## Cancel Extract Job

**post** `/api/v2/extract/{job_id}/cancel`

Cancel a running extraction job.

Stops processing and marks the job as CANCELLED. Returns the updated job. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled.

### Path Parameters

- `job_id: string`

### Query Parameters

- `organization_id: optional string`

- `project_id: optional string`

### Cookie Parameters

- `session: optional string`

### Returns

- `ExtractV2Job object { id, created_at, file_input, 10 more }`

  An extraction job.

  - `id: string`

    Unique job identifier (job_id)

  - `created_at: string`

    Creation timestamp

  - `file_input: string`

    File ID or parse job ID that was extracted

  - `project_id: string`

    Project this job belongs to

  - `status: string`

    Current job status.

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

  - `updated_at: string`

    Last update timestamp

  - `configuration: optional ExtractConfiguration`

    Extract configuration combining parse and extract settings.

    - `data_schema: map[map[unknown] or array of unknown or string or 2 more]`

      JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.

      - `map[unknown]`

      - `array of unknown`

      - `string`

      - `number`

      - `boolean`

    - `cite_sources: optional boolean`

      Include citations in results. Returned under `extract_metadata` (auto-included when set). Text-level on `turbo` (no bounding boxes).

    - `confidence_scores: optional boolean`

      Include confidence scores in results. Returned under `extract_metadata` (auto-included when set).

    - `disable_cache: optional boolean`

      Disable reuse and storage of Extract results

    - `extraction_target: optional "per_doc" or "per_page" or "per_table_row"`

      Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row

      - `"per_doc"`

      - `"per_page"`

      - `"per_table_row"`

    - `max_pages: optional number`

      Maximum number of pages to process. Omit for no limit.

    - `parse_config_id: optional string`

      Saved parse configuration ID to control how the document is parsed before extraction. Turbo extract does not support parse configuration or produce a parse output; use another tier if your workflow requires parsed text.

    - `parse_tier: optional "agentic" or "agentic_plus" or "cost_effective" or "fast"`

      Parse tier to use before extraction. Defaults to the extract tier if not specified. Turbo extract does not support parse configuration or produce a parse output; use another tier if your workflow requires parsed text.

      - `"agentic"`

      - `"agentic_plus"`

      - `"cost_effective"`

      - `"fast"`

    - `sheet_names: optional array of string`

      Optional worksheet names to extract when spreadsheet_mode is on. Overrides target_pages for spreadsheets; omit to extract every sheet. Names are matched exactly (case-sensitive) — pass them as a list, e.g. ["Sheet 1", "My Sheet"].

    - `spreadsheet_mode: optional boolean`

      Beta. When true, extract structured data directly from a spreadsheet workbook (.xlsx/.xls/.csv) — the agent reads cells straight from the workbook instead of the standard document path. Off by default (spreadsheets keep the standard path). Requires the agentic_plus tier. Billed on the standard per-page extract rate, against a page count derived from workbook size. Citations and confidence scores are not available in this mode.

    - `system_prompt: optional string`

      Custom system prompt to guide extraction behavior

    - `target_pages: optional string`

      Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

    - `tier: optional "agentic" or "agentic_plus" or "cost_effective" or "turbo"`

      Extract tier: cost_effective (5 credits/page), agentic (15 credits/page), agentic_plus (50 credits/page), or turbo (35 credits/page)

      - `"agentic"`

      - `"agentic_plus"`

      - `"cost_effective"`

      - `"turbo"`

    - `version: optional string`

      Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. Job responses always report the concrete resolved version the job runs, fixed at job creation; saved configurations keep the value as provided.

  - `configuration_id: optional string`

    Saved extract configuration ID used for this job, if any

  - `error_message: optional string`

    Error details when status is FAILED

  - `extract_metadata: optional ExtractJobMetadata`

    Extraction metadata.

    - `field_metadata: optional ExtractedFieldMetadata`

      Metadata for extracted fields including document, page, and row level info.

