Independent research for creator workflowsOfficial sources & verified limits. How we review

AI Gateway tool profile

FreeLLMAPI

An open-source, self-hosted gateway that pools the free API tiers of 34 LLM providers behind one OpenAI-compatible endpoint, with a router that fails over to the next healthy key when a provider is rate-limited.

Official sourcesIndependent researchPricing notesHow we review
Best for
Developers who want to experiment or run personal coding agents on free provider tiers through a single endpoint, without wiring each provider's key and rate limit by hand.
Starting point
Free and open source (MIT), self-hosted; no subscription needed.
Free plan
Yes — The gateway is free and open source (MIT) and self-hosted.
Key limitation
Built for personal use: the project says not to expose the proxy publicly, and each provider's Terms of Service still applies.

Choose it if

Developers who want to experiment or run personal coding agents on free provider tiers through a single endpoint, without wiring each provider's key and rate limit by hand.

Avoid it if

  • Built for personal use: the project says not to expose the proxy publicly, and each provider's Terms of Service still applies.
  • Free tiers only: no frontier models, variable latency, and no SLA; capability drops late in the day as popular models hit quotas (reset at UTC midnight).
  • Self-hosted: you run and secure it (Docker, Docker Compose, Node 20+, or the desktop app).

Free-plan suitability

The gateway is free and open source (MIT) and self-hosted. You supply your own free-tier keys from the supported providers; Premium ($19/year or $49 lifetime) only adds the live model catalog.

Where it fits

Developers who want to experiment or run personal coding agents on free provider tiers through a single endpoint, without wiring each provider's key and rate limit by hand.

DevelopersAI tool usersIndie hackersfree LLM API accessmulti-provider failovercoding-agent backendsfree-tier quota pooling

Browse all AI Gateway tools in the catalog

Pricing note

Starting point
Free and open source (MIT), self-hosted; no subscription needed.
Free plan
Yes — The gateway is free and open source (MIT) and self-hosted.

Free and open source (MIT), self-hosted; no subscription needed. Optional Premium adds the live model catalog: $19/year or $49 once (lifetime), tax included, per freellmapi.co. Free installs receive monthly catalog snapshots. You still bring your own provider keys, and each provider's free-tier limits and Terms of Service apply.

Verify the current plan, credits, output limits, and commercial terms before purchasing.

Estimate your gateway cost

Is it legit?

Who is behind FreeLLMAPI, where it is based, and what is publicly known about its funding. Company details change — verify on the official site before committing.

Company
Neu Software LLC (open source, tashfeenahmed/freellmapi)

Free plan details

The gateway is free and open source (MIT) and self-hosted. You supply your own free-tier keys from the supported providers; Premium ($19/year or $49 lifetime) only adds the live model catalog.

Trade-offs to check

  • Built for personal use: the project says not to expose the proxy publicly, and each provider's Terms of Service still applies.
  • Free tiers only: no frontier models, variable latency, and no SLA; capability drops late in the day as popular models hit quotas (reset at UTC midnight).
  • Self-hosted: you run and secure it (Docker, Docker Compose, Node 20+, or the desktop app).
  • Free installs get monthly catalog snapshots with a delay; the live catalog is a paid Premium feature.
  • Provider, model, and token counts are project claims that change quickly; recheck the repository before relying on them.

What FreeLLMAPI does

  • Aggregates free API tiers from 34 providers (including Google, Groq, Cerebras, Mistral, OpenRouter, Cloudflare, Cohere, NVIDIA and Hugging Face) behind one OpenAI-compatible /v1 endpoint
  • Router picks the highest-priority healthy model under all its rate limits; on a 429 or 5xx it cools that key down and retries the next model in the chain
  • Provider keys are encrypted at rest with AES-256-GCM in SQLite and decrypted in memory per request; apps use one bearer token
  • Project claims 605 models and about 7.4 billion free tokens per month when every supported account is configured (freellmapi.co)
  • Setup generators for Claude Code, Codex CLI, Cline, Continue, Aider and 15+ other tools; one-line Docker install, Docker Compose, and Windows/macOS desktop apps
  • MIT-licensed with a very large GitHub following (about 29.7k stars at the time of checking)

Evaluation guide

Step-by-step evaluation guides for FreeLLMAPI — workflow fit, pricing, rights, and a same-input test before paying.

Compare FreeLLMAPI with alternatives

Side-by-side pages that weigh FreeLLMAPI against overlapping tools on the same five fields.

Official sources

These links are retained beside the catalog record so changing details can be rechecked.