | paid\ngoogle/gemini-2.5-pro-preview | paid\ngoogle/gemma-2-27b-it | paid\ngoogle/gemma-2-9b-it | paid\ngoogle/gemma-2-9b-it:free | free\ngoogle/gemma-3-12b-it | paid\ngoogle/gemma-3-12b-it:free | free\ngoogle/gemma-3-27b-it | paid\ngoogle/gemma-3-27b-it:free | free\ngoogle/gemma-3-4b-it | paid\ngoogle/gemma-3-4b-it:free | free\ngoogle/gemma-3n-e2b-it:free | free\ngoogle/gemma-3n-e4b-it | paid\ngoogle/gemma-3n-e4b-it:free | free\ninception/mercury | paid\ninception/mercury-coder | paid\ninclusionai/ling-1t | paid\ninflection/inflection-3-pi | paid\ninflection/inflection-3-productivity | paid\nliquid/lfm-3b | paid\nliquid/lfm-7b | paid\nmeta-llama/llama-guard-3-8b | paid\nanthracite-org/magnum-v2-72b | paid\nanthracite-org/magnum-v4-72b | paid\nmancer/weaver | paid\nmeituan/longcat-flash-chat | paid\nmeituan/longcat-flash-chat:free | free\nmeta-llama/llama-3-70b-instruct | paid\nmeta-llama/llama-3-8b-instruct | paid\nmeta-llama/llama-3.1-405b | paid\nmeta-llama/llama-3.1-405b-instruct | paid\nmeta-llama/llama-3.1-70b-instruct | paid\nmeta-llama/llama-3.1-8b-instruct | paid\nmeta-llama/llama-3.2-11b-vision-instruct | paid\nmeta-llama/llama-3.2-1b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct:free | free\nmeta-llama/llama-3.2-90b-vision-instruct | paid\nmeta-llama/llama-3.3-70b-instruct | paid\nmeta-llama/llama-3.3-70b-instruct:free | free\nmeta-llama/llama-3.3-8b-instruct:free | free\nmeta-llama/llama-4-maverick | paid\nmeta-llama/llama-4-maverick:free | free\nmeta-llama/llama-4-scout | paid\nmeta-llama/llama-4-scout:free | free\nmeta-llama/llama-guard-4-12b | paid\nmeta-llama/llama-guard-2-8b | paid\nmicrosoft/mai-ds-r1 | paid\nmicrosoft/mai-ds-r1:free | free\nmicrosoft/phi-4 | paid\nmicrosoft/phi-4-multimodal-instruct | paid\nmicrosoft/phi-4-reasoning-plus | paid\nmicrosoft/phi-3-medium-128k-instruct | paid\nmicrosoft/phi-3-mini-128k-instruct | paid\nmicrosoft/phi-3.5-mini-128k-instruct | paid\nminimax/minimax-m1 | paid\nminimax/minimax-01 | paid\nmistralai/mistral-large | paid\nmistralai/mistral-large-2407 | paid\nmistralai/mistral-large-2411 | paid\nmistralai/mistral-small | paid\nmistralai/mistral-tiny | paid\nmistralai/codestral-2501 | paid\nmistralai/codestral-2508 | paid\nmistralai/devstral-medium | paid\nmistralai/devstral-small | paid\nmistralai/devstral-small-2505 | paid\nmistralai/devstral-small-2505:free | free\nmistralai/magistral-medium-2506 | paid\nmistralai/magistral-medium-2506:thinking | paid\nmistralai/magistral-small-2506 | paid\nmistralai/ministral-3b | paid\nmistralai/ministral-8b | paid\nmistralai/mistral-7b-instruct | paid\nmistralai/mistral-7b-instruct:free | free\nmistralai/mistral-7b-instruct-v0.1 | paid\nmistralai/mistral-7b-instruct-v0.2 | paid\nmistralai/mistral-7b-instruct-v0.3 | paid\nmistralai/mistral-medium-3 | paid\nmistralai/mistral-medium-3.1 | paid\nmistralai/mistral-nemo | paid\nmistralai/mistral-nemo:free | free\nmistralai/mistral-small-24b-instruct-2501 | paid\nmistralai/mistral-small-24b-instruct-2501:free | free\nmistralai/mistral-small-3.1-24b-instruct | paid\nmistralai/mistral-small-3.1-24b-instruct:free | free\nmistralai/mistral-small-3.2-24b-instruct | paid\nmistralai/mistral-small-3.2-24b-instruct:free | free\nmistralai/mixtral-8x22b-instruct | paid\nmistralai/mixtral-8x7b-instruct | paid\nmistralai/pixtral-12b | paid\nmistralai/pixtral-large-2411 | paid\nmistralai/mistral-saba | paid\nmoonshotai/kimi-dev-72b | paid\nmoonshotai/kimi-dev-72b:free | free\nmoonshotai/kimi-k2 | paid\nmoonshotai/kimi-k2:free | free\nmoonshotai/kimi-k2-0905 | paid\nmorph/morph-v3-fast | paid\nmorph/morph-v3-large | paid\ngryphe/mythomax-l2-13b | paid\nneversleep/llama-3.1-lumimaid-8b | paid\nneversleep/noromaid-20b | paid\nnousresearch/deephermes-3-llama-3-8b-preview | paid\nnousresearch/deephermes-3-llama-3-8b-preview:free | free\nnousresearch/deephermes-3-mistral-24b-preview | paid\nnousresearch/hermes-3-llama-3.1-405b | paid\nnousresearch/hermes-3-llama-3.1-70b | paid\nnousresearch/hermes-4-405b | paid\nnousresearch/hermes-4-70b | paid\nnousresearch/hermes-2-pro-llama-3-8b | paid\nnvidia/llama-3.1-nemotron-70b-instruct | paid\nnvidia/llama-3.1-nemotron-ultra-253b-v1 | paid\nnvidia/llama-3.3-nemotron-super-49b-v1.5 | paid\nnvidia/nemotron-nano-9b-v2 | paid\nnvidia/nemotron-nano-9b-v2:free | free\nopenai/chatgpt-4o-latest | paid\nopenai/codex-mini | paid\nopenai/gpt-3.5-turbo | paid\nopenai/gpt-3.5-turbo-0613 | paid\nopenai/gpt-3.5-turbo-16k | paid\nopenai/gpt-3.5-turbo-instruct | paid\nopenai/gpt-4 | paid\nopenai/gpt-4-0314 | paid\nopenai/gpt-4-turbo | paid\nopenai/gpt-4-1106-preview | paid\nopenai/gpt-4-turbo-preview | paid\nopenai/gpt-4.1 | paid\nopenai/gpt-4.1-mini | paid\nopenai/gpt-4.1-nano | paid\nopenai/gpt-4o | paid\nopenai/gpt-4o-2024-05-13 | paid\nopenai/gpt-4o-2024-08-06 | paid\nopenai/gpt-4o-2024-11-20 | paid\nopenai/gpt-4o:extended | paid\nopenai/gpt-4o-audio-preview | paid\nopenai/gpt-4o-search-preview | paid\nopenai/gpt-4o-mini | paid\nopenai/gpt-4o-mini-2024-07-18 | paid\nopenai/gpt-4o-mini-search-preview | paid\nopenai/gpt-5 | paid\nopenai/gpt-5-chat | paid\nopenai/gpt-5-codex | paid\nopenai/gpt-5-mini | paid\nopenai/gpt-5-nano | paid\nopenai/gpt-5-pro | paid\nopenai/gpt-oss-120b | paid\nopenai/gpt-oss-20b | paid\nopenai/gpt-oss-20b:free | free\nopenai/o1 | paid\nopenai/o1-mini | paid\nopenai/o1-mini-2024-09-12 | paid\nopenai/o1-pro | paid\nopenai/o3 | paid\nopenai/o3-mini | paid\nopenai/o3-mini-high | paid\nopenai/o3-pro | paid\nopenai/o4-mini | paid\nopenai/o4-mini-high | paid\nopengvlab/internvl3-78b | paid\nperplexity/r1-1776 | paid\nperplexity/sonar | paid\nperplexity/sonar-deep-research | paid\nperplexity/sonar-pro | paid\nperplexity/sonar-reasoning | paid\nperplexity/sonar-reasoning-pro | paid\nqwen/qwen-plus-2025-07-28 | paid\nqwen/qwen-plus-2025-07-28:thinking | paid\nqwen/qwen-vl-max | paid\nqwen/qwen-vl-plus | paid\nqwen/qwen-max | paid\nqwen/qwen-plus | paid\nqwen/qwen-turbo | paid\nqwen/qwen-2.5-7b-instruct | paid\nqwen/qwen2.5-coder-7b-instruct | paid\nqwen/qwen2.5-vl-32b-instruct | paid\nqwen/qwen2.5-vl-32b-instruct:free | free\nqwen/qwen2.5-vl-72b-instruct | paid\nqwen/qwen2.5-vl-72b-instruct:free | free\nqwen/qwen-2.5-vl-7b-instruct | paid\nqwen/qwen3-14b | paid\nqwen/qwen3-14b:free | free\nqwen/qwen3-235b-a22b | paid\nqwen/qwen3-235b-a22b:free | free\nqwen/qwen3-235b-a22b-2507 | paid\nqwen/qwen3-235b-a22b-thinking-2507 | paid\nqwen/qwen3-30b-a3b | paid\nqwen/qwen3-30b-a3b:free | free\nqwen/qwen3-30b-a3b-instruct-2507 | paid\nqwen/qwen3-30b-a3b-thinking-2507 | paid\nqwen/qwen3-32b | paid\nqwen/qwen3-4b:free | free\nqwen/qwen3-8b | paid\nqwen/qwen3-8b:free | free\nqwen/qwen3-coder-30b-a3b-instruct | paid\nqwen/qwen3-coder | paid\nqwen/qwen3-coder:free | free\nqwen/qwen3-coder-flash | paid\nqwen/qwen3-coder-plus | paid\nqwen/qwen3-max | paid\nqwen/qwen3-next-80b-a3b-instruct | paid\nqwen/qwen3-next-80b-a3b-thinking | paid\nqwen/qwen3-vl-235b-a22b-instruct | paid\nqwen/qwen3-vl-235b-a22b-thinking | paid\nqwen/qwen3-vl-30b-a3b-instruct | paid\nqwen/qwen3-vl-30b-a3b-thinking | paid\nqwen/qwq-32b | paid\nqwen/qwen-2.5-72b-instruct | paid\nqwen/qwen-2.5-72b-instruct:free | free\nqwen/qwen-2.5-coder-32b-instruct | paid\nqwen/qwen-2.5-coder-32b-instruct:free | free\nrelace/relace-apply-3 | paid\nundi95/remm-slerp-l2-13b | paid\nsao10k/l3-lunaris-8b | paid\nsao10k/l3-euryale-70b | paid\nsao10k/l3.1-70b-hanami-x1 | paid\nsao10k/l3.1-euryale-70b | paid\nsao10k/l3.3-euryale-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b:free | free\nraifle/sorcererlm-8x22b | paid\nstepfun-ai/step3 | paid\nswitchpoint/router | paid\ntencent/hunyuan-a13b-instruct | paid\ntencent/hunyuan-a13b-instruct:free | free\nthedrummer/anubis-70b-v1.1 | paid\nthedrummer/cydonia-24b-v4.1 | paid\nthedrummer/rocinante-12b | paid\nthedrummer/skyfall-36b-v2 | paid\nthedrummer/unslopnemo-12b | paid\nthudm/glm-4.1v-9b-thinking | paid\nthudm/glm-z1-32b | paid\ntngtech/deepseek-r1t-chimera | paid\ntngtech/deepseek-r1t-chimera:free | free\ntngtech/deepseek-r1t2-chimera | paid\ntngtech/deepseek-r1t2-chimera:free | free\nalibaba/tongyi-deepresearch-30b-a3b | paid\nalibaba/tongyi-deepresearch-30b-a3b:free | free\ncognitivecomputations/dolphin-mistral-24b-venice-edition:free | free\nmicrosoft/wizardlm-2-8x22b | paid\nx-ai/grok-3 | paid\nx-ai/grok-3-beta | paid\nx-ai/grok-3-mini | paid\nx-ai/grok-3-mini-beta | paid\nx-ai/grok-4 | paid\nx-ai/grok-4-fast | paid\nx-ai/grok-code-fast-1 | paid\nz-ai/glm-4-32b | paid\nz-ai/glm-4.5 | paid\nz-ai/glm-4.5-air | paid\nz-ai/glm-4.5-air:free | free\nz-ai/glm-4.5v | paid\nz-ai/glm-4.6 | paid\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenAI models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nbabbage-002\nchatgpt-4o-latest\ncodex-mini-latest\ndall-e-2\ndall-e-3\ndavinci-002\ngpt-3.5-turbo\ngpt-3.5-turbo-0125\ngpt-3.5-turbo-1106\ngpt-3.5-turbo-16k\ngpt-3.5-turbo-instruct\ngpt-3.5-turbo-instruct-0914\ngpt-4\ngpt-4-0125-preview\ngpt-4-0613\ngpt-4-1106-preview\ngpt-4-turbo\ngpt-4-turbo-2024-04-09\ngpt-4-turbo-preview\ngpt-4.1\ngpt-4.1-2025-04-14\ngpt-4.1-mini\ngpt-4.1-mini-2025-04-14\ngpt-4.1-nano\ngpt-4.1-nano-2025-04-14\ngpt-4o\ngpt-4o-2024-05-13\ngpt-4o-2024-08-06\ngpt-4o-2024-11-20\ngpt-4o-audio-preview\ngpt-4o-audio-preview-2024-10-01\ngpt-4o-audio-preview-2024-12-17\ngpt-4o-audio-preview-2025-06-03\ngpt-4o-mini\ngpt-4o-mini-2024-07-18\ngpt-4o-mini-audio-preview\ngpt-4o-mini-audio-preview-2024-12-17\ngpt-4o-mini-realtime-preview\ngpt-4o-mini-realtime-preview-2024-12-17\ngpt-4o-mini-search-preview\ngpt-4o-mini-search-preview-2025-03-11\ngpt-4o-mini-transcribe\ngpt-4o-mini-tts\ngpt-4o-realtime-preview\ngpt-4o-realtime-preview-2024-10-01\ngpt-4o-realtime-preview-2024-12-17\ngpt-4o-realtime-preview-2025-06-03\ngpt-4o-search-preview\ngpt-4o-search-preview-2025-03-11\ngpt-4o-transcribe\ngpt-5\ngpt-5-2025-08-07\ngpt-5-chat-latest\ngpt-5-codex\ngpt-5-mini\ngpt-5-mini-2025-08-07\ngpt-5-nano\ngpt-5-nano-2025-08-07\ngpt-5-pro\ngpt-5-pro-2025-10-06\ngpt-audio\ngpt-audio-2025-08-28\ngpt-audio-mini\ngpt-audio-mini-2025-10-06\ngpt-image-1\ngpt-image-1-mini\ngpt-realtime\ngpt-realtime-2025-08-28\ngpt-realtime-mini\ngpt-realtime-mini-2025-10-06\no1\no1-2024-12-17\no1-mini\no1-mini-2024-09-12\no1-pro\no1-pro-2025-03-19\no3\no3-2025-04-16\no3-mini\no3-mini-2025-01-31\no4-mini\no4-mini-2025-04-16\no4-mini-deep-research\no4-mini-deep-research-2025-06-26\nomni-moderation-2024-09-26\nomni-moderation-latest\nsora-2\nsora-2-pro\ntext-embedding-3-large\ntext-embedding-3-small\ntext-embedding-ada-002\ntts-1\ntts-1-1106\ntts-1-hd\ntts-1-hd-1106\nwhisper-1\n-----\n\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m Deepseek models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\ndeepseek-chat\ndeepseek-reasoner\n-----\n"
