Skip to Content

HTTP API for LLM inference, browser automation, and speech-to-text on dat.ai’s distributed network of edge devices.

Base URL: https://llm.dat.ai

Getting Started

The dat.ai HTTP API covers inference (LLM chat), browser automation, and audio transcription. All endpoints require a Bearer API key.

API groups

GroupEndpointsDescription
InferencePOST /v1/chat/completions, POST /api/chatOpenAI- and Ollama-compatible chat
BrowsingPOST /api/v1/browsing/*, GET .../status, GET .../screenshots/...Browser automation on real devices
TranscribingPOST /api/transcribe/*, GET .../statusSpeech-to-text (Whisper)

Quick start

Create an API key in the dashboard , then run:

curl -sS -X POST "https://llm.dat.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3:1.7b",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

Task lifecycle

Browsing and transcribing use the same async pattern:

  1. Create — POST .../async or POST .../sync → receive task_id
  2. Poll — GET .../status?task_id=... until status is completed or failed
  3. Result — when completed, the status response includes success, payload, and optional error

Sync endpoints skip step 2 and block until the result is ready (with a server-side timeout).

Next steps

Authentication