# APIParkLab/APIPark

Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.🦄云原生、超高性能 AI&API网关，LLM API 管理、分发系统、开放平台，支持所有AI API，不限于OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 请求和返回，API申请与审批，调用统计、负载均衡、多模型灾备。一键部署，开箱即用。

Repository: https://github.com/APIParkLab/APIPark
Canonical: https://ross.abutalabs.com/products/apipark
Homepage: https://apipark.com
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: api, apihub, gateway, api-gateway, ai, ai-gateway, llm-gateway, api-platform, api-portal, claude, developer-portal, openai, deepseek, qwen
Last push: 2026-05-06T05:55:24+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 81, release rhythm 54, longevity 53
- inputs: {"age_days": 752, "days_push": 119, "days_rel": 311, "gap_med": 9.5, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1803, forks 245 (observed 2026-08-28T04:05:38.203783+00:00)

## What it is
APIPark is an open-source, cloud-native AI gateway and API developer portal for managing, integrating, and deploying AI and REST APIs. It unifies access to 100+ LLM providers behind a standardized API format and adds API key management, usage monitoring, and team API sharing.

## Use cases
- manage multiple llm api keys behind one gateway
- switch between openai and claude without changing app code
- create apis from prompts and models
- share internal apis with a developer portal
- monitor ai api usage and costs
- load balance and failover across ai model providers
- self-host an ai api gateway

## When to choose
- you need a unified gateway for many LLM providers with standardized request/response formats
- you want API key management, approval workflows, and usage analytics for AI APIs
- you need a self-hosted, high-performance API gateway that also handles AI traffic
- you want to package prompts plus models into reusable REST APIs

## When to avoid
- you only call a single LLM provider directly from one application
- you need a fully managed SaaS gateway with no self-hosting overhead
- you need deep agent orchestration rather than API gateway features

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, llm-inference, monitoring, rate-limiting, auth, load-testing, analytics, logging
- domain: large-language-models, apis, developer-tools, self-hosted, backend
- platform: self-hosted, cloud
- tags: ai-gateway, llm-gateway, api-portal, developer-portal, api-management, prompt-templates, multi-model, openai, anthropic, gemini, deepseek, ai-agents, docker, linux

## Member repositories
- APIParkLab/APIPark (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:38.203783+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 2026-08-30T03:21:50.886906+00:00, confidence not recorded.
  - readme: https://github.com/APIParkLab/APIPark (fetched 2026-08-28T04:05:38.203783+00:00, sha 944b3a04bfc9)
  - homepage: https://apipark.com (fetched 2026-08-29T11:00:54.046908+00:00, sha 6c4c0ce07e22)
- Data as of 2026-08-30T08:39:29.467469+00:00.