Awesome Free LLM APIs
Bruno Perez
2 min read
We went through every LLM API we could find and kept only the ones with a permanent free tier. No trial credits, no time-limited promos.
The full list lives on GitHub: awesome-free-llm-apis. Star it to stay updated and open a PR if we are missing one.
Here is where things stand as of March 2026.
Provider APIs
APIs from the companies that actually train the models.
- Google Gemini 🇺🇸 - Gemini 2.5 Pro, Flash, Flash-Lite +4 more. 10 RPM, 20 RPD.
- Cohere 🇺🇸 - Command A, Command R+, Aya Expanse 32B +9 more. 20 RPM, 1K/mo.
- Mistral AI 🇪🇺 - Mistral Large 3, Small 3.1, Ministral 8B +3 more. 1 req/s, 1B tok/mo.
- Zhipu AI 🇨🇳 - GLM-4.7-Flash, GLM-4.5-Flash, GLM-4.6V-Flash. Limits undocumented.
Inference providers
Third-party platforms hosting open-weight models.
- GitHub Models 🇺🇸 - GPT-4o, Llama 3.3 70B, DeepSeek-R1 +more. 10-15 RPM, 50-150 RPD.
- NVIDIA NIM 🇺🇸 - Llama 3.3 70B, Mistral Large, Qwen3 235B +more. 40 RPM.
- Groq 🇺🇸 - Llama 3.3 70B, Llama 4 Scout, Kimi K2 +17 more. 30 RPM, 14,400 RPD.
- Cerebras 🇺🇸 - Llama 3.3 70B, Qwen3 235B, GPT-OSS-120B +3 more. 30 RPM, 14,400 RPD.
- Cloudflare Workers AI 🇺🇸 - Llama 3.3 70B, Qwen QwQ 32B +47 more. 10K neurons/day.
- LLM7.io 🇬🇧 - DeepSeek R1, Flash-Lite, Qwen2.5 Coder +27 more. 30 RPM (120 with token).
- Kluster AI 🇺🇸 - DeepSeek-R1, Llama 4 Maverick, Qwen3-235B +2 more. Limits undocumented.
- OpenRouter 🇺🇸 - DeepSeek R1, Llama 3.3 70B, GPT-OSS-120B +29 more. 20 RPM, 50 RPD.
- Hugging Face 🇺🇸 - Llama 3.3 70B, Qwen2.5 72B, Mistral 7B +many more. $0.10/mo in free credits.
Notes
- RPM means requests per minute. RPD means requests per day.
- “Limits undocumented” means the provider does not publish their rate limits.
- All endpoints are OpenAI SDK-compatible unless noted.
- Each link points to the provider’s API key page.
This list changes fast. Star the repo to get notified when we add providers, and open a PR if you spot one we missed.