Create Processor Run

from extend_ai import Extend
client = Extend(
    token="YOUR_TOKEN_HERE",
    extend_api_version="2026-02-09",
)
client.processor_run.create(
    processor_id="processor_id_here",
)

{
  "success": true,
  "processorRun": {
    "object": "document_processor_run",
    "id": "exr_Xj8mK2pL9nR4vT7qY5wZ",
    "processorId": "ex_Xj8mK2pL9nR4vT7qY5wZ",
    "processorVersionId": "exv_Xj8mK2pL9nR4vT7qY5wZ",
    "processorName": "Invoice Processor",
    "status": "PENDING",
    "output": {},
    "reviewed": false,
    "edited": false,
    "edits": {},
    "type": "CLASSIFY",
    "config": {
      "type": "CLASSIFY",
      "baseProcessor": "classification_performance",
      "baseVersion": "3.2.0",
      "classifications": [
        {
          "id": "my_unique_id",
          "type": "invoice",
          "description": "An invoice is a document that lists the items purchased and the total amount due."
        }
      ],
      "classificationRules": "Remember, when it comes to differentiating between invoices and purchase orders, the most important thing to look for is the date of the document.",
      "advancedOptions": {
        "context": "default",
        "advancedMultimodalEnabled": false,
        "fixedPageLimit": 30,
        "pageRanges": [
          {
            "start": 1,
            "end": 10
          },
          {
            "start": 20,
            "end": 30
          }
        ]
      },
      "parser": {
        "target": "markdown",
        "chunkingStrategy": {
          "type": "page",
          "options": {
            "minCharacters": 500,
            "maxCharacters": 10000
          }
        },
        "engine": "parse_performance",
        "engineVersion": "latest",
        "blockOptions": {
          "figures": {
            "enabled": true,
            "figureImageClippingEnabled": true,
            "advancedChartExtractionEnabled": false
          },
          "tables": {
            "enabled": true,
            "targetFormat": "html",
            "tableHeaderContinuationEnabled": false,
            "cellBlocksEnabled": false,
            "agentic": {
              "enabled": false,
              "customInstructions": "string"
            }
          },
          "text": {
            "signatureDetectionEnabled": false,
            "agentic": {
              "enabled": false,
              "customInstructions": "string"
            }
          },
          "keyValue": {
            "blankFieldFormattingEnabled": false
          },
          "barcodes": {
            "imageClippingEnabled": false,
            "readingEnabled": false
          },
          "formulas": {
            "enabled": false
          }
        },
        "advancedOptions": {
          "pageRotationEnabled": true,
          "pageRanges": [
            {
              "start": 1,
              "end": 10
            },
            {
              "start": 20,
              "end": 30
            }
          ],
          "excelParsingMode": "basic",
          "excelSkipHiddenContent": false,
          "excelUseRawCellValues": false,
          "excelSkipCalculation": true,
          "verticalGroupingThreshold": 1,
          "returnOcr": {
            "words": false
          },
          "alwaysConvertToPdf": false,
          "enrichmentFormat": "xml",
          "imageConversionQuality": "medium",
          "formattingDetection": [
            {
              "type": "change_tracking"
            }
          ]
        }
      }
    },
    "files": [
      {
        "object": "file",
        "id": "file_xK9mLPqRtN3vS8wF5hB2cQ",
        "name": "Invoices.pdf",
        "type": "PDF",
        "presignedUrl": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
        "parentFileId": "file_Zk9mNP12Qw4yTv8BdR3H",
        "metadata": {
          "pageCount": 30,
          "parentSplit": {
            "id": "string",
            "type": "Invoice",
            "identifier": "other_2_9",
            "startPage": 1,
            "endPage": 10
          }
        },
        "createdAt": "2024-03-21T16:45:00Z",
        "updatedAt": "2024-03-21T16:45:00Z",
        "contents": {
          "rawText": "string",
          "pages": [
            {
              "pageNumber": 1,
              "pageHeight": 792,
              "pageWidth": 612,
              "markdown": "# Heading\n\nThis is a paragraph with **bold** and *italic* text.\n\n- List item 1\n- List item 2\n\n> This is a blockquote",
              "html": "<div>This is the html of the page.</div>"
            }
          ],
          "sections": [
            {
              "startPageNumber": 1,
              "endPageNumber": 3,
              "markdown": "# Section Header\n\nContent spanning multiple pages...\n"
            }
          ],
          "sheets": [
            {
              "sheetName": "Sheet1",
              "rawText": "Column1,Column2\nValue1,Value2"
            }
          ]
        }
      }
    ],
    "mergedProcessors": [
      {
        "processorId": "ex_Xj8mK2pL9nR4vT7qY5wZ",
        "processorVersionId": "exv_Xj8mK2pL9nR4vT7qY5wZ",
        "processorName": "Invoice Line Items Processor"
      }
    ],
    "url": "https://dashboard.extend.ai/runs/exr_Xj8mK2pL9nR4vT7qY5wZ",
    "failureReason": "string",
    "failureMessage": "string",
    "metadata": {},
    "initialOutput": {},
    "reviewedOutput": {},
    "usage": {
      "credits": 3.5
    }
  }
}

Run processors (extraction, classification, splitting, etc.) on a given document.

