tashfeenahmed/freellmapi
tashfeenahmed/freellmapi has 49,114 GitHub stars and 6,780 forks. GitHot measured +3,535 in 7 days and +8,329 in 15 days. Last checked 2026-11-08 14:27 UTC. Last push 2026-11-01.
7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
What you can do
- Anthropic Messages API — /v1/messages speaks Anthropic's wire format over the same router, so Claude Code and the official Anthropic SDKs run against your free pool. Details →
- Native Gemini + Ollama surfaces — Gemini CLI can use /v1beta (generateContent, streaming, token counting, models), while opt-in Ollama emulation serves NDJSON chat/generate, tags, metadata, and embeddings for Zed, JetBrains, and other local-model clients.
- Fusion (multi-model synthesis) — request the virtual fusion model and the router fans your prompt out to a panel of diverse free models in parallel, then a judge model synthesizes one answer from the drafts. Details →
- Image, video & speech generation — /v1/images/generations, /v1/videos/generations, and /v1/audio/speech route across the providers that serve media models; images and speech also accept custom OpenAI-compatible media endpoints. Video jobs are normalized across synchronous and queued providers and return a completed MP4.
Measured star growth
- in 24h
- Update delayed
- in 7 days
- +3,535
- in 15 days
- +8,329
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
docs/en/README.md
OriginalEnglish · 简体中文
FreeLLMAPI documentation
This is the user entry point — start here to install the gateway, call the OpenAI-compatible API, connect coding agents and understand the high-level architecture. The root README is the product overview; this index gets you running.
Guides
- Install & deploy — quick start, Docker Compose, local development, declarative startup config, the Docker image, backups, the desktop app, where your data lives, and an FAQ on password resets, logs and uninstalling.
- API reference — chat completions,
auto:*routing strategies, streaming, tool calling, vision, Gemini Google Search grounding, embeddings, response headers, and the Anthropic Messages surface. - Supported agents — every agent FreeLLMAPI works with and its one-line setup command.
- Clients & coding agents — OpenAI-compatible clients, recipes for Claude Code / Codex CLI / Cline / Continue / Aider / opencode / Cursor, the MCP server, editor autocomplete, and Context Handoff.
- Prompt compression — request-side modes, safeguards, per-request controls, custom tool-output filters, statistics, and preview APIs.
- Proxy transports — outbound proxy transports — forward vs Fetch Relay, system auto-detect,
TRUST_PROXYfor inbound; see Fetch Relay transport for the relay protocol and Cloudflare Worker reference. - Architecture & internals — how the router works, routing and operational details, what's not supported, honest limitations, and the provider Terms-of-Service review.
More
- Android with Termux — experimental local installation using Node's built-in SQLite driver.
- Fallback chains — named fallback-chain lifecycle, empty-chain authoritative 400,
auto:<name>routing, and catalog-sync backfill. - Docker deployment — container configuration and persistent storage.
- Desktop app — build and package the Electron application.
- Contributor guide — development loop, testing expectations, and contribution policy.
- Database migrations — create, apply, inspect, and roll back schema migrations.
Website assets in this directory
index.html— project landing page.install.sh— Unix Docker bootstrap script.install.ps1— PowerShell bootstrap script.success.html— post-install success page.
Explore related projects
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
299,524 starsNousResearch/hermes-agent
The agent that grows with you
261,666 starsmultica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
230,837 starsfirecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
199,551 stars