Radar / AI infrastructure / FreeLLMAPI
FreeLLMAPI: one free endpoint across 87 LLM providers
A self-hosted router that puts 87 free LLM providers and 1,313 free model endpoints behind one OpenAI-compatible /v1 endpoint, with smart routing, failover and encrypted keys.
Why it matters
10.1 billion free tokens a month of headroom in one self-hosted box — the practical way to run Claude Code and OpenCode entirely on free tiers.
What you could build with it
An indie developer could build a zero-cost coding-agent setup for students: point Claude Code at a self-hosted FreeLLMAPI router that fails over across free tiers, so a classroom of learners gets a working agent without any paid API key.
Does it hold up?
Real writeups show it works as a self-hosted router for Claude Code and OpenCode with failover across free tiers; the honest limits are free-tier quotas, no frontier models, and a catalog that updates monthly on the free install.
Built with FreeLLMAPI
- How To Access Free LLM Models Using FreeLLMAPIf22labs · Tested the router with 100 requests and built a small Gradio tester to check behaviour under load.
- FreeLLMAPI Docker Setup for OpenCode and Claude Codecomputingforgeeks · Ran it on a lab box pointed at OpenCode and Claude Code, measuring latency, 429s and failover.
Learn more
First spotted on github: source.
More AI infrastructure
vLLM v0.34.0: extensible KV cache by default, Model Runner V2 only, and 10 new modelsThe open inference engine's latest release spans 1,061 commits from 412 contributors, adds 10 models including Mistral…infra · JEV 0.86llama.cpp v1.0.0: the local-AI engine's first stable releasellama.cpp and ggml hit v1.0.0, promising semantic versioning so breaking C API changes only arrive with major bumps.infra · JEV 0.84Graphify: turn any codebase into a knowledge graph your agent queriesA CLI plus agent skill that parses code with tree-sitter into a queryable knowledge graph of functions, classes…infra · JEV 0.77DeepSeek App API: the whole consumer app, now as developer APIsDeepSeek opened its app's capabilities through its API: web search, file parsing, URL reading, safety checks, voice…infra · JEV 0.67InferSSD: run 800B-class MoE models from an SSD on consumer hardwareWiCi's open-source inference engine streams MoE expert weights from NVMe so models larger than RAM or VRAM can run…infra · JEV 0.64TrnRT: an open LLM inference engine for AWS Trainiuminfra · JEV 0.63
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.