Back to list

FreeLLMAPI

87 providers' free tiers behind one OpenAI-compatible endpoint — one key, smart routing, automatic failover.

余时安
Author
@余时安
Project ShowcaseDeveloper ToolsOnlineclaude-code
0
0

Project intro

FreeLLMAPI puts the free tiers of 87 AI providers behind a single OpenAI-compatible endpoint. Add your own provider keys once, and every app and coding agent you already use talks to one address instead of eighty-seven.

The router picks the best available model for each request, falls over to the next provider when one hits a rate limit, and tracks per-key usage so you stay under every free-tier cap. It covers chat, completions, images, video, speech, and embeddings, and speaks the Anthropic Messages format too, so Claude Code and the Gemini CLI run against the same pool. A Fusion mode asks several free models at once and has a judge model blend their drafts into one answer.

Stacked together, the free tiers add up to about 10.1 billion tokens a month across 736 model families and 1,313 endpoints, according to the project. More than 54,000 developers starred it, with over 7,600 forks, and version 0.16.34 shipped on 17 November 2026. It is MIT licensed, runs on Node 20 and up, and ships a desktop app, a dashboard, and a playground.

Two honest limits, stated by the project itself: free tiers are for trying things out, not for production — no frontier models, no SLA, and the smartest models run thin late in the day as daily caps run out. The paid catalog feed costs $19 a year and gets new models the same day; free installs wait 30 days. Each provider's own terms still apply to traffic routed through it.

Actions

Visit project URL

Tech stack

Project info

Project category
Developer Tools
Project status
Online
Collaboration intent
None

Comments (0)

ME
0/1000
Loading comments...