osr-plastic/osr-mono
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

openrouter latest

Browse Source
This commit is contained in:
lovebird 2025-03-06 20:25:33 +01:00
parent ba1c1ec79b
commit fcf1d3fcb9
2 changed files with 276 additions and 138 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

160
packages/osr-code-bot/models/data/openai_models.json
View File

@ -1,5 +1,5 @@
{
"timestamp": 1740718317471,
"timestamp": 1741289092072,
"models": [
{
"id": "gpt-4.5-preview",
@ -7,12 +7,6 @@
"created": 1740623059,
"owned_by": "system"
},
{
"id": "omni-moderation-2024-09-26",
"object": "model",
"created": 1732734466,
"owned_by": "system"
},
{
"id": "gpt-4.5-preview-2025-02-27",
"object": "model",
@ -67,24 +61,12 @@
"created": 1725648979,
"owned_by": "system"
},
{
"id": "o1-preview-2024-09-12",
"object": "model",
"created": 1725648865,
"owned_by": "system"
},
{
"id": "o1-mini",
"object": "model",
"created": 1725649008,
"owned_by": "system"
},
{
"id": "o1-preview",
"object": "model",
"created": 1725648897,
"owned_by": "system"
},
{
"id": "gpt-4o-mini-audio-preview",
"object": "model",
@ -98,9 +80,15 @@
"owned_by": "openai-internal"
},
{
"id": "gpt-4-turbo",
"id": "omni-moderation-latest",
"object": "model",
"created": 1712361441,
"created": 1731689265,
"owned_by": "system"
},
{
"id": "omni-moderation-2024-09-26",
"object": "model",
"created": 1732734466,
"owned_by": "system"
},
{
@ -109,12 +97,6 @@
"created": 1727131766,
"owned_by": "system"
},
{
"id": "gpt-4",
"object": "model",
"created": 1687882411,
"owned_by": "openai"
},
{
"id": "babbage-002",
"object": "model",
@ -122,9 +104,15 @@
"owned_by": "system"
},
{
"id": "gpt-4-turbo-preview",
"id": "chatgpt-4o-latest",
"object": "model",
"created": 1706037777,
"created": 1723515131,
"owned_by": "system"
},
{
"id": "gpt-4o-2024-11-20",
"object": "model",
"created": 1739331543,
"owned_by": "system"
},
{
@ -133,6 +121,12 @@
"created": 1699053533,
"owned_by": "system"
},
{
"id": "text-embedding-3-large",
"object": "model",
"created": 1705953180,
"owned_by": "system"
},
{
"id": "gpt-4o-audio-preview-2024-12-17",
"object": "model",
@ -140,9 +134,15 @@
"owned_by": "system"
},
{
"id": "gpt4o-dream-ev3",
"id": "gpt-4",
"object": "model",
"created": 1740596800,
"created": 1687882411,
"owned_by": "openai"
},
{
"id": "o3-mini-2025-01-31",
"object": "model",
"created": 1738010200,
"owned_by": "system"
},
{
@ -152,15 +152,39 @@
"owned_by": "system"
},
{
"id": "gpt-4o-mini-2024-07-18",
"id": "o3-mini",
"object": "model",
"created": 1721172717,
"created": 1737146383,
"owned_by": "system"
},
{
"id": "gpt-4-0125-preview",
"id": "o1-preview",
"object": "model",
"created": 1706037612,
"created": 1725648897,
"owned_by": "system"
},
{
"id": "o1-preview-2024-09-12",
"object": "model",
"created": 1725648865,
"owned_by": "system"
},
{
"id": "gpt-4o-2024-08-06",
"object": "model",
"created": 1722814719,
"owned_by": "system"
},
{
"id": "gpt-3.5-turbo-instruct-0914",
"object": "model",
"created": 1694122472,
"owned_by": "system"
},
{
"id": "gpt-4o",
"object": "model",
"created": 1715367049,
"owned_by": "system"
},
{
@ -175,12 +199,6 @@
"created": 1699053241,
"owned_by": "system"
},
{
"id": "gpt-4-turbo-2024-04-09",
"object": "model",
"created": 1712601677,
"owned_by": "system"
},
{
"id": "davinci-002",
"object": "model",
@ -194,21 +212,9 @@
"owned_by": "system"
},
{
"id": "gpt-4o-2024-08-06",
"id": "gpt-4-turbo",
"object": "model",
"created": 1722814719,
"owned_by": "system"
},
{
"id": "gpt-4o-mini",
"object": "model",
"created": 1721172741,
"owned_by": "system"
},
{
"id": "gpt-4o-2024-05-13",
"object": "model",
"created": 1715368132,
"created": 1712361441,
"owned_by": "system"
},
{
@ -218,21 +224,21 @@
"owned_by": "system"
},
{
"id": "chatgpt-4o-latest",
"id": "gpt-4o-2024-05-13",
"object": "model",
"created": 1723515131,
"created": 1715368132,
"owned_by": "system"
},
{
"id": "gpt-4o",
"id": "o1-2024-12-17",
"object": "model",
"created": 1715367049,
"created": 1734326976,
"owned_by": "system"
},
{
"id": "gpt-3.5-turbo-instruct-0914",
"id": "o1",
"object": "model",
"created": 1694122472,
"created": 1734375816,
"owned_by": "system"
},
{
@ -253,6 +259,12 @@
"created": 1677610602,
"owned_by": "openai"
},
{
"id": "gpt-4-turbo-2024-04-09",
"object": "model",
"created": 1712601677,
"owned_by": "system"
},
{
"id": "gpt-4o-realtime-preview",
"object": "model",
@ -266,9 +278,15 @@
"owned_by": "openai-internal"
},
{
"id": "gpt-4o-2024-11-20",
"id": "gpt-4o-mini-2024-07-18",
"object": "model",
"created": 1739331543,
"created": 1721172717,
"owned_by": "system"
},
{
"id": "gpt-4o-mini",
"object": "model",
"created": 1721172741,
"owned_by": "system"
},
{
@ -289,12 +307,6 @@
"created": 1671217299,
"owned_by": "openai-internal"
},
{
"id": "text-embedding-3-large",
"object": "model",
"created": 1705953180,
"owned_by": "system"
},
{
"id": "gpt-4-0613",
"object": "model",
@ -302,9 +314,15 @@
"owned_by": "openai"
},
{
"id": "omni-moderation-latest",
"id": "gpt-4-0125-preview",
"object": "model",
"created": 1731689265,
"created": 1706037612,
"owned_by": "system"
},
{
"id": "gpt-4-turbo-preview",
"object": "model",
"created": 1706037777,
"owned_by": "system"
}
]

