| meta-llama/llama-4-maverick | Meta | 256,000 | Llama 4 Maverick |
| google/gemini-3-pro-preview | Google | 200,000 | Gemini 3 Pro Preview |
| BAAI/bge-base-en-v1.5 | BAAI | 512 | BAAI-Bge-Base-1p5 |
| togethercomputer/m2-bert-80M-32k-retrieval | Together AI | 32,000 | M2-BERT-Retrieval-32k |
| imagen-4.0-ultra-generate-preview-06-06 | Google | - | Imagen 4 Ultra |
| x-ai/grok-2-image | xAI | - | Grok 2 Image |
| claude-3-7-sonnet-20250219 | Anthropic | 200,000 | Claude 3.7 Sonnet |
| claude-3-5-haiku-20241022 | Anthropic | 200,000 | - |
| gemini-2.0-flash-exp | Google | 1,000,000 | Gemini 2.0 Flash Experimental |
| meta-llama/Meta-Llama-Guard-3-8B | Meta | 8,000 | Llama Guard 3 (8B) |
| meta-llama/LlamaGuard-2-8b | Meta | 8,000 | LlamaGuard 2 (8b) |
| meta-llama/Llama-Guard-3-11B-Vision-Turbo | Meta | 128,000 | - |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | Meta | 128,000 | Llama 3.1 70B Instruct Turbo |
| meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Meta | 4,000 | Llama 3.1 (405B) Instruct Turbo |
| meta-llama/Llama-3.2-3B-Instruct-Turbo | Meta | 131,000 | Llama 3.2 3B Instruct Turbo |
| Qwen/Qwen3-235B-A22B-fp8-tput | Alibaba Cloud | 32,000 | Qwen 3 235B A22B |
| Qwen/Qwen2.5-72B-Instruct-Turbo | Alibaba Cloud | 32,000 | Qwen 2.5 72B Instruct Turbo |
| qwen/qwen-2.5-vl-7b-instruct | Alibaba Cloud | 32,000 | Qwen2.5 VL 7B Instruct |
| mistralai/mistral-tiny | Mistral AI | 32,000 | Mistral Tiny |
| mistralai/Mistral-7B-Instruct-v0.3 | Mistral AI | 32,000 | Mistral (7B) Instruct v0.3 |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | Meta | 128,000 | Llama 3.1 8B Instruct Turbo |
| mistralai/Mistral-7B-Instruct-v0.2 | Mistral AI | 32,000 | Mistral (7B) Instruct v0.2 |
| chatgpt-4o-latest | OpenAI | 128,000 | - |
| meta-llama/llama-4-scout | Meta | 1,000,000 | Llama 4 Scout |
| BAAI/bge-large-en-v1.5 | BAAI | 512 | bge-large-en |
| bagoodex/bagoodex-search-v1 | Bagoodex | | Bagoodex Web Search v1 |
| deepseek/deepseek-prover-v2 | DeepSeek | 164,000 | DeepSeek Prover V2 |
claude-3-opus-20240229
anthropic/claude-3-opus
claude-3-opus-latest | Anthropic | 200,000 | Claude 3 Opus |
| luma/ray-1.6 | Luma AI | | Ray 1.6 |
| meta-llama/Llama-3-70b-chat-hf | Meta | 8,000 | Llama 3 70B Instruct Reference |
| bytedance/seededit-3.0-i2i | ByteDance | | Seedream 3.0 |
| textembedding-gecko-multilingual@001 | Google | 2,000 | Textembedding-gecko-multilingual@001 |
| textembedding-gecko@003 | Google | 2,000 | Textembedding-gecko@003 |
| mistralai/codestral-2501 | Mistral AI | 256,000 | Mistral Codestral-2501 |
| mistralai/Mistral-7B-Instruct-v0.1 | Mistral AI | 8,000 | Mistral (7B) Instruct v0.1 |
| Qwen/Qwen2.5-Coder-32B-Instruct | Alibaba Cloud | 131,000 | Qwen 2.5 Coder |
| Qwen/QwQ-32B | Alibaba Cloud | 131,000 | Qwq-32B |
| kling-video/v1.5/standard/text-to-video | Kling AI | 128,000 | Kling 1.5 Standart |
o1-mini
o1-mini-2024-09-12 | OpenAI | 128,000 | OpenAI o1-mini |