      - `document_metadata: optional map[map[unknown] or array of unknown or string or 2 more]`

        Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively.

        - `map[unknown]`

        - `array of unknown`

        - `string`

        - `number`

        - `boolean`

      - `page_metadata: optional array of map[map[unknown] or array of unknown or string or 2 more]`

        Per-page metadata when extraction_target is per_page

        - `map[unknown]`

        - `array of unknown`

        - `string`

        - `number`

        - `boolean`

      - `row_metadata: optional array of map[map[unknown] or array of unknown or string or 2 more]`

        Per-row metadata when extraction_target is per_table_row

        - `map[unknown]`

        - `array of unknown`

        - `string`

        - `number`

        - `boolean`

    - `parse_job_id: optional string`

      Reference to the ParseJob ID used for parsing

    - `parse_tier: optional string`

      Parse tier used for parsing the document

  - `extract_result: optional map[map[unknown] or array of unknown or string or 2 more] or array of map[map[unknown] or array of unknown or string or 2 more]`

    Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row.

    - `map[map[unknown] or array of unknown or string or 2 more]`

      - `map[unknown]`

      - `array of unknown`

      - `string`

      - `number`

      - `boolean`

    - `array of map[map[unknown] or array of unknown or string or 2 more]`

      - `map[unknown]`

      - `array of unknown`

      - `string`

      - `number`

      - `boolean`

  - `metadata: optional object { usage }`

    Job-level metadata.

    - `usage: optional ExtractJobUsage`

      Extraction usage metrics.

      - `num_pages_billed: optional number`

        Number of effective pages billed

      - `num_pages_extracted: optional number`

        Number of pages extracted

  - `usage: optional object { credits, extract_credits, parse_credits }`

    Usage recorded against an extract job.

    A parse job can back several extract jobs, so each of them reports that
    same parse cost in its total.

    - `credits: optional number`

      Total credits billed against this job. Null until billing has recorded it.

    - `extract_credits: optional number`

      Credits billed for the extraction itself

    - `parse_credits: optional number`

      Credits billed against the parse job backing this extract job

### Example

```http
curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/cancel \
    -X POST \
    -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"
```

#### Response

```json
{
  "id": "ext-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "created_at": "2019-12-27T18:11:19.117Z",
  "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "status": "COMPLETED",
  "updated_at": "2019-12-27T18:11:19.117Z",
  "configuration": {
    "data_schema": {
      "foo": {
        "foo": "bar"
      }
    },
    "cite_sources": true,
    "confidence_scores": true,
    "disable_cache": true,
    "extraction_target": "per_doc",
    "max_pages": 10,
    "parse_config_id": "cfg-11111111-2222-3333-4444-555555555555",
    "parse_tier": "fast",
    "sheet_names": [
      "Sheet 1",
      "Q4 Summary"
    ],
    "spreadsheet_mode": true,
    "system_prompt": "Extract all monetary values in USD. If a currency is not specified, assume USD.",
    "target_pages": "1,3,5-7",
    "tier": "cost_effective",
    "version": "latest"
  },
  "configuration_id": "cfg-11111111-2222-3333-4444-555555555555",
  "error_message": "error_message",
  "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": "bar",
          "confidence": "bar"
        },
        "vendor": {
          "citation": "bar",
          "confidence": "bar",
          "extraction_confidence": "bar",
          "parsing_confidence": "bar"
        }
      },
      "page_metadata": [
        {
          "foo": {
            "foo": "bar"
          }
        }
      ],
      "row_metadata": [
        {
          "foo": {
            "foo": "bar"
          }
        }
      ]
    },
    "parse_job_id": "parse_job_id",
    "parse_tier": "parse_tier"
  },
  "extract_result": {
    "foo": {
      "foo": "bar"
    }
  },
  "metadata": {
    "usage": {
      "num_pages_billed": 0,
      "num_pages_extracted": 0
    }
  },
  "usage": {
    "credits": 30,
    "extract_credits": 45,
    "parse_credits": 30
  }
}
```