A curated directory of Agent Skills, the SKILL.md instruction files that teach AI coding assistants like Claude, Codex and Copilot new tasks.
mnfst/awesome-free-llm-apis
A curated list of LLM API providers that offer permanent free tiers for text inference, with endpoints, models and rate limits.
- Stars
- 10,655
- Forks
- 1,191
- Open issues
- 53
- Last commit
- 2 days ago
What is it?
Awesome Free LLM APIs is a curated directory of large language model API providers that keep a free tier for text inference. For each provider it lists the base URL, the API key page, and a table of available models with context length, maximum output, modality and rate limits.
The providers are split into two groups: companies that train their own models, such as Google Gemini, Mistral, Cohere and Z AI, and third-party inference platforms that host open-weight models, such as Groq, Cloudflare Workers AI, Hugging Face, OpenRouter and NVIDIA NIM. Most endpoints are OpenAI SDK-compatible, and the entries note any exceptions, free-tier limits that change, and data-usage or identity-verification conditions.
The list is maintained in a README, with a glossary of RPM, RPD, TPM and TPD terms and a contributing guide for adding providers.
Key features
- 01Lists free-tier endpoints with base URLs and direct links to API key pages.
- 02Shows context length, max output, modality and rate limits for each model.
- 03Covers both model vendors and third-party inference platforms.
- 04Notes data-usage terms, regional restrictions and identity-verification requirements.
- 05Most endpoints are OpenAI SDK-compatible.
Use cases
- Prototyping an LLM feature without paying for API access.
- Comparing context windows and rate limits across free providers before choosing one.
- Finding a free fallback model for side projects or learning.
Quick start
- 1
Get a free API key from the provider's key page (e.g. Groq console)
- 2
Point an OpenAI SDK-compatible client at the provider's base URL, e.g. Groq
https://api.groq.com/openai/v1
Things to know
- Free tiers have strict rate limits and daily quotas that vary by provider.
- Some providers may use free-tier prompts to improve their products or train models.
- Cohere's free Trial key is limited to non-commercial use.
- Some providers require real-name verification or account binding, such as ModelScope.
Topics
FAQ
- What is awesome-free-llm-apis?
- A curated list of LLM API providers that offer permanent free tiers for text inference, with endpoints, models and rate limits. Awesome Free LLM APIs is a curated directory of large language model API providers that keep a free tier for text inference. For each provider it lists the base URL, the API key page, and a table of available models with context length, maximum output, modality and rate limits.
- Is awesome-free-llm-apis free to use? What license does it have?
- awesome-free-llm-apis is open source under the CC0-1.0 license. Check the license terms before using it in commercial products.
- Is awesome-free-llm-apis still maintained?
- Actively maintained. The last commit to awesome-free-llm-apis was on Oct 19, 2026.
- What can I use awesome-free-llm-apis for?
- Prototyping an LLM feature without paying for API access. Comparing context windows and rate limits across free providers before choosing one. Finding a free fallback model for side projects or learning.
- How do I install awesome-free-llm-apis?
- Get a free API key from the provider's key page (e.g. Groq console) Point an OpenAI SDK-compatible client at the provider's base URL, e.g. Groq: https://api.groq.com/openai/v1
- Where can I get awesome-free-llm-apis?
- The source code and installation instructions are on GitHub: https://github.com/mnfst/awesome-free-llm-apis
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A curated, community-maintained list of resources for Claude Code, Anthropic's coding agent, covering skills, agents, plugins, tooling and guides.
A curated hub of generative AI learning courses, research paper roundups, interview prep materials, and code notebooks, organized by journey and skill level.
A curated Chinese-language guide to ChatGPT and frontier LLMs, covering usage, prompting, app development, agents, and productivity tools.
A curated collection of prompts, prompt-engineering frameworks, and research papers for LLMs, with an emphasis on engineering practices over copy-paste templates.
A curated awesome-list of platforms, engines, UIs, models, tools and tutorials for running large language models locally.