| Qwen/Qwen2-72B-Instruct | Alibaba Cloud | 32,000 | Qwen 2 Instruct (72B) |
| claude-3-5-sonnet-20240620 | Anthropic | 200,000 | - |
| claude-3-5-sonnet-20241022 | Anthropic | 200,000 | Claude 3.5 Sonnet 20241022 |
| cohere/command-r-plus | Cohere | 128,000 | Command R+ |
| google/gemma-2-27b-it | Google | 8,000 | Gemma 2 (27b) |
| NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | Nous Research | 32,000 | - |
| nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | Nvidia | 128,000 | Llama 3.1 Nemotron 70B Instruct |
| meta-llama/Llama-3-8b-chat-hf | Meta | 8,000 | Llama 3 8B Instruct Reference |
| meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo | Meta | 131,000 | Llama 3.2 90B Vision Instruct Turbo |
| meta-llama/Llama-Vision-Free | Meta | 128,000 | - |
| meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo | Meta | 131,000 | Llama 3.2 11B Vision Instruct Turbo |
| abab6.5s-chat | MiniMax | 245,000 | - |
| openrouter/horizon-beta | OpenRouter | 256,000 | - |
| openrouter/horizon-alpha | OpenRouter | 256,000 | - |
| wan/v2.1/1.3b/text-to-video | Alibaba Cloud | - | Wan 2.1 |
o1-preview,
o1-preview-2024-09-12 | OpenAI | 128,000 | OpenAI o1-preview |
claude-3-sonnet-20240229,
anthropic/claude-3-sonnet,
claude-3-sonnet-latest | Anthropic | 200,000 | Claude 3 Sonnet |
google/gemini-2.5-pro-preview,
google/gemini-2.5-pro-preview-05-06 | Google | 1,000,000 | Gemini Pro 2.5 Preview |
| google/gemini-2.5-flash-preview | Google | 1,000,000 | Gemini 2.5 Flash Preview |
| neversleep/llama-3.1-lumimaid-70b | NeverSleep | 8,000 | Llama 3.1 Lumimaid 70b |
| x-ai/grok-beta | xAI | 131,000 | Grok-2 Beta |
| gpt-4.5-preview | OpenAI | 128,000 | Chat GPT 4.5 preview |
| gemini-1.5-flash | Google | 1,000,000 | Gemini 1.5 Flash |
| gemini-1.5-pro | Google | 1,000,000 | Gemini 1.5 Pro |
| google/gemma-3-1b-it | Google | 128,000 | Gemma 3 (1B) |
| togethercomputer/m2-bert-80M-8k-retrieval | TogetherAI | 8,000 | M2-BERT-Retrieval-8k |
| togethercomputer/m2-bert-80M-2k-retrieval | TogetherAI | 2,000 | M2-BERT-Retrieval-2K |
| Gryphe/MythoMax-L2-13b-Lite | Gryphe | 4,000 | - |
| mistralai/Mixtral-8x22B-Instruct-v0.1 | Mistral AI | 64,000 | Mixtral 8x22B Instruct |
| google/gemini-2.5-pro-exp-03-25 | Google | 1,000,000 | - |
| google/gemini-2.0-flash-thinking-exp-01 | Google | 1,000,000 | Gemini 2.0 Flash Thinking Experimental |
| ai21/jamba-1-5-mini | AI21 Labs | 256,000 | Jamba 1.5 Mini |
| textembedding-gecko@001 | Google | 3,000 | - |
| google/gemini-pro or gemini-pro | Google | 32,000 | Gemini 1.0 Pro |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo-128K | Meta | 128,000 | - |
| stabilityai/stable-diffusion-xl-base-1.0 | Stability AI | | Stable Diffusion XL 1.0 |
| upstage/solar-10.7b-instruct-v1.0 | Upstage | 4,000 | Upstage SOLAR Instruct v1 (11B) |
| meta-llama/Llama-2-13b-chat-hf | Meta | 4,100 | LLaMA-2 Chat (13B) |