},
"router": {
"type": "string",
diff --git a/packages/kbot/schema_ui.json b/packages/kbot/schema_ui.json
index 200cf80c..f2290271 100644
--- a/packages/kbot/schema_ui.json
+++ b/packages/kbot/schema_ui.json
@@ -79,7 +79,7 @@
"ui:title": "Api_key"
},
"model": {
- "ui:description": "AI model to use for processing. Available models:\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenRouter models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nagentica-org/deepcoder-14b-preview | paid\nagentica-org/deepcoder-14b-preview:free | free\nai21/jamba-large-1.7 | paid\nai21/jamba-mini-1.7 | paid\naion-labs/aion-1.0 | paid\naion-labs/aion-1.0-mini | paid\naion-labs/aion-rp-llama-3.1-8b | paid\nalfredpros/codellama-7b-instruct-solidity | paid\nallenai/molmo-7b-d | paid\nallenai/olmo-2-0325-32b-instruct | paid\namazon/nova-lite-v1 | paid\namazon/nova-micro-v1 | paid\namazon/nova-pro-v1 | paid\nanthropic/claude-3-haiku | paid\nanthropic/claude-3-opus | paid\nanthropic/claude-3.5-haiku | paid\nanthropic/claude-3.5-haiku-20241022 | paid\nanthropic/claude-3.5-sonnet | paid\nanthropic/claude-3.5-sonnet-20240620 | paid\nanthropic/claude-3.7-sonnet | paid\nanthropic/claude-3.7-sonnet:thinking | paid\nanthropic/claude-opus-4 | paid\nanthropic/claude-opus-4.1 | paid\nanthropic/claude-sonnet-4 | paid\narcee-ai/afm-4.5b | paid\narcee-ai/coder-large | paid\narcee-ai/maestro-reasoning | paid\narcee-ai/spotlight | paid\narcee-ai/virtuoso-large | paid\narliai/qwq-32b-arliai-rpr-v1 | paid\narliai/qwq-32b-arliai-rpr-v1:free | free\nopenrouter/auto | paid\nbaidu/ernie-4.5-21b-a3b | paid\nbaidu/ernie-4.5-300b-a47b | paid\nbaidu/ernie-4.5-vl-28b-a3b | paid\nbaidu/ernie-4.5-vl-424b-a47b | paid\nbytedance/seed-oss-36b-instruct | paid\nbytedance/ui-tars-1.5-7b | paid\ndeepcogito/cogito-v2-preview-llama-109b-moe | paid\ncohere/command | paid\ncohere/command-a | paid\ncohere/command-r | paid\ncohere/command-r-03-2024 | paid\ncohere/command-r-08-2024 | paid\ncohere/command-r-plus | paid\ncohere/command-r-plus-04-2024 | paid\ncohere/command-r-plus-08-2024 | paid\ncohere/command-r7b-12-2024 | paid\ndeepcogito/cogito-v2-preview-deepseek-671b | paid\ndeepseek/deepseek-prover-v2 | paid\ndeepseek/deepseek-r1-0528-qwen3-8b | paid\ndeepseek/deepseek-r1-0528-qwen3-8b:free | free\ndeepseek/deepseek-chat | paid\ndeepseek/deepseek-chat-v3-0324 | paid\ndeepseek/deepseek-chat-v3-0324:free | free\ndeepseek/deepseek-chat-v3.1 | paid\ndeepseek/deepseek-chat-v3.1:free | free\ndeepseek/deepseek-v3.1-base | paid\ndeepseek/deepseek-r1 | paid\ndeepseek/deepseek-r1:free | free\ndeepseek/deepseek-r1-0528 | paid\ndeepseek/deepseek-r1-0528:free | free\ndeepseek/deepseek-r1-distill-llama-70b | paid\ndeepseek/deepseek-r1-distill-llama-70b:free | free\ndeepseek/deepseek-r1-distill-llama-8b | paid\ndeepseek/deepseek-r1-distill-qwen-14b | paid\ndeepseek/deepseek-r1-distill-qwen-32b | paid\ncognitivecomputations/dolphin3.0-mistral-24b | paid\ncognitivecomputations/dolphin3.0-mistral-24b:free | free\ncognitivecomputations/dolphin3.0-r1-mistral-24b | paid\ncognitivecomputations/dolphin3.0-r1-mistral-24b:free | free\neleutherai/llemma_7b | paid\nalpindale/goliath-120b | paid\ngoogle/gemini-flash-1.5 | paid\ngoogle/gemini-flash-1.5-8b | paid\ngoogle/gemini-pro-1.5 | paid\ngoogle/gemini-2.0-flash-001 | paid\ngoogle/gemini-2.0-flash-exp:free | free\ngoogle/gemini-2.0-flash-lite-001 | paid\ngoogle/gemini-2.5-flash | paid\ngoogle/gemini-2.5-flash-image-preview | paid\ngoogle/gemini-2.5-flash-lite | paid\ngoogle/gemini-2.5-flash-lite-preview-06-17 | paid\ngoogle/gemini-2.5-pro | paid\ngoogle/gemini-2.5-pro-preview-05-06 | paid\ngoogle/gemini-2.5-pro-preview | paid\ngoogle/gemma-2-27b-it | paid\ngoogle/gemma-2-9b-it | paid\ngoogle/gemma-2-9b-it:free | free\ngoogle/gemma-3-12b-it | paid\ngoogle/gemma-3-12b-it:free | free\ngoogle/gemma-3-27b-it | paid\ngoogle/gemma-3-27b-it:free | free\ngoogle/gemma-3-4b-it | paid\ngoogle/gemma-3-4b-it:free | free\ngoogle/gemma-3n-e2b-it:free | free\ngoogle/gemma-3n-e4b-it | paid\ngoogle/gemma-3n-e4b-it:free | free\ninception/mercury | paid\ninception/mercury-coder | paid\ninflection/inflection-3-pi | paid\ninflection/inflection-3-productivity | paid\nliquid/lfm-3b | paid\nliquid/lfm-7b | paid\nmeta-llama/llama-guard-3-8b | paid\nanthracite-org/magnum-v2-72b | paid\nanthracite-org/magnum-v4-72b | paid\nmancer/weaver | paid\nmeituan/longcat-flash-chat | paid\nmeta-llama/llama-3-70b-instruct | paid\nmeta-llama/llama-3-8b-instruct | paid\nmeta-llama/llama-3.1-405b | paid\nmeta-llama/llama-3.1-405b-instruct | paid\nmeta-llama/llama-3.1-405b-instruct:free | free\nmeta-llama/llama-3.1-70b-instruct | paid\nmeta-llama/llama-3.1-8b-instruct | paid\nmeta-llama/llama-3.2-11b-vision-instruct | paid\nmeta-llama/llama-3.2-1b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct:free | free\nmeta-llama/llama-3.2-90b-vision-instruct | paid\nmeta-llama/llama-3.3-70b-instruct | paid\nmeta-llama/llama-3.3-70b-instruct:free | free\nmeta-llama/llama-3.3-8b-instruct:free | free\nmeta-llama/llama-4-maverick | paid\nmeta-llama/llama-4-maverick:free | free\nmeta-llama/llama-4-scout | paid\nmeta-llama/llama-4-scout:free | free\nmeta-llama/llama-guard-4-12b | paid\nmeta-llama/llama-guard-2-8b | paid\nmicrosoft/mai-ds-r1 | paid\nmicrosoft/mai-ds-r1:free | free\nmicrosoft/phi-4 | paid\nmicrosoft/phi-4-multimodal-instruct | paid\nmicrosoft/phi-4-reasoning-plus | paid\nmicrosoft/phi-3-medium-128k-instruct | paid\nmicrosoft/phi-3-mini-128k-instruct | paid\nmicrosoft/phi-3.5-mini-128k-instruct | paid\nminimax/minimax-m1 | paid\nminimax/minimax-01 | paid\nmistralai/mistral-large | paid\nmistralai/mistral-large-2407 | paid\nmistralai/mistral-large-2411 | paid\nmistralai/mistral-small | paid\nmistralai/mistral-tiny | paid\nmistralai/codestral-2501 | paid\nmistralai/codestral-2508 | paid\nmistralai/devstral-medium | paid\nmistralai/devstral-small | paid\nmistralai/devstral-small-2505 | paid\nmistralai/devstral-small-2505:free | free\nmistralai/magistral-medium-2506 | paid\nmistralai/magistral-medium-2506:thinking | paid\nmistralai/magistral-small-2506 | paid\nmistralai/ministral-3b | paid\nmistralai/ministral-8b | paid\nmistralai/mistral-7b-instruct | paid\nmistralai/mistral-7b-instruct:free | free\nmistralai/mistral-7b-instruct-v0.1 | paid\nmistralai/mistral-7b-instruct-v0.3 | paid\nmistralai/mistral-medium-3 | paid\nmistralai/mistral-medium-3.1 | paid\nmistralai/mistral-nemo | paid\nmistralai/mistral-nemo:free | free\nmistralai/mistral-small-24b-instruct-2501 | paid\nmistralai/mistral-small-24b-instruct-2501:free | free\nmistralai/mistral-small-3.1-24b-instruct | paid\nmistralai/mistral-small-3.1-24b-instruct:free | free\nmistralai/mistral-small-3.2-24b-instruct | paid\nmistralai/mistral-small-3.2-24b-instruct:free | free\nmistralai/mixtral-8x22b-instruct | paid\nmistralai/mixtral-8x7b-instruct | paid\nmistralai/pixtral-12b | paid\nmistralai/pixtral-large-2411 | paid\nmistralai/mistral-saba | paid\nmoonshotai/kimi-dev-72b | paid\nmoonshotai/kimi-dev-72b:free | free\nmoonshotai/kimi-k2 | paid\nmoonshotai/kimi-k2:free | free\nmoonshotai/kimi-k2-0905 | paid\nmoonshotai/kimi-vl-a3b-thinking | paid\nmoonshotai/kimi-vl-a3b-thinking:free | free\nmorph/morph-v3-fast | paid\nmorph/morph-v3-large | paid\ngryphe/mythomax-l2-13b | paid\nneversleep/llama-3-lumimaid-70b | paid\nneversleep/llama-3.1-lumimaid-8b | paid\nneversleep/noromaid-20b | paid\nnousresearch/deephermes-3-llama-3-8b-preview:free | free\nnousresearch/deephermes-3-mistral-24b-preview | paid\nnousresearch/hermes-3-llama-3.1-405b | paid\nnousresearch/hermes-3-llama-3.1-70b | paid\nnousresearch/hermes-4-405b | paid\nnousresearch/hermes-4-70b | paid\nnousresearch/hermes-2-pro-llama-3-8b | paid\nnvidia/llama-3.1-nemotron-70b-instruct | paid\nnvidia/llama-3.1-nemotron-ultra-253b-v1 | paid\nnvidia/nemotron-nano-9b-v2 | paid\nnvidia/nemotron-nano-9b-v2:free | free\nopenai/chatgpt-4o-latest | paid\nopenai/codex-mini | paid\nopenai/gpt-3.5-turbo | paid\nopenai/gpt-3.5-turbo-0613 | paid\nopenai/gpt-3.5-turbo-16k | paid\nopenai/gpt-3.5-turbo-instruct | paid\nopenai/gpt-4 | paid\nopenai/gpt-4-0314 | paid\nopenai/gpt-4-turbo | paid\nopenai/gpt-4-1106-preview | paid\nopenai/gpt-4-turbo-preview | paid\nopenai/gpt-4.1 | paid\nopenai/gpt-4.1-mini | paid\nopenai/gpt-4.1-nano | paid\nopenai/gpt-4o | paid\nopenai/gpt-4o-2024-05-13 | paid\nopenai/gpt-4o-2024-08-06 | paid\nopenai/gpt-4o-2024-11-20 | paid\nopenai/gpt-4o:extended | paid\nopenai/gpt-4o-audio-preview | paid\nopenai/gpt-4o-search-preview | paid\nopenai/gpt-4o-mini | paid\nopenai/gpt-4o-mini-2024-07-18 | paid\nopenai/gpt-4o-mini-search-preview | paid\nopenai/gpt-5 | paid\nopenai/gpt-5-chat | paid\nopenai/gpt-5-mini | paid\nopenai/gpt-5-nano | paid\nopenai/gpt-oss-120b | paid\nopenai/gpt-oss-120b:free | free\nopenai/gpt-oss-20b | paid\nopenai/gpt-oss-20b:free | free\nopenai/o1 | paid\nopenai/o1-mini | paid\nopenai/o1-mini-2024-09-12 | paid\nopenai/o1-pro | paid\nopenai/o3 | paid\nopenai/o3-mini | paid\nopenai/o3-mini-high | paid\nopenai/o3-pro | paid\nopenai/o4-mini | paid\nopenai/o4-mini-high | paid\nopengvlab/internvl3-78b | paid\nperplexity/r1-1776 | paid\nperplexity/sonar | paid\nperplexity/sonar-deep-research | paid\nperplexity/sonar-pro | paid\nperplexity/sonar-reasoning | paid\nperplexity/sonar-reasoning-pro | paid\nqwen/qwen-plus-2025-07-28 | paid\nqwen/qwen-plus-2025-07-28:thinking | paid\nqwen/qwen-vl-max | paid\nqwen/qwen-vl-plus | paid\nqwen/qwen-max | paid\nqwen/qwen-plus | paid\nqwen/qwen-turbo | paid\nqwen/qwen2.5-vl-32b-instruct | paid\nqwen/qwen2.5-vl-32b-instruct:free | free\nqwen/qwen2.5-vl-72b-instruct | paid\nqwen/qwen2.5-vl-72b-instruct:free | free\nqwen/qwen-2.5-vl-7b-instruct | paid\nqwen/qwen3-14b | paid\nqwen/qwen3-14b:free | free\nqwen/qwen3-235b-a22b | paid\nqwen/qwen3-235b-a22b:free | free\nqwen/qwen3-235b-a22b-2507 | paid\nqwen/qwen3-235b-a22b-thinking-2507 | paid\nqwen/qwen3-30b-a3b | paid\nqwen/qwen3-30b-a3b:free | free\nqwen/qwen3-30b-a3b-instruct-2507 | paid\nqwen/qwen3-30b-a3b-thinking-2507 | paid\nqwen/qwen3-32b | paid\nqwen/qwen3-4b:free | free\nqwen/qwen3-8b | paid\nqwen/qwen3-8b:free | free\nqwen/qwen3-coder-30b-a3b-instruct | paid\nqwen/qwen3-coder | paid\nqwen/qwen3-coder:free | free\nqwen/qwen3-coder-flash | paid\nqwen/qwen3-coder-plus | paid\nqwen/qwen3-max | paid\nqwen/qwen3-next-80b-a3b-instruct | paid\nqwen/qwen3-next-80b-a3b-thinking | paid\nqwen/qwq-32b | paid\nqwen/qwq-32b:free | free\nqwen/qwq-32b-preview | paid\nqwen/qwen-2.5-72b-instruct | paid\nqwen/qwen-2.5-72b-instruct:free | free\nqwen/qwen-2.5-7b-instruct | paid\nqwen/qwen-2.5-coder-32b-instruct | paid\nqwen/qwen-2.5-coder-32b-instruct:free | free\nundi95/remm-slerp-l2-13b | paid\nsao10k/l3-lunaris-8b | paid\nsao10k/l3-euryale-70b | paid\nsao10k/l3.1-euryale-70b | paid\nsao10k/l3.3-euryale-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b:free | free\nraifle/sorcererlm-8x22b | paid\nstepfun-ai/step3 | paid\nswitchpoint/router | paid\ntencent/hunyuan-a13b-instruct | paid\ntencent/hunyuan-a13b-instruct:free | free\nthedrummer/anubis-70b-v1.1 | paid\nthedrummer/anubis-pro-105b-v1 | paid\nthedrummer/rocinante-12b | paid\nthedrummer/skyfall-36b-v2 | paid\nthedrummer/unslopnemo-12b | paid\nthudm/glm-4.1v-9b-thinking | paid\nthudm/glm-z1-32b | paid\ntngtech/deepseek-r1t-chimera | paid\ntngtech/deepseek-r1t-chimera:free | free\ntngtech/deepseek-r1t2-chimera:free | free\nalibaba/tongyi-deepresearch-30b-a3b | paid\ncognitivecomputations/dolphin-mistral-24b-venice-edition:free | free\nmicrosoft/wizardlm-2-8x22b | paid\nx-ai/grok-3 | paid\nx-ai/grok-3-beta | paid\nx-ai/grok-3-mini | paid\nx-ai/grok-3-mini-beta | paid\nx-ai/grok-4 | paid\nx-ai/grok-4-fast:free | free\nx-ai/grok-code-fast-1 | paid\nz-ai/glm-4-32b | paid\nz-ai/glm-4.5 | paid\nz-ai/glm-4.5-air | paid\nz-ai/glm-4.5-air:free | free\nz-ai/glm-4.5v | paid\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenAI models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nbabbage-002\nchatgpt-4o-latest\ncodex-mini-latest\ndall-e-2\ndall-e-3\ndavinci-002\ngpt-3.5-turbo\ngpt-3.5-turbo-0125\ngpt-3.5-turbo-1106\ngpt-3.5-turbo-16k\ngpt-3.5-turbo-instruct\ngpt-3.5-turbo-instruct-0914\ngpt-4\ngpt-4-0125-preview\ngpt-4-0613\ngpt-4-1106-preview\ngpt-4-turbo\ngpt-4-turbo-2024-04-09\ngpt-4-turbo-preview\ngpt-4.1\ngpt-4.1-2025-04-14\ngpt-4.1-mini\ngpt-4.1-mini-2025-04-14\ngpt-4.1-nano\ngpt-4.1-nano-2025-04-14\ngpt-4o\ngpt-4o-2024-05-13\ngpt-4o-2024-08-06\ngpt-4o-2024-11-20\ngpt-4o-audio-preview\ngpt-4o-audio-preview-2024-10-01\ngpt-4o-audio-preview-2024-12-17\ngpt-4o-audio-preview-2025-06-03\ngpt-4o-mini\ngpt-4o-mini-2024-07-18\ngpt-4o-mini-audio-preview\ngpt-4o-mini-audio-preview-2024-12-17\ngpt-4o-mini-realtime-preview\ngpt-4o-mini-realtime-preview-2024-12-17\ngpt-4o-mini-search-preview\ngpt-4o-mini-search-preview-2025-03-11\ngpt-4o-mini-transcribe\ngpt-4o-mini-tts\ngpt-4o-realtime-preview\ngpt-4o-realtime-preview-2024-10-01\ngpt-4o-realtime-preview-2024-12-17\ngpt-4o-realtime-preview-2025-06-03\ngpt-4o-search-preview\ngpt-4o-search-preview-2025-03-11\ngpt-4o-transcribe\ngpt-5\ngpt-5-2025-08-07\ngpt-5-chat-latest\ngpt-5-mini\ngpt-5-mini-2025-08-07\ngpt-5-nano\ngpt-5-nano-2025-08-07\ngpt-audio\ngpt-audio-2025-08-28\ngpt-image-1\ngpt-realtime\ngpt-realtime-2025-08-28\no1\no1-2024-12-17\no1-mini\no1-mini-2024-09-12\no1-pro\no1-pro-2025-03-19\no3\no3-2025-04-16\no3-mini\no3-mini-2025-01-31\no4-mini\no4-mini-2025-04-16\no4-mini-deep-research\no4-mini-deep-research-2025-06-26\nomni-moderation-2024-09-26\nomni-moderation-latest\ntext-embedding-3-large\ntext-embedding-3-small\ntext-embedding-ada-002\ntts-1\ntts-1-1106\ntts-1-hd\ntts-1-hd-1106\nwhisper-1\n-----\n\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m Deepseek models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\ndeepseek-chat\ndeepseek-reasoner\n-----\n",
+ "ui:description": "AI model to use for processing. Available models:\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenRouter models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nagentica-org/deepcoder-14b-preview | paid\nagentica-org/deepcoder-14b-preview:free | free\nai21/jamba-large-1.7 | paid\nai21/jamba-mini-1.7 | paid\naion-labs/aion-1.0 | paid\naion-labs/aion-1.0-mini | paid\naion-labs/aion-rp-llama-3.1-8b | paid\nalfredpros/codellama-7b-instruct-solidity | paid\nallenai/molmo-7b-d | paid\nallenai/olmo-2-0325-32b-instruct | paid\namazon/nova-lite-v1 | paid\namazon/nova-micro-v1 | paid\namazon/nova-pro-v1 | paid\nanthropic/claude-3-haiku | paid\nanthropic/claude-3-opus | paid\nanthropic/claude-3.5-haiku | paid\nanthropic/claude-3.5-haiku-20241022 | paid\nanthropic/claude-3.5-sonnet | paid\nanthropic/claude-3.5-sonnet-20240620 | paid\nanthropic/claude-3.7-sonnet | paid\nanthropic/claude-3.7-sonnet:thinking | paid\nanthropic/claude-opus-4 | paid\nanthropic/claude-opus-4.1 | paid\nanthropic/claude-sonnet-4 | paid\nanthropic/claude-sonnet-4.5 | paid\narcee-ai/afm-4.5b | paid\narcee-ai/coder-large | paid\narcee-ai/maestro-reasoning | paid\narcee-ai/spotlight | paid\narcee-ai/virtuoso-large | paid\narliai/qwq-32b-arliai-rpr-v1 | paid\narliai/qwq-32b-arliai-rpr-v1:free | free\nopenrouter/auto | paid\nbaidu/ernie-4.5-21b-a3b | paid\nbaidu/ernie-4.5-21b-a3b-thinking | paid\nbaidu/ernie-4.5-300b-a47b | paid\nbaidu/ernie-4.5-vl-28b-a3b | paid\nbaidu/ernie-4.5-vl-424b-a47b | paid\nbytedance/ui-tars-1.5-7b | paid\ndeepcogito/cogito-v2-preview-llama-109b-moe | paid\ncohere/command-a | paid\ncohere/command-r-08-2024 | paid\ncohere/command-r-plus-08-2024 | paid\ncohere/command-r7b-12-2024 | paid\ndeepcogito/cogito-v2-preview-deepseek-671b | paid\ndeepseek/deepseek-prover-v2 | paid\ndeepseek/deepseek-r1-0528-qwen3-8b | paid\ndeepseek/deepseek-r1-0528-qwen3-8b:free | free\ndeepseek/deepseek-chat | paid\ndeepseek/deepseek-chat-v3-0324 | paid\ndeepseek/deepseek-chat-v3-0324:free | free\ndeepseek/deepseek-chat-v3.1 | paid\ndeepseek/deepseek-chat-v3.1:free | free\ndeepseek/deepseek-v3.1-terminus | paid\ndeepseek/deepseek-v3.2-exp | paid\ndeepseek/deepseek-r1 | paid\ndeepseek/deepseek-r1:free | free\ndeepseek/deepseek-r1-0528 | paid\ndeepseek/deepseek-r1-0528:free | free\ndeepseek/deepseek-r1-distill-llama-70b | paid\ndeepseek/deepseek-r1-distill-llama-70b:free | free\ndeepseek/deepseek-r1-distill-qwen-14b | paid\ndeepseek/deepseek-r1-distill-qwen-32b | paid\ncognitivecomputations/dolphin3.0-mistral-24b | paid\ncognitivecomputations/dolphin3.0-mistral-24b:free | free\neleutherai/llemma_7b | paid\nalpindale/goliath-120b | paid\ngoogle/gemini-2.0-flash-001 | paid\ngoogle/gemini-2.0-flash-exp:free | free\ngoogle/gemini-2.0-flash-lite-001 | paid\ngoogle/gemini-2.5-flash | paid\ngoogle/gemini-2.5-flash-image | paid\ngoogle/gemini-2.5-flash-image-preview | paid\ngoogle/gemini-2.5-flash-lite | paid\ngoogle/gemini-2.5-flash-lite-preview-06-17 | paid\ngoogle/gemini-2.5-flash-lite-preview-09-2025 | paid\ngoogle/gemini-2.5-flash-preview-09-2025 | paid\ngoogle/gemini-2.5-pro | paid\ngoogle/gemini-2.5-pro-preview-05-06 | paid\ngoogle/gemini-2.5-pro-preview | paid\ngoogle/gemma-2-27b-it | paid\ngoogle/gemma-2-9b-it | paid\ngoogle/gemma-2-9b-it:free | free\ngoogle/gemma-3-12b-it | paid\ngoogle/gemma-3-12b-it:free | free\ngoogle/gemma-3-27b-it | paid\ngoogle/gemma-3-27b-it:free | free\ngoogle/gemma-3-4b-it | paid\ngoogle/gemma-3-4b-it:free | free\ngoogle/gemma-3n-e2b-it:free | free\ngoogle/gemma-3n-e4b-it | paid\ngoogle/gemma-3n-e4b-it:free | free\ninception/mercury | paid\ninception/mercury-coder | paid\ninclusionai/ling-1t | paid\ninflection/inflection-3-pi | paid\ninflection/inflection-3-productivity | paid\nliquid/lfm-3b | paid\nliquid/lfm-7b | paid\nmeta-llama/llama-guard-3-8b | paid\nanthracite-org/magnum-v2-72b | paid\nanthracite-org/magnum-v4-72b | paid\nmancer/weaver | paid\nmeituan/longcat-flash-chat | paid\nmeituan/longcat-flash-chat:free | free\nmeta-llama/llama-3-70b-instruct | paid\nmeta-llama/llama-3-8b-instruct | paid\nmeta-llama/llama-3.1-405b | paid\nmeta-llama/llama-3.1-405b-instruct | paid\nmeta-llama/llama-3.1-70b-instruct | paid\nmeta-llama/llama-3.1-8b-instruct | paid\nmeta-llama/llama-3.2-11b-vision-instruct | paid\nmeta-llama/llama-3.2-1b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct | paid\nmeta-llama/llama-3.2-3b-instruct:free | free\nmeta-llama/llama-3.2-90b-vision-instruct | paid\nmeta-llama/llama-3.3-70b-instruct | paid\nmeta-llama/llama-3.3-70b-instruct:free | free\nmeta-llama/llama-3.3-8b-instruct:free | free\nmeta-llama/llama-4-maverick | paid\nmeta-llama/llama-4-maverick:free | free\nmeta-llama/llama-4-scout | paid\nmeta-llama/llama-4-scout:free | free\nmeta-llama/llama-guard-4-12b | paid\nmeta-llama/llama-guard-2-8b | paid\nmicrosoft/mai-ds-r1 | paid\nmicrosoft/mai-ds-r1:free | free\nmicrosoft/phi-4 | paid\nmicrosoft/phi-4-multimodal-instruct | paid\nmicrosoft/phi-4-reasoning-plus | paid\nmicrosoft/phi-3-medium-128k-instruct | paid\nmicrosoft/phi-3-mini-128k-instruct | paid\nmicrosoft/phi-3.5-mini-128k-instruct | paid\nminimax/minimax-m1 | paid\nminimax/minimax-01 | paid\nmistralai/mistral-large | paid\nmistralai/mistral-large-2407 | paid\nmistralai/mistral-large-2411 | paid\nmistralai/mistral-small | paid\nmistralai/mistral-tiny | paid\nmistralai/codestral-2501 | paid\nmistralai/codestral-2508 | paid\nmistralai/devstral-medium | paid\nmistralai/devstral-small | paid\nmistralai/devstral-small-2505 | paid\nmistralai/devstral-small-2505:free | free\nmistralai/magistral-medium-2506 | paid\nmistralai/magistral-medium-2506:thinking | paid\nmistralai/magistral-small-2506 | paid\nmistralai/ministral-3b | paid\nmistralai/ministral-8b | paid\nmistralai/mistral-7b-instruct | paid\nmistralai/mistral-7b-instruct:free | free\nmistralai/mistral-7b-instruct-v0.1 | paid\nmistralai/mistral-7b-instruct-v0.2 | paid\nmistralai/mistral-7b-instruct-v0.3 | paid\nmistralai/mistral-medium-3 | paid\nmistralai/mistral-medium-3.1 | paid\nmistralai/mistral-nemo | paid\nmistralai/mistral-nemo:free | free\nmistralai/mistral-small-24b-instruct-2501 | paid\nmistralai/mistral-small-24b-instruct-2501:free | free\nmistralai/mistral-small-3.1-24b-instruct | paid\nmistralai/mistral-small-3.1-24b-instruct:free | free\nmistralai/mistral-small-3.2-24b-instruct | paid\nmistralai/mistral-small-3.2-24b-instruct:free | free\nmistralai/mixtral-8x22b-instruct | paid\nmistralai/mixtral-8x7b-instruct | paid\nmistralai/pixtral-12b | paid\nmistralai/pixtral-large-2411 | paid\nmistralai/mistral-saba | paid\nmoonshotai/kimi-dev-72b | paid\nmoonshotai/kimi-dev-72b:free | free\nmoonshotai/kimi-k2 | paid\nmoonshotai/kimi-k2:free | free\nmoonshotai/kimi-k2-0905 | paid\nmorph/morph-v3-fast | paid\nmorph/morph-v3-large | paid\ngryphe/mythomax-l2-13b | paid\nneversleep/llama-3.1-lumimaid-8b | paid\nneversleep/noromaid-20b | paid\nnousresearch/deephermes-3-llama-3-8b-preview | paid\nnousresearch/deephermes-3-llama-3-8b-preview:free | free\nnousresearch/deephermes-3-mistral-24b-preview | paid\nnousresearch/hermes-3-llama-3.1-405b | paid\nnousresearch/hermes-3-llama-3.1-70b | paid\nnousresearch/hermes-4-405b | paid\nnousresearch/hermes-4-70b | paid\nnousresearch/hermes-2-pro-llama-3-8b | paid\nnvidia/llama-3.1-nemotron-70b-instruct | paid\nnvidia/llama-3.1-nemotron-ultra-253b-v1 | paid\nnvidia/llama-3.3-nemotron-super-49b-v1.5 | paid\nnvidia/nemotron-nano-9b-v2 | paid\nnvidia/nemotron-nano-9b-v2:free | free\nopenai/chatgpt-4o-latest | paid\nopenai/codex-mini | paid\nopenai/gpt-3.5-turbo | paid\nopenai/gpt-3.5-turbo-0613 | paid\nopenai/gpt-3.5-turbo-16k | paid\nopenai/gpt-3.5-turbo-instruct | paid\nopenai/gpt-4 | paid\nopenai/gpt-4-0314 | paid\nopenai/gpt-4-turbo | paid\nopenai/gpt-4-1106-preview | paid\nopenai/gpt-4-turbo-preview | paid\nopenai/gpt-4.1 | paid\nopenai/gpt-4.1-mini | paid\nopenai/gpt-4.1-nano | paid\nopenai/gpt-4o | paid\nopenai/gpt-4o-2024-05-13 | paid\nopenai/gpt-4o-2024-08-06 | paid\nopenai/gpt-4o-2024-11-20 | paid\nopenai/gpt-4o:extended | paid\nopenai/gpt-4o-audio-preview | paid\nopenai/gpt-4o-search-preview | paid\nopenai/gpt-4o-mini | paid\nopenai/gpt-4o-mini-2024-07-18 | paid\nopenai/gpt-4o-mini-search-preview | paid\nopenai/gpt-5 | paid\nopenai/gpt-5-chat | paid\nopenai/gpt-5-codex | paid\nopenai/gpt-5-mini | paid\nopenai/gpt-5-nano | paid\nopenai/gpt-5-pro | paid\nopenai/gpt-oss-120b | paid\nopenai/gpt-oss-20b | paid\nopenai/gpt-oss-20b:free | free\nopenai/o1 | paid\nopenai/o1-mini | paid\nopenai/o1-mini-2024-09-12 | paid\nopenai/o1-pro | paid\nopenai/o3 | paid\nopenai/o3-mini | paid\nopenai/o3-mini-high | paid\nopenai/o3-pro | paid\nopenai/o4-mini | paid\nopenai/o4-mini-high | paid\nopengvlab/internvl3-78b | paid\nperplexity/r1-1776 | paid\nperplexity/sonar | paid\nperplexity/sonar-deep-research | paid\nperplexity/sonar-pro | paid\nperplexity/sonar-reasoning | paid\nperplexity/sonar-reasoning-pro | paid\nqwen/qwen-plus-2025-07-28 | paid\nqwen/qwen-plus-2025-07-28:thinking | paid\nqwen/qwen-vl-max | paid\nqwen/qwen-vl-plus | paid\nqwen/qwen-max | paid\nqwen/qwen-plus | paid\nqwen/qwen-turbo | paid\nqwen/qwen-2.5-7b-instruct | paid\nqwen/qwen2.5-coder-7b-instruct | paid\nqwen/qwen2.5-vl-32b-instruct | paid\nqwen/qwen2.5-vl-32b-instruct:free | free\nqwen/qwen2.5-vl-72b-instruct | paid\nqwen/qwen2.5-vl-72b-instruct:free | free\nqwen/qwen-2.5-vl-7b-instruct | paid\nqwen/qwen3-14b | paid\nqwen/qwen3-14b:free | free\nqwen/qwen3-235b-a22b | paid\nqwen/qwen3-235b-a22b:free | free\nqwen/qwen3-235b-a22b-2507 | paid\nqwen/qwen3-235b-a22b-thinking-2507 | paid\nqwen/qwen3-30b-a3b | paid\nqwen/qwen3-30b-a3b:free | free\nqwen/qwen3-30b-a3b-instruct-2507 | paid\nqwen/qwen3-30b-a3b-thinking-2507 | paid\nqwen/qwen3-32b | paid\nqwen/qwen3-4b:free | free\nqwen/qwen3-8b | paid\nqwen/qwen3-8b:free | free\nqwen/qwen3-coder-30b-a3b-instruct | paid\nqwen/qwen3-coder | paid\nqwen/qwen3-coder:free | free\nqwen/qwen3-coder-flash | paid\nqwen/qwen3-coder-plus | paid\nqwen/qwen3-max | paid\nqwen/qwen3-next-80b-a3b-instruct | paid\nqwen/qwen3-next-80b-a3b-thinking | paid\nqwen/qwen3-vl-235b-a22b-instruct | paid\nqwen/qwen3-vl-235b-a22b-thinking | paid\nqwen/qwen3-vl-30b-a3b-instruct | paid\nqwen/qwen3-vl-30b-a3b-thinking | paid\nqwen/qwq-32b | paid\nqwen/qwen-2.5-72b-instruct | paid\nqwen/qwen-2.5-72b-instruct:free | free\nqwen/qwen-2.5-coder-32b-instruct | paid\nqwen/qwen-2.5-coder-32b-instruct:free | free\nrelace/relace-apply-3 | paid\nundi95/remm-slerp-l2-13b | paid\nsao10k/l3-lunaris-8b | paid\nsao10k/l3-euryale-70b | paid\nsao10k/l3.1-70b-hanami-x1 | paid\nsao10k/l3.1-euryale-70b | paid\nsao10k/l3.3-euryale-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b | paid\nshisa-ai/shisa-v2-llama3.3-70b:free | free\nraifle/sorcererlm-8x22b | paid\nstepfun-ai/step3 | paid\nswitchpoint/router | paid\ntencent/hunyuan-a13b-instruct | paid\ntencent/hunyuan-a13b-instruct:free | free\nthedrummer/anubis-70b-v1.1 | paid\nthedrummer/cydonia-24b-v4.1 | paid\nthedrummer/rocinante-12b | paid\nthedrummer/skyfall-36b-v2 | paid\nthedrummer/unslopnemo-12b | paid\nthudm/glm-4.1v-9b-thinking | paid\nthudm/glm-z1-32b | paid\ntngtech/deepseek-r1t-chimera | paid\ntngtech/deepseek-r1t-chimera:free | free\ntngtech/deepseek-r1t2-chimera | paid\ntngtech/deepseek-r1t2-chimera:free | free\nalibaba/tongyi-deepresearch-30b-a3b | paid\nalibaba/tongyi-deepresearch-30b-a3b:free | free\ncognitivecomputations/dolphin-mistral-24b-venice-edition:free | free\nmicrosoft/wizardlm-2-8x22b | paid\nx-ai/grok-3 | paid\nx-ai/grok-3-beta | paid\nx-ai/grok-3-mini | paid\nx-ai/grok-3-mini-beta | paid\nx-ai/grok-4 | paid\nx-ai/grok-4-fast | paid\nx-ai/grok-code-fast-1 | paid\nz-ai/glm-4-32b | paid\nz-ai/glm-4.5 | paid\nz-ai/glm-4.5-air | paid\nz-ai/glm-4.5-air:free | free\nz-ai/glm-4.5v | paid\nz-ai/glm-4.6 | paid\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m OpenAI models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\nbabbage-002\nchatgpt-4o-latest\ncodex-mini-latest\ndall-e-2\ndall-e-3\ndavinci-002\ngpt-3.5-turbo\ngpt-3.5-turbo-0125\ngpt-3.5-turbo-1106\ngpt-3.5-turbo-16k\ngpt-3.5-turbo-instruct\ngpt-3.5-turbo-instruct-0914\ngpt-4\ngpt-4-0125-preview\ngpt-4-0613\ngpt-4-1106-preview\ngpt-4-turbo\ngpt-4-turbo-2024-04-09\ngpt-4-turbo-preview\ngpt-4.1\ngpt-4.1-2025-04-14\ngpt-4.1-mini\ngpt-4.1-mini-2025-04-14\ngpt-4.1-nano\ngpt-4.1-nano-2025-04-14\ngpt-4o\ngpt-4o-2024-05-13\ngpt-4o-2024-08-06\ngpt-4o-2024-11-20\ngpt-4o-audio-preview\ngpt-4o-audio-preview-2024-10-01\ngpt-4o-audio-preview-2024-12-17\ngpt-4o-audio-preview-2025-06-03\ngpt-4o-mini\ngpt-4o-mini-2024-07-18\ngpt-4o-mini-audio-preview\ngpt-4o-mini-audio-preview-2024-12-17\ngpt-4o-mini-realtime-preview\ngpt-4o-mini-realtime-preview-2024-12-17\ngpt-4o-mini-search-preview\ngpt-4o-mini-search-preview-2025-03-11\ngpt-4o-mini-transcribe\ngpt-4o-mini-tts\ngpt-4o-realtime-preview\ngpt-4o-realtime-preview-2024-10-01\ngpt-4o-realtime-preview-2024-12-17\ngpt-4o-realtime-preview-2025-06-03\ngpt-4o-search-preview\ngpt-4o-search-preview-2025-03-11\ngpt-4o-transcribe\ngpt-5\ngpt-5-2025-08-07\ngpt-5-chat-latest\ngpt-5-codex\ngpt-5-mini\ngpt-5-mini-2025-08-07\ngpt-5-nano\ngpt-5-nano-2025-08-07\ngpt-5-pro\ngpt-5-pro-2025-10-06\ngpt-audio\ngpt-audio-2025-08-28\ngpt-audio-mini\ngpt-audio-mini-2025-10-06\ngpt-image-1\ngpt-image-1-mini\ngpt-realtime\ngpt-realtime-2025-08-28\ngpt-realtime-mini\ngpt-realtime-mini-2025-10-06\no1\no1-2024-12-17\no1-mini\no1-mini-2024-09-12\no1-pro\no1-pro-2025-03-19\no3\no3-2025-04-16\no3-mini\no3-mini-2025-01-31\no4-mini\no4-mini-2025-04-16\no4-mini-deep-research\no4-mini-deep-research-2025-06-26\nomni-moderation-2024-09-26\nomni-moderation-latest\nsora-2\nsora-2-pro\ntext-embedding-3-large\ntext-embedding-3-small\ntext-embedding-ada-002\ntts-1\ntts-1-1106\ntts-1-hd\ntts-1-hd-1106\nwhisper-1\n-----\n\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m Deepseek models:\u001b[22m\u001b[39m\n\u001b[35m\u001b[1m\u001b[22m\u001b[39m\ndeepseek-chat\ndeepseek-reasoner\n-----\n",
"ui:title": "Model"
},
"router": {
diff --git a/packages/kbot/src/models/cache/openai-models.ts b/packages/kbot/src/models/cache/openai-models.ts
index c5292115..932310c9 100644
--- a/packages/kbot/src/models/cache/openai-models.ts
+++ b/packages/kbot/src/models/cache/openai-models.ts
@@ -2,11 +2,11 @@ export enum E_OPENAI_MODEL {
MODEL_GPT_4_0613 = "gpt-4-0613",
MODEL_GPT_4 = "gpt-4",
MODEL_GPT_3_5_TURBO = "gpt-3.5-turbo",
- MODEL_SORA_2_PRO = "sora-2-pro",
- MODEL_GPT_AUDIO_MINI_2025_10_06 = "gpt-audio-mini-2025-10-06",
- MODEL_GPT_REALTIME_MINI = "gpt-realtime-mini",
- MODEL_GPT_REALTIME_MINI_2025_10_06 = "gpt-realtime-mini-2025-10-06",
- MODEL_SORA_2 = "sora-2",
+ MODEL_CHATGPT_IMAGE_LATEST = "chatgpt-image-latest",
+ MODEL_GPT_4O_MINI_TTS_2025_03_20 = "gpt-4o-mini-tts-2025-03-20",
+ MODEL_GPT_4O_MINI_TTS_2025_12_15 = "gpt-4o-mini-tts-2025-12-15",
+ MODEL_GPT_REALTIME_MINI_2025_12_15 = "gpt-realtime-mini-2025-12-15",
+ MODEL_GPT_AUDIO_MINI_2025_12_15 = "gpt-audio-mini-2025-12-15",
MODEL_DAVINCI_002 = "davinci-002",
MODEL_BABBAGE_002 = "babbage-002",
MODEL_GPT_3_5_TURBO_INSTRUCT = "gpt-3.5-turbo-instruct",
@@ -31,10 +31,6 @@ export enum E_OPENAI_MODEL {
MODEL_GPT_4O_MINI = "gpt-4o-mini",
MODEL_GPT_4O_2024_08_06 = "gpt-4o-2024-08-06",
MODEL_CHATGPT_4O_LATEST = "chatgpt-4o-latest",
- MODEL_O1_MINI_2024_09_12 = "o1-mini-2024-09-12",
- MODEL_O1_MINI = "o1-mini",
- MODEL_GPT_4O_REALTIME_PREVIEW_2024_10_01 = "gpt-4o-realtime-preview-2024-10-01",
- MODEL_GPT_4O_AUDIO_PREVIEW_2024_10_01 = "gpt-4o-audio-preview-2024-10-01",
MODEL_GPT_4O_AUDIO_PREVIEW = "gpt-4o-audio-preview",
MODEL_GPT_4O_REALTIME_PREVIEW = "gpt-4o-realtime-preview",
MODEL_OMNI_MODERATION_LATEST = "omni-moderation-latest",
@@ -74,6 +70,7 @@ export enum E_OPENAI_MODEL {
MODEL_GPT_4O_REALTIME_PREVIEW_2025_06_03 = "gpt-4o-realtime-preview-2025-06-03",
MODEL_GPT_4O_AUDIO_PREVIEW_2025_06_03 = "gpt-4o-audio-preview-2025-06-03",
MODEL_O4_MINI_DEEP_RESEARCH = "o4-mini-deep-research",
+ MODEL_GPT_4O_TRANSCRIBE_DIARIZE = "gpt-4o-transcribe-diarize",
MODEL_O4_MINI_DEEP_RESEARCH_2025_06_26 = "o4-mini-deep-research-2025-06-26",
MODEL_GPT_5_CHAT_LATEST = "gpt-5-chat-latest",
MODEL_GPT_5_2025_08_07 = "gpt-5-2025-08-07",
@@ -91,6 +88,27 @@ export enum E_OPENAI_MODEL {
MODEL_GPT_5_PRO_2025_10_06 = "gpt-5-pro-2025-10-06",