Synchronous vs Asynchronous Processing:

Asynchronous (default): Returns immediately with PROCESSING status. Use webhooks or polling to get results.
Synchronous: Set sync: true to wait for completion and get final results in the response (5-minute timeout).

For asynchronous processing:

You can configure webhooks to receive notifications when a processor run is complete or failed.
Or you can poll the get endpoint for updates on the status of the processor run.

Run processors (extraction, classification, splitting, etc.) on a given document. **Synchronous vs Asynchronous Processing:** - **Asynchronous (default)**: Returns immediately with `PROCESSING` status. Use webhooks or polling to get results. - **Synchronous**: Set `sync: true` to wait for completion and get final results in the response (5-minute timeout). **For asynchronous processing:** - You can [configure webhooks](https://docs.extend.ai/2026-02-09/webhooks/configuration) to receive notifications when a processor run is complete or failed. - Or you can [poll the get endpoint](https://docs.extend.ai/2026-02-09/api-reference/endpoints/legacy/get-processor-run) for updates on the status of the processor run.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

processorIdstringRequired

The ID of the processor to be run.

Example: "ex_Xj8mK2pL9nR4vT7qY5wZ"

versionstringOptionalDefaults to latest

An optional version of the processor to use. When not supplied, the most recent published version of the processor will be used. Special values include: - `"latest"` for the most recent published version. If there are no published versions, the draft version will be used. - `"draft"` for the draft version. - Specific version numbers corresponding to versions your team has published, e.g. `"1.0"`, `"2.2"`, etc.

fileobjectOptional

The file to be processed. One of `file` or `rawText` must be provided. Supported file types can be found [here](https://docs.extend.ai/2026-02-09/general/supported-file-types).

rawTextstringOptional

A raw string to be processed. Can be used in place of file when passing raw text data streams. One of file or rawText must be provided.

syncbooleanOptionalDefaults to false

Whether to run the processor synchronously. When `true`, the request will wait for the processor run to complete and return the final results. When `false` (default), the request returns immediately with a `PROCESSING` status, and you can poll for completion or use webhooks. For production use cases, we recommending leaving sync off and building around an async integration for more resiliency, unless your use case is predictably fast (e.g. sub < 30 seconds) run time or otherwise have integration constraints that require a synchronous API. See [Async Processing](https://docs.extend.ai/2026-02-09/general/async-processing) for more details. **Timeout**: Synchronous requests have a 5-minute timeout. If the processor run takes longer, it will continue processing asynchronously and you can retrieve the results via the GET endpoint.

priorityintegerOptional1-100Defaults to 50

An optional value used to determine the relative order of ProcessorRuns when rate limiting is in effect. Lower values will be prioritized before higher values.

metadatamap from strings to anyOptional

An optional object that can be passed in to identify the run of the document processor. It will be returned back to you in the response and webhooks. To categorize processor runs for billing and usage tracking, include `extend:usage_tags` with an array of string values (e.g., `{"extend:usage_tags": ["production", "team-eng", "customer-123"]}`). Tags must contain only alphanumeric characters, hyphens, and underscores; any special characters will be automatically removed.

configobjectOptional

The configuration for the processor run. If this is provided, this config will be used. If not provided, the config for the specific version you provide will be used. The type of configuration must match the processor type.

Response

Successfully created processor run

successboolean

processorRunobject

Errors

400

Bad Request Error

401

Unauthorized Error

404

Not Found Error

429

Too Many Requests Error

Whether to run the processor synchronously. When true, the request will wait for the processor run to complete and return the final results. When false (default), the request returns immediately with a PROCESSING status, and you can poll for completion or use webhooks. For production use cases, we recommending leaving sync off and building around an async integration for more resiliency, unless your use case is predictably fast (e.g. sub < 30 seconds) run time or otherwise have integration constraints that require a synchronous API. See Async Processing for more details.

Timeout: Synchronous requests have a 5-minute timeout. If the processor run takes longer, it will continue processing asynchronously and you can retrieve the results via the GET endpoint.

Create Processor Run

Authentication

Headers

Request

Response

Errors

Authentication

Headers

Request

Response

Errors