| meta-llama/meta-llama-3-70b-instruct-turbo | Meta | 128,000 | - |
| google/gemma-2-9b-it | Google | 8,000 | Gemma 2 (9B) |
| google/gemma-2b-it | Google | 8,000 | Gemma Instruct (2B) |
| Gryphe/MythoMax-L2-13b | Gryphe | 4,000 | MythoMax-L2 (13B) |
| microsoft/WizardLM-2-8x22B | Microsoft | 64,000 | WizardLM 2-8 (22B) |
| Austism/chronos-hermes-13b | Austism | 2,000 | Chronos Hermes 13b |
| databricks/dbrx-instruct | Databricks | 32,000 | DBRX Instruct |
| deepseek-ai/deepseek-llm-67b-chat | DeepSeek | 4,000 | Deepseek-LLM-67b-Chat |
| deepseek-ai/deepseek-coder-33b-instruct | DeepSeek | 16,000 | Deepseek Coder Instruct (33B) |
| Meta-Llama/Llama-2-7b-chat-hf | Meta | 4,000 | LLaMA-2 Chat (7B) |
| Meta-Llama/Meta-Llama-3-70B-Instruct-Lite | Meta | 8,000 | Llama 3 70B Instruct Lite |
| Meta-Llama/Llama-Guard-7b | Meta | 4,000 | Llama Guard (7B) |
| meta-llama/Llama-2-7b-hf | Meta | 4,000 | LLaMA-2 (7B) |
| meta-llama/Llama-3-8b-hf | Meta | 8,000 | Llama-3 (8B) |
| codellama/CodeLlama-70b-hf | Meta | 16,000 | Code Llama (70B) |
| codellama/CodeLlama-7b-Instruct-hf | Meta | 16,000 | Code Llama Instruct (7B) |
| codellama/CodeLlama-13b-Instruct-hf | Meta | 16,000 | Code Llama Instruct (13B) |
| codellama/CodeLlama-70b-Instruct-hf | Meta | 4,000 | Code Llama Instruct (70B) |
| codellama/CodeLlama-70b-Python-hf | Meta | 4,000 | Code Llama Python (70B) |
| mistralai/Mixtral-8x22B-Instruct-v0.1 | Mistral AI | 64,000 | Mixtral 8x22B Instruct |
| gpt-3.5-turbo-16k-0613 | OpenAI | | - |
| gpt-4-0613 | OpenAI | 128,000 | Chat GPT 4 Turbo |
| Qwen/Qwen-14B-Chat | Alibaba Cloud | 8,000 | Qwen Chat (14B) |
| Qwen/Qwen1.5-0.5B | Alibaba Cloud | 32,000 | Qwen 1.5 (0.5B) |
| Qwen/Qwen1.5-1.8B | Alibaba Cloud | 32,000 | Qwen 1.5 (1.8B) |
| Qwen/Qwen1.5-4B | Alibaba Cloud | 32,000 | Qwen 1.5 (4B) |
| Qwen/Qwen1.5-1.8B-Chat | Alibaba Cloud | 32,000 | Qwen 1.5 Chat (1.8B) |
| Qwen/Qwen1.5-4B-Chat | Alibaba Cloud | 32,000 | Qwen 1.5 Chat (4B) |
| Qwen/Qwen1.5-7B-Chat | Alibaba Cloud | 32,000 | Qwen 1.5 Chat (7B) |
| Qwen/Qwen1.5-14B-Chat | Alibaba Cloud | 32,000 | Qwen 1.5 Chat (14B) |
| qwen/qvq-72b-preview | Alibaba Cloud | 32,000 | QVQ-72B-Preview |
| togethercomputer/guanaco-13b | Tim Dettmers | 2,000 | Guanaco (13B) |
| togethercomputer/guanaco-33b | Tim Dettmers | 2,000 | Guanaco (33B) |
| togethercomputer/guanaco-65b | Tim Dettmers | 2,000 | Guanaco (65B) |
| togethercomputer/mpt-7b-chat | Mosaic ML | 2,000 | MPT-Chat (7B) |
| togethercomputer/mpt-30b-chat | Mosaic ML | 8,000 | MPT-Chat (30B) |
| togethercomputer/RedPajama-INCITE-7B-Instruct | RedPajama | 2,000 | RedPajama-INCITE Instruct (7B) |
| prompthero/openjourney | PromptHero | 77 | Openjourney v4 |
| wavymulder/Analog-Diffusion | wavymulder | 77 | Analog Diffusion |
| - | 01.AI | 4,000 | 01-ai Yi Base (6B) |
| Undi95/Toppy-M-7B | Undi95 | 4,000 | Toppy M (7B) |
| SG161222/Realistic_Vision_V3.0_VAE | Together | 77 | Realistic Vision 3.0 |