MODEL_GPT_5_PRO = "gpt-5-pro",
MODEL_GPT_AUDIO_MINI = "gpt-audio-mini",
+ MODEL_GPT_AUDIO_MINI_2025_10_06 = "gpt-audio-mini-2025-10-06",
+ MODEL_GPT_5_SEARCH_API = "gpt-5-search-api",
+ MODEL_GPT_REALTIME_MINI = "gpt-realtime-mini",
+ MODEL_GPT_REALTIME_MINI_2025_10_06 = "gpt-realtime-mini-2025-10-06",
+ MODEL_SORA_2 = "sora-2",
+ MODEL_SORA_2_PRO = "sora-2-pro",
+ MODEL_GPT_5_SEARCH_API_2025_10_14 = "gpt-5-search-api-2025-10-14",
+ MODEL_GPT_5_1_CHAT_LATEST = "gpt-5.1-chat-latest",
+ MODEL_GPT_5_1_2025_11_13 = "gpt-5.1-2025-11-13",
+ MODEL_GPT_5_1 = "gpt-5.1",
+ MODEL_GPT_5_1_CODEX = "gpt-5.1-codex",
+ MODEL_GPT_5_1_CODEX_MINI = "gpt-5.1-codex-mini",
+ MODEL_GPT_5_1_CODEX_MAX = "gpt-5.1-codex-max",
+ MODEL_GPT_IMAGE_1_5 = "gpt-image-1.5",
+ MODEL_GPT_5_2_2025_12_11 = "gpt-5.2-2025-12-11",
+ MODEL_GPT_5_2 = "gpt-5.2",
+ MODEL_GPT_5_2_PRO_2025_12_11 = "gpt-5.2-pro-2025-12-11",
+ MODEL_GPT_5_2_PRO = "gpt-5.2-pro",
+ MODEL_GPT_5_2_CHAT_LATEST = "gpt-5.2-chat-latest",
+ MODEL_GPT_4O_MINI_TRANSCRIBE_2025_12_15 = "gpt-4o-mini-transcribe-2025-12-15",
+ MODEL_GPT_4O_MINI_TRANSCRIBE_2025_03_20 = "gpt-4o-mini-transcribe-2025-03-20",
MODEL_GPT_3_5_TURBO_16K = "gpt-3.5-turbo-16k",
MODEL_TTS_1 = "tts-1",
MODEL_WHISPER_1 = "whisper-1",
diff --git a/packages/kbot/src/models/cache/openrouter-models-free.ts b/packages/kbot/src/models/cache/openrouter-models-free.ts
index 37f6e0f8..4052e8c9 100644
--- a/packages/kbot/src/models/cache/openrouter-models-free.ts
+++ b/packages/kbot/src/models/cache/openrouter-models-free.ts
@@ -1,53 +1,37 @@
export enum E_OPENROUTER_MODEL_FREE {
+ MODEL_FREE_ALLENAI_OLMO_3_1_32B_THINK_FREE = "allenai/olmo-3.1-32b-think:free",
+ MODEL_FREE_XIAOMI_MIMO_V2_FLASH_FREE = "xiaomi/mimo-v2-flash:free",
+ MODEL_FREE_NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE = "nvidia/nemotron-3-nano-30b-a3b:free",
+ MODEL_FREE_MISTRALAI_DEVSTRAL_2512_FREE = "mistralai/devstral-2512:free",
+ MODEL_FREE_NEX_AGI_DEEPSEEK_V3_1_NEX_N1_FREE = "nex-agi/deepseek-v3.1-nex-n1:free",
+ MODEL_FREE_ARCEE_AI_TRINITY_MINI_FREE = "arcee-ai/trinity-mini:free",
+ MODEL_FREE_TNGTECH_TNG_R1T_CHIMERA_FREE = "tngtech/tng-r1t-chimera:free",
+ MODEL_FREE_ALLENAI_OLMO_3_32B_THINK_FREE = "allenai/olmo-3-32b-think:free",
+ MODEL_FREE_KWAIPILOT_KAT_CODER_PRO_FREE = "kwaipilot/kat-coder-pro:free",
+ MODEL_FREE_NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE = "nvidia/nemotron-nano-12b-v2-vl:free",
MODEL_FREE_ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B_FREE = "alibaba/tongyi-deepresearch-30b-a3b:free",
- MODEL_FREE_MEITUAN_LONGCAT_FLASH_CHAT_FREE = "meituan/longcat-flash-chat:free",
MODEL_FREE_NVIDIA_NEMOTRON_NANO_9B_V2_FREE = "nvidia/nemotron-nano-9b-v2:free",
- MODEL_FREE_DEEPSEEK_DEEPSEEK_CHAT_V3_1_FREE = "deepseek/deepseek-chat-v3.1:free",
+ MODEL_FREE_OPENAI_GPT_OSS_120B_FREE = "openai/gpt-oss-120b:free",
MODEL_FREE_OPENAI_GPT_OSS_20B_FREE = "openai/gpt-oss-20b:free",
MODEL_FREE_Z_AI_GLM_4_5_AIR_FREE = "z-ai/glm-4.5-air:free",
MODEL_FREE_QWEN_QWEN3_CODER_FREE = "qwen/qwen3-coder:free",
MODEL_FREE_MOONSHOTAI_KIMI_K2_FREE = "moonshotai/kimi-k2:free",
MODEL_FREE_COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION_FREE = "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
MODEL_FREE_GOOGLE_GEMMA_3N_E2B_IT_FREE = "google/gemma-3n-e2b-it:free",
- MODEL_FREE_TENCENT_HUNYUAN_A13B_INSTRUCT_FREE = "tencent/hunyuan-a13b-instruct:free",
MODEL_FREE_TNGTECH_DEEPSEEK_R1T2_CHIMERA_FREE = "tngtech/deepseek-r1t2-chimera:free",
- MODEL_FREE_MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.2-24b-instruct:free",
- MODEL_FREE_MOONSHOTAI_KIMI_DEV_72B_FREE = "moonshotai/kimi-dev-72b:free",
- MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_0528_QWEN3_8B_FREE = "deepseek/deepseek-r1-0528-qwen3-8b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_0528_FREE = "deepseek/deepseek-r1-0528:free",
- MODEL_FREE_MISTRALAI_DEVSTRAL_SMALL_2505_FREE = "mistralai/devstral-small-2505:free",
MODEL_FREE_GOOGLE_GEMMA_3N_E4B_IT_FREE = "google/gemma-3n-e4b-it:free",
- MODEL_FREE_META_LLAMA_LLAMA_3_3_8B_INSTRUCT_FREE = "meta-llama/llama-3.3-8b-instruct:free",
MODEL_FREE_QWEN_QWEN3_4B_FREE = "qwen/qwen3-4b:free",
- MODEL_FREE_QWEN_QWEN3_30B_A3B_FREE = "qwen/qwen3-30b-a3b:free",
- MODEL_FREE_QWEN_QWEN3_8B_FREE = "qwen/qwen3-8b:free",
- MODEL_FREE_QWEN_QWEN3_14B_FREE = "qwen/qwen3-14b:free",
- MODEL_FREE_QWEN_QWEN3_235B_A22B_FREE = "qwen/qwen3-235b-a22b:free",
MODEL_FREE_TNGTECH_DEEPSEEK_R1T_CHIMERA_FREE = "tngtech/deepseek-r1t-chimera:free",
- MODEL_FREE_MICROSOFT_MAI_DS_R1_FREE = "microsoft/mai-ds-r1:free",
- MODEL_FREE_SHISA_AI_SHISA_V2_LLAMA3_3_70B_FREE = "shisa-ai/shisa-v2-llama3.3-70b:free",
- MODEL_FREE_ARLIAI_QWQ_32B_ARLIAI_RPR_V1_FREE = "arliai/qwq-32b-arliai-rpr-v1:free",
- MODEL_FREE_AGENTICA_ORG_DEEPCODER_14B_PREVIEW_FREE = "agentica-org/deepcoder-14b-preview:free",
- MODEL_FREE_META_LLAMA_LLAMA_4_MAVERICK_FREE = "meta-llama/llama-4-maverick:free",
- MODEL_FREE_META_LLAMA_LLAMA_4_SCOUT_FREE = "meta-llama/llama-4-scout:free",
- MODEL_FREE_QWEN_QWEN2_5_VL_32B_INSTRUCT_FREE = "qwen/qwen2.5-vl-32b-instruct:free",
- MODEL_FREE_DEEPSEEK_DEEPSEEK_CHAT_V3_0324_FREE = "deepseek/deepseek-chat-v3-0324:free",
MODEL_FREE_MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.1-24b-instruct:free",
MODEL_FREE_GOOGLE_GEMMA_3_4B_IT_FREE = "google/gemma-3-4b-it:free",
MODEL_FREE_GOOGLE_GEMMA_3_12B_IT_FREE = "google/gemma-3-12b-it:free",
MODEL_FREE_GOOGLE_GEMMA_3_27B_IT_FREE = "google/gemma-3-27b-it:free",
- MODEL_FREE_NOUSRESEARCH_DEEPHERMES_3_LLAMA_3_8B_PREVIEW_FREE = "nousresearch/deephermes-3-llama-3-8b-preview:free",
- MODEL_FREE_COGNITIVECOMPUTATIONS_DOLPHIN3_0_MISTRAL_24B_FREE = "cognitivecomputations/dolphin3.0-mistral-24b:free",
- MODEL_FREE_QWEN_QWEN2_5_VL_72B_INSTRUCT_FREE = "qwen/qwen2.5-vl-72b-instruct:free",
- MODEL_FREE_MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501_FREE = "mistralai/mistral-small-24b-instruct-2501:free",
- MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B_FREE = "deepseek/deepseek-r1-distill-llama-70b:free",
- MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_FREE = "deepseek/deepseek-r1:free",
MODEL_FREE_GOOGLE_GEMINI_2_0_FLASH_EXP_FREE = "google/gemini-2.0-flash-exp:free",
MODEL_FREE_META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE = "meta-llama/llama-3.3-70b-instruct:free",
- MODEL_FREE_QWEN_QWEN_2_5_CODER_32B_INSTRUCT_FREE = "qwen/qwen-2.5-coder-32b-instruct:free",
MODEL_FREE_META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE = "meta-llama/llama-3.2-3b-instruct:free",
- MODEL_FREE_QWEN_QWEN_2_5_72B_INSTRUCT_FREE = "qwen/qwen-2.5-72b-instruct:free",
- MODEL_FREE_MISTRALAI_MISTRAL_NEMO_FREE = "mistralai/mistral-nemo:free",
- MODEL_FREE_GOOGLE_GEMMA_2_9B_IT_FREE = "google/gemma-2-9b-it:free",
+ MODEL_FREE_QWEN_QWEN_2_5_VL_7B_INSTRUCT_FREE = "qwen/qwen-2.5-vl-7b-instruct:free",
+ MODEL_FREE_NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE = "nousresearch/hermes-3-llama-3.1-405b:free",
+ MODEL_FREE_META_LLAMA_LLAMA_3_1_405B_INSTRUCT_FREE = "meta-llama/llama-3.1-405b-instruct:free",
MODEL_FREE_MISTRALAI_MISTRAL_7B_INSTRUCT_FREE = "mistralai/mistral-7b-instruct:free"
}
\ No newline at end of file
diff --git a/packages/kbot/src/models/cache/openrouter-models.ts b/packages/kbot/src/models/cache/openrouter-models.ts
index 13f2e3ea..24d0376a 100644
--- a/packages/kbot/src/models/cache/openrouter-models.ts
+++ b/packages/kbot/src/models/cache/openrouter-models.ts
@@ -1,5 +1,70 @@
export enum E_OPENROUTER_MODEL {
- MODEL_INCLUSIONAI_LING_1T = "inclusionai/ling-1t",
+ MODEL_BYTEDANCE_SEED_SEED_1_6_FLASH = "bytedance-seed/seed-1.6-flash",
+ MODEL_BYTEDANCE_SEED_SEED_1_6 = "bytedance-seed/seed-1.6",
+ MODEL_MINIMAX_MINIMAX_M2_1 = "minimax/minimax-m2.1",
+ MODEL_Z_AI_GLM_4_7 = "z-ai/glm-4.7",
+ MODEL_GOOGLE_GEMINI_3_FLASH_PREVIEW = "google/gemini-3-flash-preview",
+ MODEL_MISTRALAI_MISTRAL_SMALL_CREATIVE = "mistralai/mistral-small-creative",
+ MODEL_ALLENAI_OLMO_3_1_32B_THINK_FREE = "allenai/olmo-3.1-32b-think:free",
+ MODEL_XIAOMI_MIMO_V2_FLASH_FREE = "xiaomi/mimo-v2-flash:free",
+ MODEL_NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE = "nvidia/nemotron-3-nano-30b-a3b:free",
+ MODEL_NVIDIA_NEMOTRON_3_NANO_30B_A3B = "nvidia/nemotron-3-nano-30b-a3b",
+ MODEL_OPENAI_GPT_5_2_CHAT = "openai/gpt-5.2-chat",
+ MODEL_OPENAI_GPT_5_2_PRO = "openai/gpt-5.2-pro",
+ MODEL_OPENAI_GPT_5_2 = "openai/gpt-5.2",
+ MODEL_MISTRALAI_DEVSTRAL_2512_FREE = "mistralai/devstral-2512:free",
+ MODEL_MISTRALAI_DEVSTRAL_2512 = "mistralai/devstral-2512",
+ MODEL_RELACE_RELACE_SEARCH = "relace/relace-search",
+ MODEL_Z_AI_GLM_4_6V = "z-ai/glm-4.6v",
+ MODEL_NEX_AGI_DEEPSEEK_V3_1_NEX_N1_FREE = "nex-agi/deepseek-v3.1-nex-n1:free",
+ MODEL_ESSENTIALAI_RNJ_1_INSTRUCT = "essentialai/rnj-1-instruct",
+ MODEL_OPENROUTER_BODYBUILDER = "openrouter/bodybuilder",
+ MODEL_OPENAI_GPT_5_1_CODEX_MAX = "openai/gpt-5.1-codex-max",
+ MODEL_AMAZON_NOVA_2_LITE_V1 = "amazon/nova-2-lite-v1",
+ MODEL_MISTRALAI_MINISTRAL_14B_2512 = "mistralai/ministral-14b-2512",
+ MODEL_MISTRALAI_MINISTRAL_8B_2512 = "mistralai/ministral-8b-2512",
+ MODEL_MISTRALAI_MINISTRAL_3B_2512 = "mistralai/ministral-3b-2512",
+ MODEL_MISTRALAI_MISTRAL_LARGE_2512 = "mistralai/mistral-large-2512",
+ MODEL_ARCEE_AI_TRINITY_MINI_FREE = "arcee-ai/trinity-mini:free",
+ MODEL_ARCEE_AI_TRINITY_MINI = "arcee-ai/trinity-mini",
+ MODEL_DEEPSEEK_DEEPSEEK_V3_2_SPECIALE = "deepseek/deepseek-v3.2-speciale",
+ MODEL_DEEPSEEK_DEEPSEEK_V3_2 = "deepseek/deepseek-v3.2",
+ MODEL_PRIME_INTELLECT_INTELLECT_3 = "prime-intellect/intellect-3",
+ MODEL_TNGTECH_TNG_R1T_CHIMERA_FREE = "tngtech/tng-r1t-chimera:free",
+ MODEL_TNGTECH_TNG_R1T_CHIMERA = "tngtech/tng-r1t-chimera",
+ MODEL_ANTHROPIC_CLAUDE_OPUS_4_5 = "anthropic/claude-opus-4.5",
+ MODEL_ALLENAI_OLMO_3_32B_THINK_FREE = "allenai/olmo-3-32b-think:free",
+ MODEL_ALLENAI_OLMO_3_7B_INSTRUCT = "allenai/olmo-3-7b-instruct",
+ MODEL_ALLENAI_OLMO_3_7B_THINK = "allenai/olmo-3-7b-think",
+ MODEL_GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW = "google/gemini-3-pro-image-preview",
+ MODEL_X_AI_GROK_4_1_FAST = "x-ai/grok-4.1-fast",
+ MODEL_GOOGLE_GEMINI_3_PRO_PREVIEW = "google/gemini-3-pro-preview",
+ MODEL_DEEPCOGITO_COGITO_V2_1_671B = "deepcogito/cogito-v2.1-671b",