254
packages/osr-code-bot/models/data/openrouter_models.json
View File

@ -1,6 +1,126 @@
{
"timestamp": 1740718317830,
"timestamp": 1741289092304,
"models": [
{
"id": "qwen/qwq-32b:free",
"name": "Qwen: QwQ 32B (free)",
"created": 1741208814,
"description": "QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.",
"context_length": 32768,
"architecture": {
"modality": "text->text",
"tokenizer": "Qwen",
"instruct_type": "qwq"
},
"pricing": {
"prompt": "0",
"completion": "0",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 32768,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "qwen/qwq-32b",
"name": "Qwen: QwQ 32B",
"created": 1741208814,
"description": "QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"tokenizer": "Qwen",
"instruct_type": "qwq"
},
"pricing": {
"prompt": "0.00000015",
"completion": "0.00000045",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "qwen/qwen2.5-32b-instruct",
"name": "Qwen: Qwen2.5 32B Instruct",
"created": 1741042744,
"description": "Qwen2.5 32B Instruct is the instruction-tuned variant of the latest Qwen large language model series. It provides enhanced instruction-following capabilities, improved proficiency in coding and mathematical reasoning, and robust handling of structured data and outputs such as JSON. It supports long-context processing up to 128K tokens and multilingual tasks across 29+ languages. The model has 32.5 billion parameters, 64 layers, and utilizes an advanced transformer architecture with RoPE, SwiGLU, RMSNorm, and Attention QKV bias.\n\nFor details, please refer to the [Qwen2.5 Blog](https://qwenlm.github.io/blog/qwen2.5/).",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"tokenizer": "Qwen",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000079",
"completion": "0.00000079",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "moonshotai/moonlight-16b-a3b-instruct:free",
"name": "Moonshot AI: Moonlight 16B A3B Instruct (free)",
"created": 1740719801,
"description": "Moonlight-16B-A3B-Instruct is a 16B-parameter Mixture-of-Experts (MoE) language model developed by Moonshot AI. It is optimized for instruction-following tasks with 3B activated parameters per inference. The model advances the Pareto frontier in performance per FLOP across English, coding, math, and Chinese benchmarks. It outperforms comparable models like Llama3-3B and Deepseek-v2-Lite while maintaining efficient deployment capabilities through Hugging Face integration and compatibility with popular inference engines like vLLM12.",
"context_length": 8192,
"architecture": {
"modality": "text->text",
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0",
"completion": "0",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 8192,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "nousresearch/deephermes-3-llama-3-8b-preview:free",
"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",
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0",
"completion": "0",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "openai/gpt-4.5-preview",
"name": "OpenAI: GPT-4.5 (Preview)",
@ -15,7 +135,7 @@
"pricing": {
"prompt": "0.000075",
"completion": "0.00015",
"image": "0",
"image": "0.108375",
"request": "0"
},
"top_provider": {
@ -222,20 +342,20 @@
"name": "Llama Guard 3 8B",
"created": 1739401318,
"description": "Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\n\nLlama Guard 3 was aligned to safeguard against the MLCommons standardized hazards taxonomy and designed to support Llama 3.1 capabilities. Specifically, it provides content moderation in 8 languages, and was optimized to support safety and security for search and code interpreter tool calls.\n",
"context_length": 16384,
"context_length": 8192,
"architecture": {
"modality": "text->text",
"tokenizer": "Llama3",
"instruct_type": "none"
},
"pricing": {
"prompt": "0.0000003",
"completion": "0.0000003",
"prompt": "0.0000002",
"completion": "0.0000002",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 16384,
"context_length": 8192,
"max_completion_tokens": null,
"is_moderated": false
},
@ -889,6 +1009,30 @@
},
"per_request_limits": null
},
{
"id": "deepseek/deepseek-r1-zero:free",
"name": "DeepSeek: DeepSeek R1 Zero (free)",
"created": 1737607919,
