# chatanywhere/GPT_API_free

免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！

Repository: https://github.com/chatanywhere/GPT_API_free
Canonical: https://ross.abutalabs.com/products/gpt_api_free
Homepage: https://api.chatanywhere.tech
License: MIT
License Family: permissive
Topics: api, chatgpt, claude, deepseek, gemini, gpt, grok, llm-agents
Last push: 2026-07-28T19:03:18+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 35, longevity 87
- inputs: {"age_days": 1228, "days_push": 36, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 41190, forks 2704 (observed 2026-08-28T04:12:08.483365+00:00)

## What it is
A hosted API forwarding/proxy service that provides free daily-quota access to GPT, DeepSeek, Claude, Gemini, and other major LLMs via a unified OpenAI-compatible endpoint. It offers China-optimized routing without a VPN and discounted paid tiers, with keys obtained by binding a GitHub account.

## Use cases
- call GPT or DeepSeek APIs for free from China without a VPN
- use an OpenAI-compatible endpoint for multiple LLM providers
- test LLM applications with a free daily quota
- integrate Claude or Gemini models via OpenAI protocol
- reduce latency for OpenAI API calls from mainland China
- get cheap paid access to Codex and Claude models

## When to choose
- you need OpenAI-compatible LLM access from mainland China without a proxy
- you want to experiment with multiple LLM providers through one unified API
- you need a free personal quota for non-commercial or educational projects

## When to avoid
- you need commercial or production-grade usage on the free tier (prohibited)
- you require strict data privacy guarantees beyond the upstream provider's policies
- you need high request volumes without rate limits on a free plan

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, api-framework, http-server
- domain: large-language-models, artificial-intelligence, apis, self-hosted
- platform: cloud, cross-platform
- tags: api-proxy, free-tier, openai-compatible, api-forwarding, china-access, deepseek, gpt, claude, gemini, web-server

## Member repositories
- chatanywhere/GPT_API_free (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.483365+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 2026-08-29T16:23:11.928951+00:00, confidence not recorded.
  - readme: https://github.com/chatanywhere/GPT_API_free (fetched 2026-08-28T04:12:08.483365+00:00, sha 231834126487)
  - homepage: https://api.chatanywhere.tech (fetched 2026-08-29T07:46:46.511343+00:00, sha 50c5ff76bafe)
- Data as of 2026-08-30T08:39:29.467469+00:00.