API3 - Universal AI API

API Documentation

One API key, all Chinese LLMs. Use standard OpenAI or Anthropic SDKs.

Quick Start

After creating an API key, call any supported model via OpenAI or Anthropic compatible endpoints.

Base URL

https://api3.co

Authentication

Authorization: Bearer YOUR_API_KEY

x-api-key: YOUR_API_KEY

OpenAI Compatible

/v1/chat/completions

Works with the standard openai SDK. Just change base_url.

curl

Python

Node.js

curl https://api3.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "ds/deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Anthropic Compatible

/v1/messages

Works with the standard @anthropic-ai/sdk. Just change base_url.

curl

Python

Node.js

curl https://api3.co/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "ds/deepseek-chat",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Available Models

All models accessible with a single API key. Pricing per 1M tokens (USD).

Model ID	Name	Provider	Input /1M	Output /1M	Formats

Rate Limits

60 requests per minute per API key. Contact us for higher limits.

Error Codes

Status	Meaning
`200`	Success
`400`	Bad Request
`401`	Unauthorized — Invalid API key
`429`	Rate limit exceeded
`500`	Internal Server Error
`502`	Bad Gateway — Upstream provider error