FreeLLMAPI
Self-hosted gateway that pools free LLM API tiers behind one endpoint
What it is
FreeLLMAPI gathers the free tiers of dozens of model providers, along with any self-supplied endpoint that speaks the OpenAI format, and serves them through a single /v1 API. It stores provider keys encrypted, routes each request to an available model, fails over when a provider hits its rate limit, and tracks per-key usage against free-tier caps. Hobbyists and tinkerers run it locally or in Docker to point coding agents and OpenAI client libraries at free inference for personal experiments. Desktop and mobile apps are also available.