POST /api/v1/browsing/async

Creates a browsing task and returns task_id immediately.

Request body (JSON):

Unknown JSON fields are rejected (400).

Retention

A task’s request (the task text or script) and its result (payload) are kept for ttl_days after the task is created — 7 days unless you say otherwise, 30 at most — and then deleted. Collect the result within that window; it is not recoverable afterwards.

The task itself is not deleted: status keeps answering with the status, timings and traffic figures, and once the result is gone it says so with "payload_expired": true instead of a payload. The day the result goes away is in payload_expires_on.

Templates

template picks how the task drives the browser. Omit it for the default. An unknown value is rejected with 400.

Response (200):

{ "task_id": "web:550e8400-e29b-41d4-a716-446655440000" }

curl -sS -X POST "https://llm.dat.ai/api/v1/browsing/async" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "task": "Open https://example.com and summarize the page",
    "filter": { "country_iso": "DE" },
    "screenshots": { "mode": "final_only", "full_page": true },
    "fanout": 1,
    "timeout_sec": 600
  }'

POST /api/v1/browsing/sync

Same request body as async. Blocks until the task completes or times out — 10 minutes unless timeout_sec says otherwise.

Response (200):

{
  "task_id": "web:...",
  "success": true,
  "payload": { "...": "..." },
  "execution_time_ms": 12345,
  "traffic_in": 184320,
  "traffic_out": 4096,
  "traffic_total": 188416
}

On failure, success is false and error contains a message. Timeout returns 504 with "Task timeout".

Traffic fields:

Traffic is reported only for a task that finished and produced a result. The three fields are omitted when the run failed or the traffic could not be measured.

GET /api/v1/browsing/status

Poll task status and result.

Query: task_id (required)

curl -sS "https://llm.dat.ai/api/v1/browsing/status?task_id=web:YOUR_TASK_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response (200):

{
  "task_id": "web:...",
  "status": "completed",
  "created_at": "2026-01-13T12:34:56Z",
  "assigned_at": "2026-01-13T12:34:57Z",
  "started_at": "2026-01-13T12:35:00Z",
  "completed_at": "2026-01-13T12:35:42Z",
  "payload_expires_on": "2026-01-20",
  "success": true,
  "payload": { "...": "..." },
  "execution_time_ms": 42000,
  "traffic_in": 184320,
  "traffic_out": 4096,
  "traffic_total": 188416
}

success, payload, and error are included only when status is completed.

payload_expires_on is the day after which the result is deleted (see Retention). Past that day the response carries "payload_expired": true and no payload; everything else stays.

GET /api/v1/browsing/screenshots/task_id/filename

Download a screenshot captured during a browsing task.

curl -sS "https://llm.dat.ai/api/v1/browsing/screenshots/web%3AYOUR_TASK_ID/step-001.png" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -o screenshot.png

• task_id and filename must be URL-encoded in the path
• Returns the image file on success (200)
• 403 if the task belongs to another account
• 404 if the task or screenshot does not exist

Screenshots are only available when screenshots was set in the create request. Files are kept for up to 5 days, then deleted automatically.

Errors

All browsing endpoints return { "error": "..." }.