FreeLLMAPIFind AI model APIs you can use for free
Compare free quotas, usage limits and sign-up requirements across providers, and see how each listing was checked.
- Allam 2 7BFast & lightweightGeneral useConfirmed from docs1 free access options
- Compound MiniFast & lightweightGeneral useConfirmed from docs1 free access options
- Dolphin Mistral 24B Venice EditionFast & lightweightGeneral useConfirmed from docs1 free access options
- GLM-4-Flash-250414Fast & lightweightGeneral useConfirmed from docs1 free access options
- Gemini 2.5 Flash-LiteFast & lightweightGeneral useImage understandingConfirmed from docs1 free access options
- Gemini 3 FlashFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemini 3.1 Flash-LiteFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemini 3.5 FlashFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemma 2B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemma 3 12B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemma 3 1B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemma 3 27B InstructFast & lightweightGeneral useConfirmed from docs2 free access options
- Gemma 3 4B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemma 4 26B A4B ITFast & lightweightGeneral useConfirmed from docs3 free access options
- Gemma 4 31B ITFast & lightweightGeneral useConfirmed from docs2 free access options
- Gemma 7B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Gemma sea lion v4 27b itFast & lightweightGeneral useConfirmed from docs1 free access options
- Granite 4.0 h microFast & lightweightGeneral useConfirmed from docs1 free access options
- Llama 2 7B ChatFast & lightweightGeneral useConfirmed from docs1 free access options
- Llama 3.1 8BFast & lightweightGeneral useConfirmed from docs2 free access options
- Llama 3.1 8B InstantFast & lightweightGeneral useConfirmed from docs1 free access options
- Llama 3.1 8B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Llama 3.2 1B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Llama 3.2 3B InstructFast & lightweightGeneral useConfirmed from docs2 free access options
- Llama Guard 3 8BFast & lightweightGeneral useConfirmed from docs1 free access options
- Meta-Llama-3.1-8B-InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Ministral 3BFast & lightweightGeneral useConfirmed from docs1 free access options
- Mistral 7B Instruct v0.2Fast & lightweightGeneral useConfirmed from docs1 free access options
- Mistral Small 3.1Fast & lightweightGeneral useConfirmed from docs1 free access options
- Mistral Small 3.1 24B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Nemotron 3 Nano 30B A3BFast & lightweightGeneral useConfirmed from docs1 free access options
- Nemotron Nano 9B v2Fast & lightweightGeneral useConfirmed from docs1 free access options
- OpenAI GPT-4.1-miniFast & lightweightGeneral useConfirmed from docs1 free access options
- OpenAI GPT-4.1-nanoFast & lightweightGeneral useConfirmed from docs1 free access options
- Phi-4-mini-instructFast & lightweightGeneral useConfirmed from docs1 free access options
- Pixtral 12BFast & lightweightImage understandingGeneral useConfirmed from docs2 free access options
- Qwen3 30b a3b fp8Fast & lightweightGeneral useConfirmed from docs1 free access options
- Qwen3 Next 80B A3B InstructFast & lightweightGeneral useConfirmed from docs1 free access options
- Qwen3.6 27BFast & lightweightGeneral useConfirmed from docs1 free access options
- command-r7b-12-2024Fast & lightweightGeneral useConfirmed from docs1 free access options
- command-r7b-arabic-02-2025Fast & lightweightGeneral useConfirmed from docs1 free access options
- holo2-30b-a3bFast & lightweightGeneral useConfirmed from docs1 free access options
- minimax-m2.7Fast & lightweightGeneral useConfirmed from docs1 free access options
- mistral-medium-3.5-128bFast & lightweightGeneral useConfirmed from docs1 free access options
- mistral-small-3.2-24b-instruct-2506Fast & lightweightGeneral useConfirmed from docs1 free access options
- qwen3.5-397b-a17bFast & lightweightGeneral useConfirmed from docs1 free access options
- qwen3.6-35b-a3bFast & lightweightGeneral useConfirmed from docs1 free access options
- voxtral-small-24b-2507Fast & lightweightGeneral useConfirmed from docs1 free access options
Unified AI API launch updates
Use one API to call multiple free AI models while keeping your own provider API keys. Leave your email and we’ll notify you when it launches — no account needed.