API Reference
Use the Aqta API by sending requests to our gateway. Same request shape as OpenAI, we add cost tracking, safety enforcement, and audit data to every response.
Base URL
- Production:
https://api.aqta.ai - Local dev:
http://localhost:8000
All gateway endpoints use the /v1/ prefix (e.g. POST /v1/chat/completions).
Authentication
Include your API key in every request:
bashAuthorization: Bearer sk-aqta-YOUR_KEY_HERE
Get your API key from the dashboard: Settings → API Keys.
See Authentication for setup details and security best practices.
Main endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST | /v1/chat/completions | Chat completions (OpenAI-compatible) |
| GET | /v1/models | List available models |
Supports streaming and multiple providers (OpenAI, Anthropic, Google, Perplexity). See API Endpoints for request/response details.
Response shape
Responses match the OpenAI format, with an extra aqta object:
trace_id, request identifier for support and audit logscost_eur, cost in euros for this requestprovider, which provider served the requeststatus,passed,suppressed, orblocked
Sign in to view the full response schema and all dashboard endpoints.
Quick example (cURL)
bashcurl https://api.aqta.ai/v1/chat/completions \ -H "Authorization: Bearer sk-aqta-YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4o", "messages": [{"role": "user", "content": "Hello!"}] }'