"description": "DeepSeek-R1-Zero is a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step. It's 671B parameters in size, with 37B active in an inference pass.\n\nIt demonstrates remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.\n\nDeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. See [DeepSeek R1](/deepseek/deekseek-r1) for the SFT model.\n\n",
"context_length": 163840,
"architecture": {
"modality": "text->text",
"tokenizer": "Other",
"instruct_type": "deepseek-r1"
},
"pricing": {
"prompt": "0",
"completion": "0",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 163840,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "google/gemini-2.0-flash-thinking-exp:free",
"name": "Google: Gemini 2.0 Flash Thinking Experimental 01-21 (free)",
@ -942,21 +1086,21 @@
"name": "DeepSeek: R1",
"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": 128000,
"context_length": 64000,
"architecture": {
"modality": "text->text",
"tokenizer": "DeepSeek",
"instruct_type": "deepseek-r1"
},
"pricing": {
"prompt": "0.0000008",
"completion": "0.0000024",
"prompt": "0.00000055",
"completion": "0.00000219",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 128000,
"max_completion_tokens": null,
"context_length": 64000,
"max_completion_tokens": 64000,
"is_moderated": false
},
"per_request_limits": null
@ -1117,14 +1261,14 @@
"instruct_type": null
},
"pricing": {
"prompt": "0.00000125",
"completion": "0.00000125",
"prompt": "0.0000012",
"completion": "0.0000012",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": 12288,
"max_completion_tokens": 65536,
"is_moderated": false
},
"per_request_limits": null
@ -1705,6 +1849,30 @@
},
"per_request_limits": null
},
{
"id": "qwen/qwen-2.5-coder-32b-instruct:free",
"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": 128000,
"architecture": {
"modality": "text->text",
"tokenizer": "Qwen",
"instruct_type": "chatml"
},
"pricing": {
"prompt": "0",
"completion": "0",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 128000,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "qwen/qwen-2.5-coder-32b-instruct",
"name": "Qwen2.5 Coder 32B Instruct",
@ -2420,7 +2588,7 @@
},
"top_provider": {
"context_length": 16384,
"max_completion_tokens": null,
"max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null
@ -2838,7 +3006,7 @@
"name": "Nous: Hermes 3 405B Instruct",
"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,
"context_length": 131000,
"architecture": {
"modality": "text->text",
"tokenizer": "Llama3",
@ -2851,32 +3019,8 @@
"request": "0"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": 8192,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "perplexity/llama-3.1-sonar-huge-128k-online",
"name": "Perplexity: Llama 3.1 Sonar 405B Online",
"created": 1723593600,
"description": "Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. The model is built upon the Llama 3.1 405B and has internet access.",
"context_length": 127072,
"architecture": {
"modality": "text->text",
"tokenizer": "Llama3",
"instruct_type": null
},
"pricing": {
"prompt": "0.000005",
"completion": "0.000005",
"image": "0",
"request": "0.005"
},
"top_provider": {
"context_length": 127072,
"max_completion_tokens": null,
"context_length": 131000,
"max_completion_tokens": 131000,
"is_moderated": false
},
"per_request_limits": null
@ -3303,7 +3447,7 @@
"pricing": {
"prompt": "0.00000015",
"completion": "0.0000006",
"image": "0.007225",
"image": "0.000217",
"request": "0"
},
"top_provider": {
@ -3889,30 +4033,6 @@
},
"per_request_limits": null
},
{
"id": "deepseek/deepseek-chat-v2.5",
"name": "DeepSeek V2.5",
"created": 1715644800,
"description": "DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct. The new model integrates the general and coding abilities of the two previous versions. For model details, please visit [DeepSeek-V2 page](https://github.com/deepseek-ai/DeepSeek-V2) for more information.",
"context_length": 8192,
"architecture": {
"modality": "text->text",
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0.000002",
"completion": "0.000002",
"image": "0",
"request": "0"
},
"top_provider": {
"context_length": 8192,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null
},
{
"id": "openai/gpt-4o-2024-05-13",
"name": "OpenAI: GPT-4o (2024-05-13)",