API Documentation

OpenAI-compatible endpoints provided by autoclawpi

Base URL

http://localhost:8787
Replace localhost:8787 with your server address.

Available Models

auto auto-fast glm-5-turbo glm-5.3 glm-5.3-flash deepseek-v4-pro deepseek-v4-flash

Endpoints

GET /v1/models

List available models. No authentication required.

curl http://localhost:8787/v1/models
POST /v1/chat/completions

Send a chat completion request. OpenAI-compatible format.

curl -X POST http://localhost:8787/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-5-turbo","messages":[{"role":"user","content":"halo"}]}'

Parameters

Parameter Type Description
model string Model ID (e.g., glm-5-turbo, glm-5.3, deepseek-v4-pro)
messages array Chat messages [{role, content}]
stream bool Enable SSE streaming (default: false)
max_tokens int Maximum tokens in response

Authentication

If an API key is configured in Settings, include it as a header:

curl -H "Authorization: Bearer sk-your-key-here" http://localhost:8787/v1/models