+ MODEL_OPENAI_GPT_5_1 = "openai/gpt-5.1",
+ MODEL_OPENAI_GPT_5_1_CHAT = "openai/gpt-5.1-chat",
+ MODEL_OPENAI_GPT_5_1_CODEX = "openai/gpt-5.1-codex",
+ MODEL_OPENAI_GPT_5_1_CODEX_MINI = "openai/gpt-5.1-codex-mini",
+ MODEL_KWAIPILOT_KAT_CODER_PRO_FREE = "kwaipilot/kat-coder-pro:free",
+ MODEL_MOONSHOTAI_KIMI_K2_THINKING = "moonshotai/kimi-k2-thinking",
+ MODEL_AMAZON_NOVA_PREMIER_V1 = "amazon/nova-premier-v1",
+ MODEL_PERPLEXITY_SONAR_PRO_SEARCH = "perplexity/sonar-pro-search",
+ MODEL_MISTRALAI_VOXTRAL_SMALL_24B_2507 = "mistralai/voxtral-small-24b-2507",
+ MODEL_OPENAI_GPT_OSS_SAFEGUARD_20B = "openai/gpt-oss-safeguard-20b",
+ MODEL_NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE = "nvidia/nemotron-nano-12b-v2-vl:free",
+ MODEL_NVIDIA_NEMOTRON_NANO_12B_V2_VL = "nvidia/nemotron-nano-12b-v2-vl",
+ MODEL_MINIMAX_MINIMAX_M2 = "minimax/minimax-m2",
+ MODEL_QWEN_QWEN3_VL_32B_INSTRUCT = "qwen/qwen3-vl-32b-instruct",
+ MODEL_LIQUID_LFM2_8B_A1B = "liquid/lfm2-8b-a1b",
+ MODEL_LIQUID_LFM_2_2_6B = "liquid/lfm-2.2-6b",
+ MODEL_IBM_GRANITE_GRANITE_4_0_H_MICRO = "ibm-granite/granite-4.0-h-micro",
+ MODEL_DEEPCOGITO_COGITO_V2_PREVIEW_LLAMA_405B = "deepcogito/cogito-v2-preview-llama-405b",
+ MODEL_OPENAI_GPT_5_IMAGE_MINI = "openai/gpt-5-image-mini",
+ MODEL_ANTHROPIC_CLAUDE_HAIKU_4_5 = "anthropic/claude-haiku-4.5",
+ MODEL_QWEN_QWEN3_VL_8B_THINKING = "qwen/qwen3-vl-8b-thinking",
+ MODEL_QWEN_QWEN3_VL_8B_INSTRUCT = "qwen/qwen3-vl-8b-instruct",
+ MODEL_OPENAI_GPT_5_IMAGE = "openai/gpt-5-image",
+ MODEL_OPENAI_O3_DEEP_RESEARCH = "openai/o3-deep-research",
+ MODEL_OPENAI_O4_MINI_DEEP_RESEARCH = "openai/o4-mini-deep-research",
MODEL_NVIDIA_LLAMA_3_3_NEMOTRON_SUPER_49B_V1_5 = "nvidia/llama-3.3-nemotron-super-49b-v1.5",
MODEL_BAIDU_ERNIE_4_5_21B_A3B_THINKING = "baidu/ernie-4.5-21b-a3b-thinking",
MODEL_GOOGLE_GEMINI_2_5_FLASH_IMAGE = "google/gemini-2.5-flash-image",
@@ -7,6 +72,7 @@ export enum E_OPENROUTER_MODEL {
MODEL_QWEN_QWEN3_VL_30B_A3B_INSTRUCT = "qwen/qwen3-vl-30b-a3b-instruct",
MODEL_OPENAI_GPT_5_PRO = "openai/gpt-5-pro",
MODEL_Z_AI_GLM_4_6 = "z-ai/glm-4.6",
+ MODEL_Z_AI_GLM_4_6_EXACTO = "z-ai/glm-4.6:exacto",
MODEL_ANTHROPIC_CLAUDE_SONNET_4_5 = "anthropic/claude-sonnet-4.5",
MODEL_DEEPSEEK_DEEPSEEK_V3_2_EXP = "deepseek/deepseek-v3.2-exp",
MODEL_THEDRUMMER_CYDONIA_24B_V4_1 = "thedrummer/cydonia-24b-v4.1",
@@ -18,31 +84,30 @@ export enum E_OPENROUTER_MODEL {
MODEL_QWEN_QWEN3_MAX = "qwen/qwen3-max",
MODEL_QWEN_QWEN3_CODER_PLUS = "qwen/qwen3-coder-plus",
MODEL_OPENAI_GPT_5_CODEX = "openai/gpt-5-codex",
+ MODEL_DEEPSEEK_DEEPSEEK_V3_1_TERMINUS_EXACTO = "deepseek/deepseek-v3.1-terminus:exacto",
MODEL_DEEPSEEK_DEEPSEEK_V3_1_TERMINUS = "deepseek/deepseek-v3.1-terminus",
MODEL_X_AI_GROK_4_FAST = "x-ai/grok-4-fast",
MODEL_ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B_FREE = "alibaba/tongyi-deepresearch-30b-a3b:free",
MODEL_ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B = "alibaba/tongyi-deepresearch-30b-a3b",
MODEL_QWEN_QWEN3_CODER_FLASH = "qwen/qwen3-coder-flash",
- MODEL_ARCEE_AI_AFM_4_5B = "arcee-ai/afm-4.5b",
MODEL_OPENGVLAB_INTERNVL3_78B = "opengvlab/internvl3-78b",
MODEL_QWEN_QWEN3_NEXT_80B_A3B_THINKING = "qwen/qwen3-next-80b-a3b-thinking",
MODEL_QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT = "qwen/qwen3-next-80b-a3b-instruct",
- MODEL_MEITUAN_LONGCAT_FLASH_CHAT_FREE = "meituan/longcat-flash-chat:free",
MODEL_MEITUAN_LONGCAT_FLASH_CHAT = "meituan/longcat-flash-chat",
MODEL_QWEN_QWEN_PLUS_2025_07_28 = "qwen/qwen-plus-2025-07-28",
MODEL_QWEN_QWEN_PLUS_2025_07_28_THINKING = "qwen/qwen-plus-2025-07-28:thinking",
MODEL_NVIDIA_NEMOTRON_NANO_9B_V2_FREE = "nvidia/nemotron-nano-9b-v2:free",
MODEL_NVIDIA_NEMOTRON_NANO_9B_V2 = "nvidia/nemotron-nano-9b-v2",
MODEL_MOONSHOTAI_KIMI_K2_0905 = "moonshotai/kimi-k2-0905",
+ MODEL_MOONSHOTAI_KIMI_K2_0905_EXACTO = "moonshotai/kimi-k2-0905:exacto",
+ MODEL_DEEPCOGITO_COGITO_V2_PREVIEW_LLAMA_70B = "deepcogito/cogito-v2-preview-llama-70b",
MODEL_DEEPCOGITO_COGITO_V2_PREVIEW_LLAMA_109B_MOE = "deepcogito/cogito-v2-preview-llama-109b-moe",
- MODEL_DEEPCOGITO_COGITO_V2_PREVIEW_DEEPSEEK_671B = "deepcogito/cogito-v2-preview-deepseek-671b",
MODEL_STEPFUN_AI_STEP3 = "stepfun-ai/step3",
MODEL_QWEN_QWEN3_30B_A3B_THINKING_2507 = "qwen/qwen3-30b-a3b-thinking-2507",
MODEL_X_AI_GROK_CODE_FAST_1 = "x-ai/grok-code-fast-1",
MODEL_NOUSRESEARCH_HERMES_4_70B = "nousresearch/hermes-4-70b",
MODEL_NOUSRESEARCH_HERMES_4_405B = "nousresearch/hermes-4-405b",
MODEL_GOOGLE_GEMINI_2_5_FLASH_IMAGE_PREVIEW = "google/gemini-2.5-flash-image-preview",
- MODEL_DEEPSEEK_DEEPSEEK_CHAT_V3_1_FREE = "deepseek/deepseek-chat-v3.1:free",
MODEL_DEEPSEEK_DEEPSEEK_CHAT_V3_1 = "deepseek/deepseek-chat-v3.1",
MODEL_OPENAI_GPT_4O_AUDIO_PREVIEW = "openai/gpt-4o-audio-preview",
MODEL_MISTRALAI_MISTRAL_MEDIUM_3_1 = "mistralai/mistral-medium-3.1",
@@ -55,7 +120,9 @@ export enum E_OPENROUTER_MODEL {
MODEL_OPENAI_GPT_5 = "openai/gpt-5",
MODEL_OPENAI_GPT_5_MINI = "openai/gpt-5-mini",
MODEL_OPENAI_GPT_5_NANO = "openai/gpt-5-nano",
+ MODEL_OPENAI_GPT_OSS_120B_FREE = "openai/gpt-oss-120b:free",
MODEL_OPENAI_GPT_OSS_120B = "openai/gpt-oss-120b",
+ MODEL_OPENAI_GPT_OSS_120B_EXACTO = "openai/gpt-oss-120b:exacto",
MODEL_OPENAI_GPT_OSS_20B_FREE = "openai/gpt-oss-20b:free",
MODEL_OPENAI_GPT_OSS_20B = "openai/gpt-oss-20b",
MODEL_ANTHROPIC_CLAUDE_OPUS_4_1 = "anthropic/claude-opus-4.1",
@@ -69,6 +136,7 @@ export enum E_OPENROUTER_MODEL {
MODEL_Z_AI_GLM_4_32B = "z-ai/glm-4-32b",
MODEL_QWEN_QWEN3_CODER_FREE = "qwen/qwen3-coder:free",
MODEL_QWEN_QWEN3_CODER = "qwen/qwen3-coder",
+ MODEL_QWEN_QWEN3_CODER_EXACTO = "qwen/qwen3-coder:exacto",
MODEL_BYTEDANCE_UI_TARS_1_5_7B = "bytedance/ui-tars-1.5-7b",
MODEL_GOOGLE_GEMINI_2_5_FLASH_LITE = "google/gemini-2.5-flash-lite",
MODEL_QWEN_QWEN3_235B_A22B_2507 = "qwen/qwen3-235b-a22b-2507",
@@ -81,7 +149,6 @@ export enum E_OPENROUTER_MODEL {
MODEL_COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION_FREE = "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
MODEL_X_AI_GROK_4 = "x-ai/grok-4",
MODEL_GOOGLE_GEMMA_3N_E2B_IT_FREE = "google/gemma-3n-e2b-it:free",
- MODEL_TENCENT_HUNYUAN_A13B_INSTRUCT_FREE = "tencent/hunyuan-a13b-instruct:free",
MODEL_TENCENT_HUNYUAN_A13B_INSTRUCT = "tencent/hunyuan-a13b-instruct",
MODEL_TNGTECH_DEEPSEEK_R1T2_CHIMERA_FREE = "tngtech/deepseek-r1t2-chimera:free",
MODEL_TNGTECH_DEEPSEEK_R1T2_CHIMERA = "tngtech/deepseek-r1t2-chimera",
@@ -89,35 +156,25 @@ export enum E_OPENROUTER_MODEL {
MODEL_MORPH_MORPH_V3_FAST = "morph/morph-v3-fast",
MODEL_BAIDU_ERNIE_4_5_VL_424B_A47B = "baidu/ernie-4.5-vl-424b-a47b",
MODEL_BAIDU_ERNIE_4_5_300B_A47B = "baidu/ernie-4.5-300b-a47b",
- MODEL_THEDRUMMER_ANUBIS_70B_V1_1 = "thedrummer/anubis-70b-v1.1",
MODEL_INCEPTION_MERCURY = "inception/mercury",
- MODEL_MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.2-24b-instruct:free",
MODEL_MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT = "mistralai/mistral-small-3.2-24b-instruct",
MODEL_MINIMAX_MINIMAX_M1 = "minimax/minimax-m1",
- MODEL_GOOGLE_GEMINI_2_5_FLASH_LITE_PREVIEW_06_17 = "google/gemini-2.5-flash-lite-preview-06-17",
MODEL_GOOGLE_GEMINI_2_5_FLASH = "google/gemini-2.5-flash",
MODEL_GOOGLE_GEMINI_2_5_PRO = "google/gemini-2.5-pro",
- MODEL_MOONSHOTAI_KIMI_DEV_72B_FREE = "moonshotai/kimi-dev-72b:free",
MODEL_MOONSHOTAI_KIMI_DEV_72B = "moonshotai/kimi-dev-72b",
MODEL_OPENAI_O3_PRO = "openai/o3-pro",
MODEL_X_AI_GROK_3_MINI = "x-ai/grok-3-mini",
MODEL_X_AI_GROK_3 = "x-ai/grok-3",
- MODEL_MISTRALAI_MAGISTRAL_SMALL_2506 = "mistralai/magistral-small-2506",
- MODEL_MISTRALAI_MAGISTRAL_MEDIUM_2506 = "mistralai/magistral-medium-2506",
- MODEL_MISTRALAI_MAGISTRAL_MEDIUM_2506_THINKING = "mistralai/magistral-medium-2506:thinking",
MODEL_GOOGLE_GEMINI_2_5_PRO_PREVIEW = "google/gemini-2.5-pro-preview",
- MODEL_DEEPSEEK_DEEPSEEK_R1_0528_QWEN3_8B_FREE = "deepseek/deepseek-r1-0528-qwen3-8b:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528_QWEN3_8B = "deepseek/deepseek-r1-0528-qwen3-8b",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528_FREE = "deepseek/deepseek-r1-0528:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528 = "deepseek/deepseek-r1-0528",
MODEL_ANTHROPIC_CLAUDE_OPUS_4 = "anthropic/claude-opus-4",
MODEL_ANTHROPIC_CLAUDE_SONNET_4 = "anthropic/claude-sonnet-4",
- MODEL_MISTRALAI_DEVSTRAL_SMALL_2505_FREE = "mistralai/devstral-small-2505:free",
MODEL_MISTRALAI_DEVSTRAL_SMALL_2505 = "mistralai/devstral-small-2505",
MODEL_GOOGLE_GEMMA_3N_E4B_IT_FREE = "google/gemma-3n-e4b-it:free",
MODEL_GOOGLE_GEMMA_3N_E4B_IT = "google/gemma-3n-e4b-it",
MODEL_OPENAI_CODEX_MINI = "openai/codex-mini",
- MODEL_META_LLAMA_LLAMA_3_3_8B_INSTRUCT_FREE = "meta-llama/llama-3.3-8b-instruct:free",
MODEL_NOUSRESEARCH_DEEPHERMES_3_MISTRAL_24B_PREVIEW = "nousresearch/deephermes-3-mistral-24b-preview",
MODEL_MISTRALAI_MISTRAL_MEDIUM_3 = "mistralai/mistral-medium-3",
MODEL_GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06 = "google/gemini-2.5-pro-preview-05-06",
@@ -130,46 +187,29 @@ export enum E_OPENROUTER_MODEL {
MODEL_QWEN_QWEN3_4B_FREE = "qwen/qwen3-4b:free",
MODEL_DEEPSEEK_DEEPSEEK_PROVER_V2 = "deepseek/deepseek-prover-v2",
MODEL_META_LLAMA_LLAMA_GUARD_4_12B = "meta-llama/llama-guard-4-12b",
- MODEL_QWEN_QWEN3_30B_A3B_FREE = "qwen/qwen3-30b-a3b:free",
MODEL_QWEN_QWEN3_30B_A3B = "qwen/qwen3-30b-a3b",
- MODEL_QWEN_QWEN3_8B_FREE = "qwen/qwen3-8b:free",
MODEL_QWEN_QWEN3_8B = "qwen/qwen3-8b",
- MODEL_QWEN_QWEN3_14B_FREE = "qwen/qwen3-14b:free",
MODEL_QWEN_QWEN3_14B = "qwen/qwen3-14b",
MODEL_QWEN_QWEN3_32B = "qwen/qwen3-32b",
- MODEL_QWEN_QWEN3_235B_A22B_FREE = "qwen/qwen3-235b-a22b:free",
MODEL_QWEN_QWEN3_235B_A22B = "qwen/qwen3-235b-a22b",
MODEL_TNGTECH_DEEPSEEK_R1T_CHIMERA_FREE = "tngtech/deepseek-r1t-chimera:free",
MODEL_TNGTECH_DEEPSEEK_R1T_CHIMERA = "tngtech/deepseek-r1t-chimera",
- MODEL_MICROSOFT_MAI_DS_R1_FREE = "microsoft/mai-ds-r1:free",
- MODEL_MICROSOFT_MAI_DS_R1 = "microsoft/mai-ds-r1",
- MODEL_THUDM_GLM_Z1_32B = "thudm/glm-z1-32b",
MODEL_OPENAI_O4_MINI_HIGH = "openai/o4-mini-high",
MODEL_OPENAI_O3 = "openai/o3",
MODEL_OPENAI_O4_MINI = "openai/o4-mini",
- MODEL_SHISA_AI_SHISA_V2_LLAMA3_3_70B_FREE = "shisa-ai/shisa-v2-llama3.3-70b:free",
- MODEL_SHISA_AI_SHISA_V2_LLAMA3_3_70B = "shisa-ai/shisa-v2-llama3.3-70b",
