Let AI Run API Documentation

This page is a local Markdown/MDX render. Create your token first in the dashboard before integrating.

1. Overview

• Website: https://api.letai.run/
• API Base URL: https://api.letai.run/v1
• CN2 Accelerated API Base URL (Mainland China): https://cn-api.letai.run/v1
• Protocol: OpenAI-compatible Chat Completions / Embeddings
• Auth: Authorization: Bearer <YOUR_TOKEN>
• Response format: application/json

2. Quickstart

curl --request POST \
  --url https://api.letai.run/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer YOUR_TOKEN' \
  --data '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Introduce Let AI Run in one sentence."}
    ],
    "stream": false
  }'

For accelerated access in Mainland China, replace the request URL with https://cn-api.letai.run/v1/chat/completions.

3. Common Headers

4. Error Codes

5. Production Checklist

1. Attach business request IDs on every call.
2. Apply exponential backoff for 429 and 5xx.
3. Keep secrets on the server side only.
4. Add timeout and circuit breaker policies on the caller side.

6. Internal Links

• Home: /
• Welfare: /welfare
• Dashboard: /dashboard
• Platform External Open API (server-side):