Skip to main content
Astrolabe Cloud provides a hosted gateway at: 
https://api.astrolabe.run/v1
The gateway is OpenAI-compatible for the public inference surface and adds Cloud-specific routing, billing, stack policy, and observability.

​
Public endpoints

  • GET /health
  • GET /ready
  • GET /v1/models
  • GET /v1/lanes
  • POST /v1/responses
  • POST /v1/chat/completions

​
Authentication

Create API keys in the Cloud app. Send a key with either: 
Authorization: Bearer $ASTROLABE_CLOUD_KEY
or: 
x-api-key: $ASTROLABE_CLOUD_KEY
Keys belong to a workspace and can be revoked from the dashboard.

​
Gateway behavior

The gateway:
  • rejects missing or invalid keys
  • rejects suspended workspaces or revoked keys
  • enforces key-level rate limits
  • requires sufficient prepaid balance before routing
  • resolves stack policy before provider calls
  • records route traces and model-call records
  • returns Cloud request ids and routing headers

​
Compatibility

Use POST /v1/responses for new integrations. Use POST /v1/chat/completions when an existing client only supports Chat Completions. Both endpoints use the same stack, billing, and routing runtime.