MODEL_QWEN_QWEN2_5_CODER_7B_INSTRUCT = "qwen/qwen2.5-coder-7b-instruct",
MODEL_OPENAI_GPT_4_1 = "openai/gpt-4.1",
MODEL_OPENAI_GPT_4_1_MINI = "openai/gpt-4.1-mini",
MODEL_OPENAI_GPT_4_1_NANO = "openai/gpt-4.1-nano",
MODEL_ELEUTHERAI_LLEMMA_7B = "eleutherai/llemma_7b",
MODEL_ALFREDPROS_CODELLAMA_7B_INSTRUCT_SOLIDITY = "alfredpros/codellama-7b-instruct-solidity",
- MODEL_ARLIAI_QWQ_32B_ARLIAI_RPR_V1_FREE = "arliai/qwq-32b-arliai-rpr-v1:free",
MODEL_ARLIAI_QWQ_32B_ARLIAI_RPR_V1 = "arliai/qwq-32b-arliai-rpr-v1",
- MODEL_AGENTICA_ORG_DEEPCODER_14B_PREVIEW_FREE = "agentica-org/deepcoder-14b-preview:free",
- MODEL_AGENTICA_ORG_DEEPCODER_14B_PREVIEW = "agentica-org/deepcoder-14b-preview",
MODEL_X_AI_GROK_3_MINI_BETA = "x-ai/grok-3-mini-beta",
MODEL_X_AI_GROK_3_BETA = "x-ai/grok-3-beta",
MODEL_NVIDIA_LLAMA_3_1_NEMOTRON_ULTRA_253B_V1 = "nvidia/llama-3.1-nemotron-ultra-253b-v1",
- MODEL_META_LLAMA_LLAMA_4_MAVERICK_FREE = "meta-llama/llama-4-maverick:free",
MODEL_META_LLAMA_LLAMA_4_MAVERICK = "meta-llama/llama-4-maverick",
- MODEL_META_LLAMA_LLAMA_4_SCOUT_FREE = "meta-llama/llama-4-scout:free",
MODEL_META_LLAMA_LLAMA_4_SCOUT = "meta-llama/llama-4-scout",
- MODEL_ALLENAI_MOLMO_7B_D = "allenai/molmo-7b-d",
- MODEL_QWEN_QWEN2_5_VL_32B_INSTRUCT_FREE = "qwen/qwen2.5-vl-32b-instruct:free",
MODEL_QWEN_QWEN2_5_VL_32B_INSTRUCT = "qwen/qwen2.5-vl-32b-instruct",
- MODEL_DEEPSEEK_DEEPSEEK_CHAT_V3_0324_FREE = "deepseek/deepseek-chat-v3-0324:free",
MODEL_DEEPSEEK_DEEPSEEK_CHAT_V3_0324 = "deepseek/deepseek-chat-v3-0324",
MODEL_OPENAI_O1_PRO = "openai/o1-pro",
MODEL_MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.1-24b-instruct:free",
@@ -190,15 +230,10 @@ export enum E_OPENROUTER_MODEL {
MODEL_PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro",
MODEL_PERPLEXITY_SONAR_DEEP_RESEARCH = "perplexity/sonar-deep-research",
MODEL_QWEN_QWQ_32B = "qwen/qwq-32b",
- MODEL_NOUSRESEARCH_DEEPHERMES_3_LLAMA_3_8B_PREVIEW_FREE = "nousresearch/deephermes-3-llama-3-8b-preview:free",
- MODEL_NOUSRESEARCH_DEEPHERMES_3_LLAMA_3_8B_PREVIEW = "nousresearch/deephermes-3-llama-3-8b-preview",
MODEL_GOOGLE_GEMINI_2_0_FLASH_LITE_001 = "google/gemini-2.0-flash-lite-001",
- MODEL_ANTHROPIC_CLAUDE_3_7_SONNET = "anthropic/claude-3.7-sonnet",
MODEL_ANTHROPIC_CLAUDE_3_7_SONNET_THINKING = "anthropic/claude-3.7-sonnet:thinking",
- MODEL_PERPLEXITY_R1_1776 = "perplexity/r1-1776",
+ MODEL_ANTHROPIC_CLAUDE_3_7_SONNET = "anthropic/claude-3.7-sonnet",
MODEL_MISTRALAI_MISTRAL_SABA = "mistralai/mistral-saba",
- MODEL_COGNITIVECOMPUTATIONS_DOLPHIN3_0_MISTRAL_24B_FREE = "cognitivecomputations/dolphin3.0-mistral-24b:free",
- MODEL_COGNITIVECOMPUTATIONS_DOLPHIN3_0_MISTRAL_24B = "cognitivecomputations/dolphin3.0-mistral-24b",
MODEL_META_LLAMA_LLAMA_GUARD_3_8B = "meta-llama/llama-guard-3-8b",
MODEL_OPENAI_O3_MINI_HIGH = "openai/o3-mini-high",
MODEL_GOOGLE_GEMINI_2_0_FLASH_001 = "google/gemini-2.0-flash-001",
@@ -208,25 +243,18 @@ export enum E_OPENROUTER_MODEL {
MODEL_AION_LABS_AION_RP_LLAMA_3_1_8B = "aion-labs/aion-rp-llama-3.1-8b",
MODEL_QWEN_QWEN_VL_MAX = "qwen/qwen-vl-max",
MODEL_QWEN_QWEN_TURBO = "qwen/qwen-turbo",
- MODEL_QWEN_QWEN2_5_VL_72B_INSTRUCT_FREE = "qwen/qwen2.5-vl-72b-instruct:free",
MODEL_QWEN_QWEN2_5_VL_72B_INSTRUCT = "qwen/qwen2.5-vl-72b-instruct",
MODEL_QWEN_QWEN_PLUS = "qwen/qwen-plus",
MODEL_QWEN_QWEN_MAX = "qwen/qwen-max",
MODEL_OPENAI_O3_MINI = "openai/o3-mini",
- MODEL_MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501_FREE = "mistralai/mistral-small-24b-instruct-2501:free",
MODEL_MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501 = "mistralai/mistral-small-24b-instruct-2501",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_32B = "deepseek/deepseek-r1-distill-qwen-32b",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_14B = "deepseek/deepseek-r1-distill-qwen-14b",
MODEL_PERPLEXITY_SONAR_REASONING = "perplexity/sonar-reasoning",
MODEL_PERPLEXITY_SONAR = "perplexity/sonar",
- MODEL_LIQUID_LFM_7B = "liquid/lfm-7b",
- MODEL_LIQUID_LFM_3B = "liquid/lfm-3b",
- MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B_FREE = "deepseek/deepseek-r1-distill-llama-70b:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B = "deepseek/deepseek-r1-distill-llama-70b",
- MODEL_DEEPSEEK_DEEPSEEK_R1_FREE = "deepseek/deepseek-r1:free",
MODEL_DEEPSEEK_DEEPSEEK_R1 = "deepseek/deepseek-r1",
MODEL_MINIMAX_MINIMAX_01 = "minimax/minimax-01",
- MODEL_MISTRALAI_CODESTRAL_2501 = "mistralai/codestral-2501",
MODEL_MICROSOFT_PHI_4 = "microsoft/phi-4",
MODEL_SAO10K_L3_1_70B_HANAMI_X1 = "sao10k/l3.1-70b-hanami-x1",
MODEL_DEEPSEEK_DEEPSEEK_CHAT = "deepseek/deepseek-chat",
@@ -243,91 +271,85 @@ export enum E_OPENROUTER_MODEL {
MODEL_MISTRALAI_MISTRAL_LARGE_2411 = "mistralai/mistral-large-2411",
MODEL_MISTRALAI_MISTRAL_LARGE_2407 = "mistralai/mistral-large-2407",
MODEL_MISTRALAI_PIXTRAL_LARGE_2411 = "mistralai/pixtral-large-2411",
- MODEL_QWEN_QWEN_2_5_CODER_32B_INSTRUCT_FREE = "qwen/qwen-2.5-coder-32b-instruct:free",
MODEL_QWEN_QWEN_2_5_CODER_32B_INSTRUCT = "qwen/qwen-2.5-coder-32b-instruct",
MODEL_RAIFLE_SORCERERLM_8X22B = "raifle/sorcererlm-8x22b",
MODEL_THEDRUMMER_UNSLOPNEMO_12B = "thedrummer/unslopnemo-12b",
- MODEL_ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic/claude-3.5-haiku",
MODEL_ANTHROPIC_CLAUDE_3_5_HAIKU_20241022 = "anthropic/claude-3.5-haiku-20241022",
+ MODEL_ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic/claude-3.5-haiku",
MODEL_ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic/claude-3.5-sonnet",
MODEL_ANTHRACITE_ORG_MAGNUM_V4_72B = "anthracite-org/magnum-v4-72b",
MODEL_MISTRALAI_MINISTRAL_8B = "mistralai/ministral-8b",
MODEL_MISTRALAI_MINISTRAL_3B = "mistralai/ministral-3b",
MODEL_QWEN_QWEN_2_5_7B_INSTRUCT = "qwen/qwen-2.5-7b-instruct",
MODEL_NVIDIA_LLAMA_3_1_NEMOTRON_70B_INSTRUCT = "nvidia/llama-3.1-nemotron-70b-instruct",
- MODEL_INFLECTION_INFLECTION_3_PRODUCTIVITY = "inflection/inflection-3-productivity",
MODEL_INFLECTION_INFLECTION_3_PI = "inflection/inflection-3-pi",
+ MODEL_INFLECTION_INFLECTION_3_PRODUCTIVITY = "inflection/inflection-3-productivity",
MODEL_THEDRUMMER_ROCINANTE_12B = "thedrummer/rocinante-12b",
- MODEL_ANTHRACITE_ORG_MAGNUM_V2_72B = "anthracite-org/magnum-v2-72b",
MODEL_META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE = "meta-llama/llama-3.2-3b-instruct:free",
MODEL_META_LLAMA_LLAMA_3_2_3B_INSTRUCT = "meta-llama/llama-3.2-3b-instruct",
MODEL_META_LLAMA_LLAMA_3_2_1B_INSTRUCT = "meta-llama/llama-3.2-1b-instruct",
- MODEL_META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT = "meta-llama/llama-3.2-11b-vision-instruct",
MODEL_META_LLAMA_LLAMA_3_2_90B_VISION_INSTRUCT = "meta-llama/llama-3.2-90b-vision-instruct",
- MODEL_QWEN_QWEN_2_5_72B_INSTRUCT_FREE = "qwen/qwen-2.5-72b-instruct:free",
+ MODEL_META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT = "meta-llama/llama-3.2-11b-vision-instruct",
MODEL_QWEN_QWEN_2_5_72B_INSTRUCT = "qwen/qwen-2.5-72b-instruct",
MODEL_NEVERSLEEP_LLAMA_3_1_LUMIMAID_8B = "neversleep/llama-3.1-lumimaid-8b",
- MODEL_OPENAI_O1_MINI = "openai/o1-mini",
- MODEL_OPENAI_O1_MINI_2024_09_12 = "openai/o1-mini-2024-09-12",
MODEL_MISTRALAI_PIXTRAL_12B = "mistralai/pixtral-12b",
MODEL_COHERE_COMMAND_R_08_2024 = "cohere/command-r-08-2024",
MODEL_COHERE_COMMAND_R_PLUS_08_2024 = "cohere/command-r-plus-08-2024",
+ MODEL_QWEN_QWEN_2_5_VL_7B_INSTRUCT_FREE = "qwen/qwen-2.5-vl-7b-instruct:free",
MODEL_QWEN_QWEN_2_5_VL_7B_INSTRUCT = "qwen/qwen-2.5-vl-7b-instruct",
MODEL_SAO10K_L3_1_EURYALE_70B = "sao10k/l3.1-euryale-70b",
MODEL_MICROSOFT_PHI_3_5_MINI_128K_INSTRUCT = "microsoft/phi-3.5-mini-128k-instruct",
MODEL_NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B = "nousresearch/hermes-3-llama-3.1-70b",
+ MODEL_NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE = "nousresearch/hermes-3-llama-3.1-405b:free",
MODEL_NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B = "nousresearch/hermes-3-llama-3.1-405b",
MODEL_OPENAI_CHATGPT_4O_LATEST = "openai/chatgpt-4o-latest",
MODEL_SAO10K_L3_LUNARIS_8B = "sao10k/l3-lunaris-8b",
MODEL_OPENAI_GPT_4O_2024_08_06 = "openai/gpt-4o-2024-08-06",
MODEL_META_LLAMA_LLAMA_3_1_405B = "meta-llama/llama-3.1-405b",
- MODEL_META_LLAMA_LLAMA_3_1_405B_INSTRUCT = "meta-llama/llama-3.1-405b-instruct",
- MODEL_META_LLAMA_LLAMA_3_1_8B_INSTRUCT = "meta-llama/llama-3.1-8b-instruct",
MODEL_META_LLAMA_LLAMA_3_1_70B_INSTRUCT = "meta-llama/llama-3.1-70b-instruct",
- MODEL_MISTRALAI_MISTRAL_NEMO_FREE = "mistralai/mistral-nemo:free",
+ MODEL_META_LLAMA_LLAMA_3_1_8B_INSTRUCT = "meta-llama/llama-3.1-8b-instruct",
+ MODEL_META_LLAMA_LLAMA_3_1_405B_INSTRUCT_FREE = "meta-llama/llama-3.1-405b-instruct:free",
+ MODEL_META_LLAMA_LLAMA_3_1_405B_INSTRUCT = "meta-llama/llama-3.1-405b-instruct",
MODEL_MISTRALAI_MISTRAL_NEMO = "mistralai/mistral-nemo",
MODEL_OPENAI_GPT_4O_MINI_2024_07_18 = "openai/gpt-4o-mini-2024-07-18",
MODEL_OPENAI_GPT_4O_MINI = "openai/gpt-4o-mini",
MODEL_GOOGLE_GEMMA_2_27B_IT = "google/gemma-2-27b-it",
- MODEL_GOOGLE_GEMMA_2_9B_IT_FREE = "google/gemma-2-9b-it:free",
MODEL_GOOGLE_GEMMA_2_9B_IT = "google/gemma-2-9b-it",
- MODEL_ANTHROPIC_CLAUDE_3_5_SONNET_20240620 = "anthropic/claude-3.5-sonnet-20240620",
MODEL_SAO10K_L3_EURYALE_70B = "sao10k/l3-euryale-70b",
- MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_3 = "mistralai/mistral-7b-instruct-v0.3",
- MODEL_NOUSRESEARCH_HERMES_2_PRO_LLAMA_3_8B = "nousresearch/hermes-2-pro-llama-3-8b",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_FREE = "mistralai/mistral-7b-instruct:free",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT = "mistralai/mistral-7b-instruct",
+ MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_3 = "mistralai/mistral-7b-instruct-v0.3",
+ MODEL_NOUSRESEARCH_HERMES_2_PRO_LLAMA_3_8B = "nousresearch/hermes-2-pro-llama-3-8b",
MODEL_MICROSOFT_PHI_3_MINI_128K_INSTRUCT = "microsoft/phi-3-mini-128k-instruct",
MODEL_MICROSOFT_PHI_3_MEDIUM_128K_INSTRUCT = "microsoft/phi-3-medium-128k-instruct",
MODEL_OPENAI_GPT_4O = "openai/gpt-4o",
MODEL_OPENAI_GPT_4O_EXTENDED = "openai/gpt-4o:extended",
MODEL_OPENAI_GPT_4O_2024_05_13 = "openai/gpt-4o-2024-05-13",
MODEL_META_LLAMA_LLAMA_GUARD_2_8B = "meta-llama/llama-guard-2-8b",
- MODEL_META_LLAMA_LLAMA_3_8B_INSTRUCT = "meta-llama/llama-3-8b-instruct",
