Extract

Get Extract Job

Get a single extraction job by ID.

Returns the job status and results when complete. Use expand=configuration to include the full configuration used, and expand=extract_metadata for per-field metadata.

get/api/v2/extract/{job_id}

Path parameters

job_idstring required

Query parameters

expandstring[]

Additional fields to include: configuration, extract_metadata

project_idstring uuid nullable

organization_idstring uuid nullable

Cookies

sessionstring nullable

Response

Successful Response

file_inputstring required

File ID or parse job ID that was extracted

idstring required

Unique job identifier (job_id)

project_idstring required

Project this job belongs to

configuration_idstring nullable

Saved extract configuration ID used for this job, if any

statusstring required

Current job status.

PENDING — queued, not yet started
RUNNING — actively processing
COMPLETED — finished successfully
FAILED — terminated with an error
CANCELLED — cancelled by user

error_messagestring nullable

Error details when status is FAILED

created_atstring date-time required

Creation timestamp

updated_atstring date-time required

Last update timestamp

Example response

{
  "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "id": "ext-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "configuration_id": "cfg-11111111-2222-3333-4444-555555555555",
  "configuration": {
    "target_pages": "1,3,5-7",
    "max_pages": 10,
    "tier": "cost_effective",
    "version": "latest",
    "extraction_target": "per_doc",
    "system_prompt": "Extract all monetary values in USD. If a currency is not specified, assume USD.",
    "parse_tier": "fast",
    "parse_config_id": "cfg-11111111-2222-3333-4444-555555555555"
  },
  "status": "COMPLETED",
  "extract_metadata": {
    "field_metadata": {
      "document_metadata": {
        "items": [
          {
            "amount": {
              "citation": [
                {
                  "matching_text": "$10.00",
                  "page": 1
                }
              ],
              "confidence": 1
            },
            "description": {
              "citation": [
                {
                  "matching_text": "$10/month",
                  "page": 1
                }
              ],
              "confidence": 0.998
            }
          }
        ],
        "total": {
          "citation": [
            {
              "matching_text": "$10.00",
              "page": 1
            }
          ],
          "confidence": 1
        },
        "vendor": {
          "citation": [
            {
              "matching_text": "Noisebridge",
              "page": 1
            }
          ],
          "confidence": 1,
          "extraction_confidence": 1,
          "parsing_confidence": 1
        }
      }
    }
  }
}

Changes

Changed in 8 of the 33 revisions of this API.147

Jun 9, 2026b17341164de92See the full diff
- ○
  added the optional property detail/items/ctx to the response with the 422 status
  response-optional-property-added
- ○
  added the optional property detail/items/input to the response with the 422 status
  response-optional-property-added
This revision also has 5 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
Jun 4, 2026d40e17e17bd111See the full diff
- ●
  removed the optional property configuration/anyOf[subschema #1: ExtractConfiguration]/extract_version from the response with the 200 status
  response-optional-property-removed
- ○
  added the optional property configuration/anyOf[subschema #1: ExtractConfiguration]/version to the response with the 200 status
  response-optional-property-added
May 27, 20261c29e1491a382See the full diff
- ●
  removed the optional property metadata/anyOf[subschema #1: ExtractV2JobMetadata]/usage/anyOf[subschema #1: ExtractJobUsage]/num_document_tokens from the response with the 200 status
  response-optional-property-removed
- ●
  removed the optional property metadata/anyOf[subschema #1: ExtractV2JobMetadata]/usage/anyOf[subschema #1: ExtractJobUsage]/num_output_tokens from the response with the 200 status
  response-optional-property-removed
This revision also has 2 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
May 16, 2026c317ed7c691a1See the full diff
- ○
  api tag LlamaExtract removed
  api-tag-removed
May 14, 20261bbc901f8c0d1See the full diff
- ○
  api tag LlamaExtract added
  api-tag-added
This revision also has 6 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
Apr 29, 2026beb65a9b42eb1See the full diff
- ○
  api tag LlamaExtract removed
  api-tag-removed
Apr 8, 202601ac7197eb4a1See the full diff
- ●
  removed the optional property configuration/anyOf[subschema #1: ExtractConfiguration]/lang from the response with the 200 status
  response-optional-property-removed
This revision also has 4 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
Apr 1, 20267e0726654d2211See the full diff
- ▲
  removed the required property document_input_value from the response with the 200 status
  response-required-property-removed
- ○
  added the required property file_input to the response with the 200 status
  response-required-property-added

Full history