← Directory

FreeLLMAPI

FreeLLMAPI is a large language model (LLM) gateway that aggregates the free tiers of many model providers behind one OpenAI-compatible /v1 endpoint.

  • AI
  • Network Services
  • Tools & Utilities
FreeLLMAPI is a large language model (LLM) gateway that aggregates the free tiers of many model providers behind one OpenAI-compatible /v1 endpoint. It selects an available model for each request, fails over when a provider rate limits, and tracks per-key usage so you stay inside provider caps. It supports Anthropic Messages, Gemini, and Ollama-compatible endpoints, and works with coding tools such as Claude Code, Cline, Aider, and Open WebUI.

Platform availability

Available on 4 of 9 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac
  • Windows
  • Linux

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

77/100 Good

Maintained
100last commit 0 days ago
Popular
9447,475 GitHub stars
Easy to install
504 install platforms, Docker image
Light to run
304 GB minimum RAM
Security check
70no serious findings, 27 minor, CI, tests

Availability: platform listings confirmed today

GitHub stars
47,475
Open issues
57
Last commit
2026-11-04
Latest release
v0.16.19
License
MIT
Activity
rising

Checked today - source: GitHub (tashfeenahmed/freellmapi)

Resources & Compatibility

Minimum requirements: 4 GB RAM, 2 GB disk.

Checked today - source: Docker Hub image tags and published docs

First-install notes

  • Prepare .env, then start Docker Compose Before running docker compose up -d, install Docker and Docker Compose, then create .env with ENCRYPTION_KEY (for example, openssl rand -hex 32) and PORT=3001. The key protects keys stored on disk, so keep it safe and use the same key later. source
  • Check the Docker Compose logs After starting the stack, run docker compose logs -f freellmapi to watch the gateway start. If the container fails or stops, the dashboard and API will not respond until you find the error in the logs. source
  • Confirm URL and API key for agents Before running setup commands for an agent, confirm the gateway URL and the unified API key (the password the agent uses to reach the gateway). If either is wrong, the setup creates settings the agent cannot use and the tool cannot authenticate. source
  • Install from GitHub Releases Download the latest FreeLLMAPI build for macOS, Windows, or Linux from the GitHub Releases page, then follow the operating-system-specific installation instructions. source

Fetched today - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How are provider keys stored and what should I back up?

Provider keys are stored encrypted. Back up the .encryption-key file together with the database.

What happens when a provider applies a rate limit?

The router fails over to the next provider and tracks per-key usage so requests stay under each free-tier cap.

Can I point normal OpenAI-compatible clients at it?

Yes. It exposes an OpenAI-compatible /v1 endpoint for clients that use that API.

Do free self-hosted installs receive new models from the live feed?

Free installs receive a monthly snapshot, so a model reaches them about 30 days after it joins the live feed. Premium routers receive it the same day.

Answers sourced from github.com

Community

No community discussions collected yet.