Skip to main content
Use Extract Jobs v2 to extract structured data asynchronously. Instead of waiting for a single request to finish, you create a job, receive a job_id immediately, and retrieve the result when the job completes. Use Extract Jobs for long-running extractions, such as extracting from long documents or with large, complex schemas.

​
Endpoints

The request fields are the same as the synchronous Extract API. See Extract Input Parameters. Extract Jobs uses these endpoints:
MethodEndpointPurpose
POST/v2/extract/jobsCreate an extract job.
GET/v2/extract/jobs/{job_id}Get the status and result of a job.

​
Workflow

  1. Build your extraction schema. See Extraction Schema (JSON).
  2. Submit the Markdown and schema to POST /v2/extract/jobs.
  3. Get the job_id from the response.
  4. Poll GET /v2/extract/jobs/{job_id} until status is completed.
  5. Read the extracted fields from the job’s result. See Extract API Response.

​
Create a Job

Send the same fields you would send to the synchronous endpoint. Replace YOUR_API_KEY with your API key and parse-output.md with the path to your Markdown file. 
curl -X POST 'https://api.ade.landing.ai/v2/extract/jobs' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'markdown=@parse-output.md' \
  -F 'schema={"type":"object","properties":{"revenue":{"type":"string","description":"Q1 2024 revenue"}}}'
The request returns a 202 response with the job_id and the initial status: 
{
  "job_id": "d3kpfw9bf0ez7e501an5qqe8z",
  "status": "pending",
  "created_at": 1781819747
}

​
Choose a Service Tier

Set the optional service_tier form field to control the job’s turnaround time and credit consumption. If you omit service_tier, the job runs on the standard tier. For credit consumption by tier, see Credit Consumption.
TierBehavior
standardConsumes half the credits of the priority tier, with a slower turnaround. Best for cost-sensitive or non-urgent workloads.
priorityConsumes credits at the full rate, the same as synchronous extraction, with a faster turnaround. Best for time-sensitive jobs.
Set the tier. Include the service_tier field in your create-job request: 
curl -X POST 'https://api.ade.landing.ai/v2/extract/jobs' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'markdown=@parse-output.md' \
  -F 'schema={"type":"object","properties":{"revenue":{"type":"string","description":"Q1 2024 revenue"}}}' \
  -F 'service_tier=priority'

​
Get a Job

Poll the job with its job_id: 
curl 'https://api.ade.landing.ai/v2/extract/jobs/JOB_ID' \
  -H 'Authorization: Bearer YOUR_API_KEY'
The response includes the job status and, once the job finishes, the result:
FieldDescription
job_idThe unique identifier for the job.
statusThe current state of the job. See Job Statuses.
created_atWhen the job was created.
completed_atWhen the job finished. Present once the job reaches a final state.
progressHow far the job has progressed, from 0 to 1. Present while the job is processing.
resultThe extraction result, present when status is completed. This object has the same shape as a synchronous response. See Extract API Response.
errorPresent when status is failed. Contains a code and a message.

​
Job Statuses

StatusDescription
pendingThe job is accepted and queued, but has not started.
processingThe job is running.
completedThe job finished. Read the extraction from the result field.
failedThe job did not finish. See the error field for details.

​
Rate Limits

Extract Jobs submissions are always accepted (HTTP 202) and never return a rate-limit error; jobs are paced internally instead. There is no input size cap. See Rate Limits.