| tiiuae/falcon-40b | TII | 2,000 | Falcon (40B) |
| allenai/OLMo-7B | Allen Institute for AI | 2,000 | OLMo-7B |
| bigcode/starcoder | BigCode | 8,000 | StarCoder (16B) |
| HuggingFaceH4/starchat-alpha | Hugging Face | 8,000 | StarCoderChat Alpha (16B) |
| NousResearch/Nous-Hermes-Llama2-70b | NousResearch | 4,000 | Nous Hermes LLaMA-2 (70B) |
| NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT | NousResearch | 32,000 | Nous Hermes 2 - Mixtral 8x7B-SFT |
| NousResearch/Nous-Hermes-2-Mistral-7B-DPO | NousResearch | 32,000 | Nous Hermes 2 - Mistral DPO (7B) |
| NousResearch/Hermes-2-Theta-Llama-3-70B | NousResearch | 8,000 | Hermes 2 Theta Llama-3 70B |
| defog/sqlcoder | Defog AI | 8,000 | SQLCoder (15B) |
| replit/replit-code-v1-3b | Replit | 2,000 | Replit-Code-v1 (3B) |
| lmsys/vicuna-13b-v1.5 | Imsys | 4,000 | Vicuna v1.5 (13B) |
| microsoft/phi-2 | Microsoft | 2,000 | Microsoft Phi-2 |
| stabilityai/stablelm-base-alpha-3b | StabilityAI | 4,000 | StableLM Base Alpha 3B |
| runwayml/stable-diffusion-v1-5 | StabilityAI | 77 | Stable Diffusion 1.5 |
| stabilityai/stable-diffusion-2-1 | StabilityAI | 77 | Stable Diffusion 2.1 |
| teknium/OpenHermes-2p5-Mistral-7B | Teknium | 8,000 | OpenHermes-2.5-Mistral (7B) |
| openchat/openchat-3.5-1210 | OpenChat | 8,000 | OpenChat 3.5 (7B) |
| DiscoResearch/DiscoLM-mixtral-8x7b-v2 | Disco Research | 32,000 | DiscoLM Mixtral 8x7b (46.7B) |
| google/flan-t5-xl | Google | 512 | FLAN T5 XL (3B) |
| garage-bAInd/Platypus2-70B-instruct | Garage-bAInd | 4,000 | Platypus2-70B-Instruct |
| EleutherAI/gpt-neox-20b | EleutherAI | 2,000 | GPT Neox 20B |
| gradientai/Llama-3-70B-Instruct-Gradient-1048k | Gradient | 1,048,000 | Llama-3 70B Gradient Instruct 1048k |
| WhereIsAI/UAE-Large-V1 | WhereIsAI | 512 | UAE-Large-V1 |
| zero-one-ai/Yi-34B-Chat | 01.AI | 4,000 | Yi-34B-Chat |
| meta-llama/Meta-Llama-3.1-70B-Reference | Meta | 32,000 | – |
| meta-llama/Meta-Llama-3.1-8B-Reference | Meta | 32,000 | – |
| EleutherAI/llemma_7b | EleutherAI | 32,000 | – |
| huggyllama/llama-30b | Huggyllama | 32,000 | – |
| huggyllama/llama-13b | Huggyllama | 32,000 | – |
| togethercomputer/llama-2-70b | TogetherAI | 32,000 | – |
| togethercomputer/llama-2-13b | TogetherAI | 32,000 | – |
| huggyllama/llama-65b | Huggyllama | 32,000 | – |
| WizardLM/WizardLM-70B-V1.0 | WizardLM | 32,000 | – |
| huggyllama/llama-7b | Huggyllama | 32,000 | – |
| togethercomputer/llama-2-7b | TogetherAI | 32,000 | – |
| NousResearch/Nous-Hermes-13b | NousResearch | 2,000 | – |
| mistralai/Mistral-7B-v0.1 | Mistral AI | 32,000 | Mixtral 7B |
| mistralai/Mixtral-8x7B-v0.1 | Mistral AI | 32,000 | Mixtral-8x7B Instruct v0.1 |
| - | Suno AI | 32 | Suno AI |
Deprecated / No Longer Supported Models
{% hint style="danger" %}
These models are no longer available for API or Playground calls.\
Their description and API reference pages have also been removed from this documentation portal.
{% endhint %}