Reference

Job

Async AI job objects

The object that AI endpoints create and that you poll or stream. See Async AI jobs for the endpoints that operate on it.

JSON

1{
2  "job_id": "job_8f3a2b...",
3  "type": "discover",
4  "status": "running",
5  "progress": {
6    "message": "Reading datasheet — Electrical Characteristics",
7    "fraction": 0.4,
8    "updated_at": "2026-06-01T17:05:12Z"
9  },
10  "created_at": "2026-06-01T17:04:00Z",
11  "completed_at": null,
12  "stream_url": "https://api.zenode.ai/v1/jobs/job_8f3a2b.../stream",
13  "usage": {
14    "input_tokens": 18234,
15    "output_tokens": 2451,
16    "total_tokens": 20685
17  },
18  "result": null,
19  "error": null,
20  "request_id": "req_2c19..."
21}

Field	Type	Notes
`job_id`	string	Opaque job identifier
`type`	string	`discover` \| `deep_dive` — determines the shape of `result`
`status`	string	`queued` \| `running` \| `completed` \| `failed` \| `cancelled`
`progress`	object \| null	Coarse progress — `{ message, fraction, updated_at }`
`created_at`	string	ISO-8601
`completed_at`	string \| null	ISO-8601; set on a terminal status
`stream_url`	string	Absolute URL of the SSE progress stream
`usage`	object \| null	LLM tokens consumed — `{ input_tokens, output_tokens, total_tokens }`
`result`	object \| null	Typed result once `completed`; `null` until then
`error`	`Error` \| null	Populated when `status` is `failed`

The result shape depends on type: a DiscoverResult (summary + DiscoverPick[]) for discover, or a DeepDiveResult (answers of Answer) for deep_dive.

JobSummary

The compact list row returned by GET /v1/jobs — a Job without the heavy result (job_id, type, status, progress, created_at, completed_at, error). Fetch the job by id for the full payload.

Used by: Async AI jobs.

PreviousCategory Next Answer