Skip to main content

​
API Reference

The WithGiga API allows you to programmatically create, manage, and interact with AI-driven cloud computers. The API is hosted at: 
https://api.withgiga.ai

​
Core Concepts

The API is built around three main concepts:
  1. Sessions (Threads): A session represents a conversational thread with an AI agent. It holds the history of messages and context.
  2. Runs: A run is an execution of an AI agent within a session. When you start a run, the agent processes the prompt and interacts with the computer.
  3. Sandboxes (Computers): A sandbox is the actual virtual machine where the AI agent operates. The sandbox lifecycle is tied to the run.

​
Standard Error Format

All non-2xx responses follow the same envelope: 
{
  "error": {
    "code": "RESOURCE_NOT_FOUND|INVALID_REQUEST|UNAUTHORIZED|RATE_LIMITED|INTERNAL_ERROR",
    "message": "human readable summary",
    "hint": "optional remediation guidance",
    "requestId": "uuid for support"
  }
}

​
Rate Limits & Timeouts

  • Default limit is 60 requests/min per API key. Responses include X-RateLimit-Remaining and Retry-After when throttled (HTTP 429).
  • Long running run-creation calls keep the HTTP connection open for up to 15s; sandbox work continues asynchronously.
  • Web clients should back off exponentially on 429/5xx responses.