open-free-llm-api/awesome-freellm-apis

134+ free LLM APIs & AI API keys from 40+ providers. Google Gemini, NVIDIA NIM, Groq, OpenRouter & more. One-click setup for Claude Code, Cursor and Codex.

What it solves

Finding free Large Language Model (LLM) APIs is often a tedious process of searching through fragmented documentation, guessing which providers still offer free tiers, and managing different sign-up requirements. This project eliminates that friction by providing a centralized, machine-readable directory of over 526 free LLM APIs.

How it works

The project maintains a live, daily-updated database of free LLM providers. It categorizes them by their requirements (such as whether they need a credit card or just an email) and provides the necessary base URLs and model IDs. Because these providers use OpenAI-compatible endpoints, you can plug these details directly into popular developer tools like Cursor, Aider, or Claude Code by simply updating your configuration settings.

Who it’s for

This is for developers, researchers, and hobbyists who want to integrate LLMs into their workflows or applications without the immediate cost of paid subscriptions. It is particularly useful for those already using AI-assisted coding tools who want to swap out expensive default models for free alternatives.

Highlights

  • Always current: Data is refreshed daily via automated monitoring.
  • Transparent requirements: Clearly identifies which providers require credit cards, phone verification, or simple email registration.
  • Ready-to-use configs: Includes one-click configuration snippets for popular tools like Cursor, Aider, and Claude Code.
  • Side-by-side comparison: Instantly compare context windows, rate limits, and supported modalities across 30 different providers.

Related

  • Project
    dusty-nv/jetson-containers

    jetson‑containers is a modular Docker‑based build system that supplies ready‑made, CUDA‑compatible AI/ML, robotics, and simulation packages for NVIDIA Jetson edge devices. It lets you pick frameworks (PyTorch, TensorFlow, LLM toolkits, ROS, etc.), build a single container with a single command, and run it with NVIDIA runtime defaults. Ideal for developers and researchers who need reproducible, high‑performance AI environments on Jetson hardware.

  • Project
    sdli1995/dlssg_for_sm86

    A proxy tool that enables NVIDIA DLSS Frame Generation and optimized Super Resolution on RTX 20 and 30 series graphics cards by bypassing hardware architecture checks.

  • Project
    arrayfire/arrayfire

    A general-purpose tensor library that provides a high-level abstraction for parallel computing across CPUs, GPUs, and other hardware accelerators.

  • Project
    skyzh/tiny-llm

    tiny-llm is a hands-on course for systems engineers to understand LLM inference end to end. You build a Qwen3 model from scratch using MLX arrays, implement operators yourself, and progress from basic matmul to a mini-vLLM and a coding agent — all on Apple silicon.