
What is OpenPAI
OpenPAI (openp.ai) is an LLM API aggregation gateway built for developers and enterprises. Through a single, OpenAI-compatible interface you can seamlessly call all the major model providers — without registering separate accounts, managing multiple keys, or handling billing for each vendor.Unified interface
Fully compatible with the OpenAI SDK, with native support for the Claude
/v1/messages and Google Gemini formats.Hundreds of models
OpenAI, Anthropic, Google, DeepSeek, Qwen, Midjourney, Suno, Cohere, Jina and more, continuously added.
Pay as you go
Transparent token-based billing, lower rates on cache hits, with top-ups and quota management.
High availability
Weighted multi-channel routing + automatic retries, so a single upstream outage won’t break your service.
Quickstart
Just three steps to send your first request in five minutes:Sign up and get an API key
Register at openp.ai, then create an API key starting with
sk- on the Tokens page of the console.Pick a model
Browse available models on the Models page of the console, or see the Models overview to choose the right one.
Explore the docs
Quickstart guide
The full flow from sign-up to your first request.
Supported models
See every available model, its billing multiplier, and context window.
API reference
Request/response fields, error codes and examples for every endpoint.
Client integrations
Connect tools like Cherry Studio, LobeChat, Cursor and Dify.
Three native protocols
Beyond full OpenAI compatibility, OpenPAI also exposes native Claude and Gemini protocol endpoints, so you can switch upstreams without rewriting your application:OpenAI-compatible
POST /v1/chat/completions
Authorization: Bearer sk-...Claude Messages
POST /v1/messages
x-api-key: sk-...Gemini native
POST /v1beta/models/{model}:generateContent
x-goog-api-key: sk-...Need help?
FAQ
Answers to common questions about top-ups, models, billing and errors.
