# tashfeenahmed/freellmapi

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

Repository: https://github.com/tashfeenahmed/freellmapi
Canonical: https://ross.abutalabs.com/products/freellmapi
Homepage: https://freellmapi.co
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T09:06:41+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 9
- inputs: {"age_days": 134, "days_push": 7, "days_rel": 7, "gap_med": 1, "n_releases_24m": 24}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 20682, forks 2973 (observed 2026-08-28T04:11:30.215442+00:00)

## What it is
FreeLLMAPI is an open-source, self-hosted LLM gateway that aggregates free tiers from 34 providers (600+ free model endpoints) behind a single OpenAI-compatible /v1 endpoint. It provides smart routing, automatic failover on rate limits, per-key quota tracking, and encrypted key storage, with an optional paid live model-catalog feed.

## Use cases
- use free LLM APIs without juggling multiple provider keys
- route coding agents like Claude Code, Codex, Aider, or Cline across free model tiers
- automatically fail over to another provider when one is rate-limited
- track usage to stay under each provider's free-tier caps
- self-host an OpenAI-compatible gateway with keys kept local
- experiment with frontier models like DeepSeek, Qwen, Gemini Flash, and Llama for free

## When to choose
- you want one OpenAI-compatible endpoint over many providers' free tiers
- you need automatic failover and quota tracking across free LLM providers
- you prefer self-hosting so provider keys stay on your machine
- you want to point existing OpenAI SDK-based tools or coding agents at free models

## When to avoid
- you need production-grade SLAs or paid-tier reliability and throughput
- you need the very latest model catalog without the 30-day free-tier delay and won't pay for Premium
- you require providers or models not present in the free-tier catalog
- your usage exceeds free-tier token caps and you'd be better served by a paid API directly

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, api-framework, http-server, middleware, configuration-management, developer-tools
- domain: large-language-models, artificial-intelligence, developer-tools, self-hosted, apis
- platform: self-hosted, cross-platform, cli
- tags: openai-compatible, llm-router, free-tier, api-gateway, failover, rate-limiting, model-catalog, coding-agents, proxy, docker, nodejs, web-server

## Member repositories
- tashfeenahmed/freellmapi (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:30.215442+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:58:34.073086+00:00, confidence not recorded.
  - readme: https://github.com/tashfeenahmed/freellmapi (fetched 2026-08-28T04:11:30.215442+00:00, sha cb29e48a6f0f)
  - homepage: https://freellmapi.co (fetched 2026-08-29T07:57:36.407083+00:00, sha 6f09702eac97)
  - site_page: https://freellmapi.co/about (fetched 2026-08-29T07:57:36.418613+00:00, sha 792315e06110)
  - registry_npm: https://registry.npmjs.org/freellmapi (fetched 2026-08-29T07:57:36.422092+00:00, sha 854d964dfafd)
  - site_page: https://freellmapi.co/pricing (fetched 2026-08-29T07:57:36.416363+00:00, sha e9983e0ea2d5)
  - site_page: https://freellmapi.co/faq (fetched 2026-08-29T07:57:36.420437+00:00, sha a7750b97e10a)
- Data as of 2026-08-30T08:39:29.467469+00:00.