Models Providers Config Compare Playground Changelog

Compare Free LLM APIs Side by Side

勾选 2 个以上模型，点击 Compare 查看对比。

OpenRouter — Owl Alpha OpenRouter — NVIDIA: Nemotron 3 Nano Omni (free) OpenRouter — Poolside: Laguna XS.2 (free) OpenRouter — Poolside: Laguna M.1 (free) OpenRouter — inclusionAI: Ling-2.6-1T (free) OpenRouter — Tencent: Hy3 preview (free) OpenRouter — Baidu: Qianfan-OCR-Fast (free) OpenRouter — Google: Gemma 4 26B A4B (free) OpenRouter — Google: Gemma 4 31B (free) OpenRouter — Google: Lyria 3 Pro Preview OpenRouter — Google: Lyria 3 Clip Preview OpenRouter — NVIDIA: Nemotron 3 Super (free) OpenRouter — MiniMax: MiniMax M2.5 (free) OpenRouter — Free Models Router OpenRouter — LiquidAI: LFM2.5-1.2B-Thinking (free) OpenRouter — LiquidAI: LFM2.5-1.2B-Instruct (free) OpenRouter — NVIDIA: Nemotron 3 Nano 30B A3B (free) OpenRouter — NVIDIA: Nemotron Nano 12B 2 VL (free) OpenRouter — Qwen: Qwen3 Next 80B A3B Instruct (free) OpenRouter — NVIDIA: Nemotron Nano 9B V2 (free) OpenRouter — OpenAI: gpt-oss-120b (free) OpenRouter — OpenAI: gpt-oss-20b (free) OpenRouter — Z.ai: GLM 4.5 Air (free) OpenRouter — Qwen: Qwen3 Coder 480B A35B (free) OpenRouter — Venice: Uncensored (free) OpenRouter — Google: Gemma 3n 2B (free) OpenRouter — Google: Gemma 3n 4B (free) OpenRouter — Google: Gemma 3 4B (free) OpenRouter — Google: Gemma 3 12B (free) OpenRouter — Google: Gemma 3 27B (free) OpenRouter — Meta: Llama 3.3 70B Instruct (free) OpenRouter — Meta: Llama 3.2 3B Instruct (free) OpenRouter — Nous: Hermes 3 405B Instruct (free) NVIDIA NIM — Various open models Mistral (La Plateforme) — Open and Proprietary Mistral models Cohere — Command A (111B) Cohere — Command R+ Cohere — Command R7B Cohere — Embed 4 Cohere — Rerank 3.5 Google Gemini — Gemini 2.5 Flash Google Gemini — Gemini 2.5 Flash-Lite Mistral AI — Mistral Small 4 Mistral AI — Mistral Medium 3 Mistral AI — Mistral Large 3 Mistral AI — Mistral Nemo (12B) Mistral AI — Codestral Mistral AI — Pixtral Large Z AI (Zhipu AI) — GLM-4.7-Flash Z AI (Zhipu AI) — GLM-4.5-Flash Z AI (Zhipu AI) — GLM-4.6V-Flash Cerebras — llama3.1-8b Cerebras — gpt-oss-120b Cerebras — qwen-3-235b-a22b-instruct-2507 Cerebras — zai-glm-4.7 Cloudflare Workers AI — @cf/meta/llama-3.3-70b-instruct-fp8-fast Cloudflare Workers AI — @cf/meta/llama-3.1-8b-instruct-fp8-fast Cloudflare Workers AI — @cf/meta/llama-3.2-11b-vision-instruct Cloudflare Workers AI — @cf/meta/llama-4-scout-17b-16e-instruct Cloudflare Workers AI — @cf/mistralai/mistral-small-3.1-24b-instruct Cloudflare Workers AI — @cf/google/gemma-4-26b-a4b-it Cloudflare Workers AI — @cf/qwen/qwq-32b Cloudflare Workers AI — @cf/deepseek-ai/deepseek-r1-distill-qwen-32b Cloudflare Workers AI — + 42 more models GitHub Models — gpt-4.1 GitHub Models — gpt-4.1-mini GitHub Models — gpt-4o GitHub Models — o3-mini GitHub Models — o4-mini GitHub Models — Llama-4-Scout-17B-16E GitHub Models — Llama-4-Maverick-17B-128E GitHub Models — Meta-Llama-3.3-70B GitHub Models — DeepSeek-R1 GitHub Models — Mistral-Small-3.1 GitHub Models — + 35 more models Groq — llama-3.3-70b-versatile Groq — llama-3.1-8b-instant Groq — llama-4-scout-17b-16e-instruct Groq — llama-4-maverick-17b-128e-instruct Groq — qwen3-32b Groq — kimi-k2-instruct Groq — deepseek-r1-distill-70b Groq — whisper-large-v3 Groq — whisper-large-v3-turbo Hugging Face — Meta-Llama-3.1-8B-Instruct Hugging Face — Mistral-7B-Instruct-v0.3 Hugging Face — Mixtral-8x7B-Instruct-v0.1 Hugging Face — Phi-3.5-mini-instruct Hugging Face — Qwen2.5-7B-Instruct Hugging Face — + thousands of community models Kilo Code — bytedance-seed/dola-seed-2.0-pro:free Kilo Code — x-ai/grok-code-fast-1:optimized:free Kilo Code — nvidia/nemotron-3-super-120b-a12b:free Kilo Code — arcee-ai/trinity-large-thinking:free Kilo Code — openrouter/free LLM7.io — deepseek-r1-0528 LLM7.io — deepseek-v3-0324 LLM7.io — gpt-4o-mini LLM7.io — mistral-small-3.1-24b LLM7.io — qwen2.5-coder-32b LLM7.io — + ~24 more models ModelScope — Qwen/Qwen3.5-35B-A3B ModelScope — Qwen/Qwen3.5-27B ModelScope — Qwen/Qwen-Image ModelScope — + API-Inference-enabled models NVIDIA NIM — deepseek-ai/deepseek-r1 NVIDIA NIM — nvidia/llama-3.1-nemotron-ultra-253b-v1 NVIDIA NIM — nvidia/nemotron-3-super-120b-a12b NVIDIA NIM — nvidia/nemotron-3-nano-30b-a3b NVIDIA NIM — meta/llama-3.1-405b-instruct NVIDIA NIM — qwen/qwen2.5-72b-instruct NVIDIA NIM — google/gemma-4-31b NVIDIA NIM — mistralai/mistral-large-2-instruct NVIDIA NIM — nvidia/nemotron-nano-2-vl NVIDIA NIM — minimax/minimax-m2.7 NVIDIA NIM — + 90 more models Ollama Cloud — llama3.1:cloud Ollama Cloud — deepseek-r1:cloud Ollama Cloud — qwen2.5:cloud Ollama Cloud — gemma2:cloud Ollama Cloud — mistral:cloud Ollama Cloud — + 400 more models OVHcloud AI Endpoints — Meta-Llama-3_3-70B-Instruct OVHcloud AI Endpoints — DeepSeek-R1-Distill-Llama-70B OVHcloud AI Endpoints — Qwen3-Coder-30B-A3B-Instruct OVHcloud AI Endpoints — Qwen2.5-VL-72B-Instruct OVHcloud AI Endpoints — Mistral-Nemo-Instruct-2407 OVHcloud AI Endpoints — Qwen3Guard-Gen-8B OVHcloud AI Endpoints — Qwen3Guard-Gen-0.6B OVHcloud AI Endpoints — + 30 more models SiliconFlow — Qwen/Qwen3-8B SiliconFlow — deepseek-ai/DeepSeek-R1-0528-Qwen3-8B SiliconFlow — deepseek-ai/DeepSeek-R1-Distill-Qwen-7B SiliconFlow — THUDM/glm-4-9b-chat SiliconFlow — THUDM/GLM-4.1V-9B-Thinking SiliconFlow — deepseek-ai/DeepSeek-OCR SiliconFlow — + embedding/speech models SiliconFlow — Abbreviation

0 selected

Select 2-4 models from the table above to compare them side by side.

Free LLM Hub

Built with free LLM APIs