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.
-
Updated
Aug 15, 2026
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.
Use 30+ AI models (DeepSeek, Kimi, GLM, Claude, GPT-5.5, Gemini, Grok) in GitHub Copilot Chat — free via BYOK. No Copilot Pro needed.
Rescene Agent OS — less chat, more automatic. A 24H self-iterating AI agent that aggregates free models across the web into one OpenAI-compatible API, with a digital daughter who learns online, journals daily, and remembers you. Local-first, free forever.
Reusable starter kit for routing Hermes Agent through a local LiteLLM-based free/free-tier model router with clean aliases, fallback examples, systemd service templates, and terminal-first setup.
Built on Cloudflare Workers, Workers AI, AI Gateway, D1, and KV. Bring your OpenAI, Gemini, Anthropic, or OpenRouter API keys. We route everything through a single sk-stier-… key and a fully OpenAI-compatible endpoint.
Lightweight OpenAI-compatible proxy for OpenRouter's free models. Automatically routes to the best available free (privacy-first) model with seamless failover.
Proxy server that translates Anthropic Claude API requests to OpenAI-compatible format, forwarding to NVIDIA NIM free models. Use Claude Code with free NVIDIA-hosted LLMs (Kimi, MiniMax, GLM, DeepSeek). With a real-time analytics dashboard.
Local gateway that routes Claude Code, Codex & any OpenAI-compatible coding tool across 26 free-tier AI providers — with auto-failover, quota-aware routing, and request auto-fit.
A source-linked directory of free and trial LLM APIs, multimodal models, embeddings, speech, translation, safety, and other inference endpoints. Companion catalog for freellmapi.io.
Easily switch the AI provider and model that Claude Code uses (OpenRouter, Z.ai/GLM, Ollama, HuggingFace, Free-Way) across all your projects with one command. Free-tier focused, secrets-fre
Self-hosted trust layer for cheap AI: offload bulk LLM work to free models, QC'd by a multi-model council — a vetted answer + confidence verdict at $0. OpenAI-compatible.
Claude Code plugin orchestrating anomalyco/opencode — CC plans + reviews, OpenCode executes with free models (Ollama / Groq / OpenRouter / DeepSeek)
Run Claude Code (incl. Ultracode workflows) on free & low-cost models — opencode Zen, OpenRouter, or a ChatGPT/Codex endpoint. Single Go binary, zero config.
OpenAI-compatible proxy & library that auto-routes across OpenRouter's free models, with fallback on rate limits. Run it as a server or import it as a Python submodule.
自动查找 OpenRouter 上的免费模型排序 a Python tool that automatically discovers and ranks free OpenRouter models by availability, latency, and quality
Universal Local Model Launcher — pick your AI agent, pick your local model, launch
CLI to test which OpenRouter free models are currently working. Also supports any OpenAI-compatible API (Groq, Ollama, Together AI).
This is a starter template for projects using Claude Code. It includes configuration files and guidelines to help you get started quickly.
Add a description, image, and links to the free-models topic page so that developers can more easily learn about it.
To associate your repository with the free-models topic, visit your repo's landing page and select "manage topics."