freellmapi

MCP.Pizza Chef: tashfeenahmed

This tool pools the free usage allowances offered by dozens of separate AI companies — including Google, Mistral, and Cohere — into one connection your coding assistant can use. Instead of juggling accounts and settings for each provider, you add your free keys once, and the tool quietly picks a working model and switches to a backup the moment one runs low. It works with tools such as Cursor, Cline, Roo Code, and Claude Code, and setup means pasting one short snippet into your app's settings.

Coding

Use This MCP server To

Keep coding with AI help even after hitting a free limit Combine free trials from many AI providers into one connection Automatically switch to a backup AI provider if one runs out Try different free AI models without signing up for each one Connect a locally-run AI model to my coding assistant Avoid paying for AI access while experimenting in my coding assistant

README

FreeLLMAPI

4 billion tokens per month. 29 free LLM providers. 358 free model endpoints. One OpenAI-compatible endpoint.

Aggregate free tiers from dozens of providers, plus custom OpenAI-compatible chat, embedding, image, and audio endpoints, behind a single /v1 API. Keys are stored encrypted. A router picks the best available model for each request, falls over to the next provider when one is rate-limited, and tracks per-key usage so you stay under every free-tier cap.

CI GitHub stars License: MIT PRs Welcome Docker image Ask DeepWiki

freellmapi.co · browse the full catalog: 251 model families, 358 free endpoints

English · 简体中文

FreeLLMAPI dashboard — Models page with the monthly token budget

Your router updates its own model catalog from a signed feed: new free models, quota changes, and compatibility fixes land without a git pull. Go live at freellmapi.co ($19/yr, cancel anytime).


Contents

freellmapi FAQ

Do I need to pay to use this?
The tool itself doesn't charge you — it works by pooling the free usage that AI companies already give away, so you can use it at no cost as long as you stay within those free limits.
Which apps can I use this with?
It works with coding assistants and command-line tools such as Cursor, Cline, Goose, Roo Code, Claude Code, Codex CLI, Gemini CLI, and Aider.
Do I need my own accounts with the AI companies?
Yes — you sign up for free accounts with the providers you want (for example Google, Mistral, or Cohere), grab their free keys, and add them to this tool; it doesn't include an AI service of its own.
How hard is it to set up?
Setup is quick: you install it with one command, then paste a short snippet into your app's settings, similar to adding a browser extension.
Can I use this to avoid running out of free AI usage?
Yes — when one provider's free daily or monthly limit runs out, the tool automatically switches your requests to another provider that still has room left, so your work isn't interrupted.
Can I use this to connect a locally-run AI model?
Yes — alongside the free providers, you can point it at any compatible AI server you run yourself, including local tools like Ollama or LM Studio.
Which AI companies' free plans does this include?
It pools free plans from around 28 providers, including Google, Mistral, Cohere, and NVIDIA, plus many smaller ones, and the full list is kept current automatically.
Is it safe to store my keys with this tool?
The tool encrypts the keys you add, and since you run it yourself, they stay on your own setup rather than being sent to a third party.