Picture published by the creator on GitHub.
FreeLLMAPI: Combine many AI providers' free tiers behind one address
Added · Updated
Made by Tashfeen
View profile on GitHub (opens in a new tab)Send AI requests to one local server that routes across many providers' free tiers, for developers and coding-agent users who want to stack free quotas.
What it does
You add keys for providers such as Google, Groq or Mistral. FreeLLMAPI stores them encrypted and offers one OpenAI-compatible address, a request format many AI apps already use. A router picks an available model for each request, switches to the next provider when one hits its rate limit, and tracks usage to stay under each free cap.
How to use it
Run the local server, add provider keys on the Keys page, then point any OpenAI client library or coding agent at it. Most agents can be configured with one command that backs up their existing settings and merges in the new ones.
Common use cases
- Point Claude Code, Aider or Cursor at your local server so coding requests keep working when one provider's free limit runs out.
- Add a local Ollama or LM Studio model as a custom provider and reach it through the same address as cloud models.
Can I use this?
Requirements Open source under MIT. Add API keys for the providers you choose; the source lists 34 providers and 635 model endpoints. A paid premium live catalog costs $19/yr, separate from the self-hosted router's monthly snapshots.
Caveat Each provider controls its own free tier, and quotas shift weekly. Some models have extra conditions, such as needing an Aliyun cn binding.
Worth knowing Free installs get model catalog updates 30 days after premium routers. Provider free tiers, models and quotas change without notice. Licensed under MIT.
Why it's here
- 3,780 people starred it on GitHub this week — 49,104 in total.
Numbers as of 8 November 2026, from BuildTube’s latest daily refresh.
Behind it
View sourceBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is FreeLLMAPI?
- You add keys for providers such as Google, Groq or Mistral.
- What can I use FreeLLMAPI for?
- Point Claude Code, Aider or Cursor at your local server so coding requests keep working when one provider's free limit runs out; Add a local Ollama or LM Studio model as a custom provider and reach it through the same address as cloud models
- Can I run FreeLLMAPI on my computer?
- It installs as a desktop app on your own computer.
- What do I need to use FreeLLMAPI?
- API keys from the AI providers you want to use and a machine to run the local server. Hardware needs are not documented in the source.
- What license does FreeLLMAPI use?
- Licensed under MIT.
More from this week
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
- Auto-Ontology Give AI agents checked business meanings for your database
Help AI agents answer questions about company databases using reviewed definitions and SQL, with each answer showing its steps.
- Spec Kit Turn a written spec into plans, tasks and code
Spec Kit gives your AI coding agent a step-by-step process to build a feature, fix a bug or assess an idea.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/gh-tashfeenahmed-freellmapi/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/gh-tashfeenahmed-freellmapi/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="FreeLLMAPI on BuildTube"></iframe>