MODEL_META_LLAMA_LLAMA_3_70B_INSTRUCT = "meta-llama/llama-3-70b-instruct",
+ MODEL_META_LLAMA_LLAMA_3_8B_INSTRUCT = "meta-llama/llama-3-8b-instruct",
MODEL_MISTRALAI_MIXTRAL_8X22B_INSTRUCT = "mistralai/mixtral-8x22b-instruct",
MODEL_MICROSOFT_WIZARDLM_2_8X22B = "microsoft/wizardlm-2-8x22b",
MODEL_OPENAI_GPT_4_TURBO = "openai/gpt-4-turbo",
MODEL_ANTHROPIC_CLAUDE_3_HAIKU = "anthropic/claude-3-haiku",
MODEL_ANTHROPIC_CLAUDE_3_OPUS = "anthropic/claude-3-opus",
MODEL_MISTRALAI_MISTRAL_LARGE = "mistralai/mistral-large",
- MODEL_OPENAI_GPT_3_5_TURBO_0613 = "openai/gpt-3.5-turbo-0613",
MODEL_OPENAI_GPT_4_TURBO_PREVIEW = "openai/gpt-4-turbo-preview",
+ MODEL_OPENAI_GPT_3_5_TURBO_0613 = "openai/gpt-3.5-turbo-0613",
MODEL_MISTRALAI_MISTRAL_TINY = "mistralai/mistral-tiny",
- MODEL_MISTRALAI_MISTRAL_SMALL = "mistralai/mistral-small",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_2 = "mistralai/mistral-7b-instruct-v0.2",
MODEL_MISTRALAI_MIXTRAL_8X7B_INSTRUCT = "mistralai/mixtral-8x7b-instruct",
MODEL_NEVERSLEEP_NOROMAID_20B = "neversleep/noromaid-20b",
MODEL_ALPINDALE_GOLIATH_120B = "alpindale/goliath-120b",
MODEL_OPENROUTER_AUTO = "openrouter/auto",
MODEL_OPENAI_GPT_4_1106_PREVIEW = "openai/gpt-4-1106-preview",
- MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_1 = "mistralai/mistral-7b-instruct-v0.1",
MODEL_OPENAI_GPT_3_5_TURBO_INSTRUCT = "openai/gpt-3.5-turbo-instruct",
+ MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_1 = "mistralai/mistral-7b-instruct-v0.1",
MODEL_OPENAI_GPT_3_5_TURBO_16K = "openai/gpt-3.5-turbo-16k",
MODEL_MANCER_WEAVER = "mancer/weaver",
MODEL_UNDI95_REMM_SLERP_L2_13B = "undi95/remm-slerp-l2-13b",
MODEL_GRYPHE_MYTHOMAX_L2_13B = "gryphe/mythomax-l2-13b",
- MODEL_OPENAI_GPT_3_5_TURBO = "openai/gpt-3.5-turbo",
MODEL_OPENAI_GPT_4_0314 = "openai/gpt-4-0314",
- MODEL_OPENAI_GPT_4 = "openai/gpt-4"
+ MODEL_OPENAI_GPT_4 = "openai/gpt-4",
+ MODEL_OPENAI_GPT_3_5_TURBO = "openai/gpt-3.5-turbo"
}
\ No newline at end of file
diff --git a/packages/kbot/src/zod_types.ts b/packages/kbot/src/zod_types.ts
index 9223e34b..8258f286 100644
--- a/packages/kbot/src/zod_types.ts
+++ b/packages/kbot/src/zod_types.ts
@@ -55,6 +55,7 @@ export interface IKBotOptions {
anthropic/claude-opus-4 | paid
anthropic/claude-opus-4.1 | paid
anthropic/claude-sonnet-4 | paid
+ anthropic/claude-sonnet-4.5 | paid
arcee-ai/afm-4.5b | paid
arcee-ai/coder-large | paid
arcee-ai/maestro-reasoning | paid
@@ -64,19 +65,14 @@ export interface IKBotOptions {
arliai/qwq-32b-arliai-rpr-v1:free | free
openrouter/auto | paid
baidu/ernie-4.5-21b-a3b | paid
+ baidu/ernie-4.5-21b-a3b-thinking | paid
baidu/ernie-4.5-300b-a47b | paid
baidu/ernie-4.5-vl-28b-a3b | paid
baidu/ernie-4.5-vl-424b-a47b | paid
- bytedance/seed-oss-36b-instruct | paid
bytedance/ui-tars-1.5-7b | paid
deepcogito/cogito-v2-preview-llama-109b-moe | paid
- cohere/command | paid
cohere/command-a | paid
- cohere/command-r | paid
- cohere/command-r-03-2024 | paid
cohere/command-r-08-2024 | paid
- cohere/command-r-plus | paid
- cohere/command-r-plus-04-2024 | paid
cohere/command-r-plus-08-2024 | paid
cohere/command-r7b-12-2024 | paid
deepcogito/cogito-v2-preview-deepseek-671b | paid
@@ -88,32 +84,30 @@ export interface IKBotOptions {
deepseek/deepseek-chat-v3-0324:free | free
deepseek/deepseek-chat-v3.1 | paid
deepseek/deepseek-chat-v3.1:free | free
- deepseek/deepseek-v3.1-base | paid
+ deepseek/deepseek-v3.1-terminus | paid
+ deepseek/deepseek-v3.2-exp | paid
deepseek/deepseek-r1 | paid
deepseek/deepseek-r1:free | free
deepseek/deepseek-r1-0528 | paid
deepseek/deepseek-r1-0528:free | free
deepseek/deepseek-r1-distill-llama-70b | paid
deepseek/deepseek-r1-distill-llama-70b:free | free
- deepseek/deepseek-r1-distill-llama-8b | paid
deepseek/deepseek-r1-distill-qwen-14b | paid
deepseek/deepseek-r1-distill-qwen-32b | paid
cognitivecomputations/dolphin3.0-mistral-24b | paid
cognitivecomputations/dolphin3.0-mistral-24b:free | free
- cognitivecomputations/dolphin3.0-r1-mistral-24b | paid
- cognitivecomputations/dolphin3.0-r1-mistral-24b:free | free
eleutherai/llemma_7b | paid
alpindale/goliath-120b | paid
- google/gemini-flash-1.5 | paid
- google/gemini-flash-1.5-8b | paid
- google/gemini-pro-1.5 | paid
google/gemini-2.0-flash-001 | paid
google/gemini-2.0-flash-exp:free | free
google/gemini-2.0-flash-lite-001 | paid
google/gemini-2.5-flash | paid
+ google/gemini-2.5-flash-image | paid
google/gemini-2.5-flash-image-preview | paid
google/gemini-2.5-flash-lite | paid
google/gemini-2.5-flash-lite-preview-06-17 | paid
+ google/gemini-2.5-flash-lite-preview-09-2025 | paid
+ google/gemini-2.5-flash-preview-09-2025 | paid
google/gemini-2.5-pro | paid
google/gemini-2.5-pro-preview-05-06 | paid
google/gemini-2.5-pro-preview | paid
@@ -131,6 +125,7 @@ export interface IKBotOptions {
google/gemma-3n-e4b-it:free | free
inception/mercury | paid
inception/mercury-coder | paid
+ inclusionai/ling-1t | paid
inflection/inflection-3-pi | paid
inflection/inflection-3-productivity | paid
liquid/lfm-3b | paid
@@ -140,11 +135,11 @@ export interface IKBotOptions {
anthracite-org/magnum-v4-72b | paid
mancer/weaver | paid
meituan/longcat-flash-chat | paid
+ meituan/longcat-flash-chat:free | free
meta-llama/llama-3-70b-instruct | paid
meta-llama/llama-3-8b-instruct | paid
meta-llama/llama-3.1-405b | paid
meta-llama/llama-3.1-405b-instruct | paid
- meta-llama/llama-3.1-405b-instruct:free | free
meta-llama/llama-3.1-70b-instruct | paid
meta-llama/llama-3.1-8b-instruct | paid
meta-llama/llama-3.2-11b-vision-instruct | paid
@@ -190,6 +185,7 @@ export interface IKBotOptions {
mistralai/mistral-7b-instruct | paid
mistralai/mistral-7b-instruct:free | free
mistralai/mistral-7b-instruct-v0.1 | paid
+ mistralai/mistral-7b-instruct-v0.2 | paid
mistralai/mistral-7b-instruct-v0.3 | paid
mistralai/mistral-medium-3 | paid
mistralai/mistral-medium-3.1 | paid
@@ -211,14 +207,12 @@ export interface IKBotOptions {
moonshotai/kimi-k2 | paid
moonshotai/kimi-k2:free | free
moonshotai/kimi-k2-0905 | paid
- moonshotai/kimi-vl-a3b-thinking | paid
- moonshotai/kimi-vl-a3b-thinking:free | free
morph/morph-v3-fast | paid
morph/morph-v3-large | paid
gryphe/mythomax-l2-13b | paid
- neversleep/llama-3-lumimaid-70b | paid
neversleep/llama-3.1-lumimaid-8b | paid
neversleep/noromaid-20b | paid
+ nousresearch/deephermes-3-llama-3-8b-preview | paid
nousresearch/deephermes-3-llama-3-8b-preview:free | free
nousresearch/deephermes-3-mistral-24b-preview | paid
nousresearch/hermes-3-llama-3.1-405b | paid
@@ -228,6 +222,7 @@ export interface IKBotOptions {
nousresearch/hermes-2-pro-llama-3-8b | paid
nvidia/llama-3.1-nemotron-70b-instruct | paid
nvidia/llama-3.1-nemotron-ultra-253b-v1 | paid
+ nvidia/llama-3.3-nemotron-super-49b-v1.5 | paid
nvidia/nemotron-nano-9b-v2 | paid
nvidia/nemotron-nano-9b-v2:free | free
openai/chatgpt-4o-latest | paid
@@ -256,10 +251,11 @@ export interface IKBotOptions {
openai/gpt-4o-mini-search-preview | paid
openai/gpt-5 | paid
openai/gpt-5-chat | paid
+ openai/gpt-5-codex | paid
openai/gpt-5-mini | paid
openai/gpt-5-nano | paid
+ openai/gpt-5-pro | paid
openai/gpt-oss-120b | paid
- openai/gpt-oss-120b:free | free
openai/gpt-oss-20b | paid
openai/gpt-oss-20b:free | free
openai/o1 | paid
@@ -286,6 +282,8 @@ export interface IKBotOptions {
qwen/qwen-max | paid
qwen/qwen-plus | paid
qwen/qwen-turbo | paid
+ qwen/qwen-2.5-7b-instruct | paid
+ qwen/qwen2.5-coder-7b-instruct | paid
qwen/qwen2.5-vl-32b-instruct | paid
qwen/qwen2.5-vl-32b-instruct:free | free
qwen/qwen2.5-vl-72b-instruct | paid
@@ -313,17 +311,20 @@ export interface IKBotOptions {
qwen/qwen3-max | paid
qwen/qwen3-next-80b-a3b-instruct | paid
qwen/qwen3-next-80b-a3b-thinking | paid
+ qwen/qwen3-vl-235b-a22b-instruct | paid
+ qwen/qwen3-vl-235b-a22b-thinking | paid
+ qwen/qwen3-vl-30b-a3b-instruct | paid
+ qwen/qwen3-vl-30b-a3b-thinking | paid
qwen/qwq-32b | paid
- qwen/qwq-32b:free | free
- qwen/qwq-32b-preview | paid
qwen/qwen-2.5-72b-instruct | paid
qwen/qwen-2.5-72b-instruct:free | free
- qwen/qwen-2.5-7b-instruct | paid
qwen/qwen-2.5-coder-32b-instruct | paid
qwen/qwen-2.5-coder-32b-instruct:free | free
+ relace/relace-apply-3 | paid
undi95/remm-slerp-l2-13b | paid
sao10k/l3-lunaris-8b | paid
sao10k/l3-euryale-70b | paid
+ sao10k/l3.1-70b-hanami-x1 | paid
sao10k/l3.1-euryale-70b | paid
sao10k/l3.3-euryale-70b | paid
shisa-ai/shisa-v2-llama3.3-70b | paid
@@ -334,7 +335,7 @@ export interface IKBotOptions {
tencent/hunyuan-a13b-instruct | paid
tencent/hunyuan-a13b-instruct:free | free
thedrummer/anubis-70b-v1.1 | paid
- thedrummer/anubis-pro-105b-v1 | paid
+ thedrummer/cydonia-24b-v4.1 | paid
thedrummer/rocinante-12b | paid
thedrummer/skyfall-36b-v2 | paid
thedrummer/unslopnemo-12b | paid
@@ -342,8 +343,10 @@ export interface IKBotOptions {
thudm/glm-z1-32b | paid
tngtech/deepseek-r1t-chimera | paid
tngtech/deepseek-r1t-chimera:free | free
+ tngtech/deepseek-r1t2-chimera | paid
tngtech/deepseek-r1t2-chimera:free | free
alibaba/tongyi-deepresearch-30b-a3b | paid
+ alibaba/tongyi-deepresearch-30b-a3b:free | free
cognitivecomputations/dolphin-mistral-24b-venice-edition:free | free
microsoft/wizardlm-2-8x22b | paid
x-ai/grok-3 | paid
@@ -351,13 +354,14 @@ export interface IKBotOptions {
x-ai/grok-3-mini | paid
x-ai/grok-3-mini-beta | paid
x-ai/grok-4 | paid
- x-ai/grok-4-fast:free | free
+ x-ai/grok-4-fast | paid
x-ai/grok-code-fast-1 | paid
z-ai/glm-4-32b | paid
z-ai/glm-4.5 | paid
z-ai/glm-4.5-air | paid
z-ai/glm-4.5-air:free | free
z-ai/glm-4.5v | paid
+ z-ai/glm-4.6 | paid
[35m[1m[22m[39m
[35m[1m OpenAI models:[22m[39m
[35m[1m[22m[39m
@@ -414,15 +418,23 @@ export interface IKBotOptions {
gpt-5
gpt-5-2025-08-07
gpt-5-chat-latest
+ gpt-5-codex
gpt-5-mini
gpt-5-mini-2025-08-07
gpt-5-nano
gpt-5-nano-2025-08-07
+ gpt-5-pro
+ gpt-5-pro-2025-10-06
gpt-audio
gpt-audio-2025-08-28
+ gpt-audio-mini
+ gpt-audio-mini-2025-10-06
gpt-image-1
+ gpt-image-1-mini
gpt-realtime
gpt-realtime-2025-08-28
+ gpt-realtime-mini
+ gpt-realtime-mini-2025-10-06
o1
o1-2024-12-17
o1-mini
@@ -439,6 +451,8 @@ export interface IKBotOptions {
o4-mini-deep-research-2025-06-26
omni-moderation-2024-09-26
omni-moderation-latest
+ sora-2
+ sora-2-pro
text-embedding-3-large
text-embedding-3-small
text-embedding-ada-002