Extract File (Sync)

POST

/extract

POST

/extract

1 from extend_ai import Extend, FileFromUrl, ExtractConfigJson
2 
3 client = Extend(
4     token="YOUR_TOKEN_HERE",
5     extend_api_version="2026-02-09",
6 )
7 
8 client.extract(
9     file=FileFromUrl(
10         url="https://example.com/invoice.pdf",
11     ),
12     config=ExtractConfigJson(
13         schema={
14             "type": "object",
15             "properties": {"vendor_name": {"type": "string", "description": "The name of the vendor"}, "invoice_number": {"type": "string", "description": "The invoice number"}, "total_amount": {"type": "object", "extend:type": "currency", "description": "The total amount due", "properties": {"amount": {"type": ["number", "null"]}, "iso_4217_currency_code": {"type": ["string", "null"]}}, "required": ["amount", "iso_4217_currency_code"]}}
16         },
17     ),
18 )

1 {
2   "object": "extract_run",
3   "id": "exr_Xj8mK2pL9nR4vT7qY5wZ",
4   "status": "PROCESSING",
5   "output": {
6     "value": {},
7     "metadata": {}
8   },
9   "initialOutput": {
10     "value": {},
11     "metadata": {}
12   },
13   "reviewedOutput": {
14     "value": {},
15     "metadata": {}
16   },
17   "failureReason": "PARSING_ERROR",
18   "failureMessage": "string",
19   "metadata": {},
20   "reviewed": false,
21   "edited": false,
22   "edits": {},
23   "config": {
24     "baseProcessor": "extraction_performance",
25     "baseVersion": "string",
26     "extractionRules": "string",
27     "schema": {},
28     "advancedOptions": {
29       "modelReasoningInsightsEnabled": true,
30       "advancedMultimodalEnabled": true,
31       "citationsEnabled": true,
32       "citationMode": "line",
33       "arrayCitationStrategy": "item",
34       "arrayStrategy": {
35         "type": "large_array_heuristics"
36       },
37       "chunkingOptions": {
38         "chunkingStrategy": "standard",
39         "pageChunkSize": 1,
40         "chunkSelectionStrategy": "intelligent",
41         "customSemanticChunkingRules": "string"
42       },
43       "excelSheetRanges": [
44         {
45           "start": 1,
46           "end": 1
47         }
48       ],
49       "excelSheetSelectionStrategy": "intelligent",
50       "pageRanges": [
51         {
52           "start": 1,
53           "end": 10
54         },
55         {
56           "start": 20,
57           "end": 30
58         }
59       ],
60       "reviewAgent": {
61         "enabled": true
62       },
63       "currentDateEnabled": true
64     },
65     "parseConfig": {
66       "target": "markdown",
67       "chunkingStrategy": {
68         "type": "page",
69         "options": {
70           "minCharacters": 500,
71           "maxCharacters": 10000
72         }
73       },
74       "engine": "parse_performance",
75       "engineVersion": "latest",
76       "blockOptions": {
77         "figures": {
78           "enabled": true,
79           "figureImageClippingEnabled": true,
80           "advancedChartExtractionEnabled": false
81         },
82         "tables": {
83           "enabled": true,
84           "targetFormat": "html",
85           "tableHeaderContinuationEnabled": false,
86           "cellBlocksEnabled": false,
87           "agentic": {
88             "enabled": false,
89             "customInstructions": "string"
90           }
91         },
92         "text": {
93           "signatureDetectionEnabled": false,
94           "agentic": {
95             "enabled": false,
96             "customInstructions": "string"
97           }
98         },
99         "keyValue": {
100           "blankFieldFormattingEnabled": false
101         },
102         "barcodes": {
103           "imageClippingEnabled": false,
104           "readingEnabled": false
105         },
106         "formulas": {
107           "enabled": false
108         }
109       },
110       "advancedOptions": {
111         "pageRotationEnabled": true,
112         "pageRanges": [
113           {
114             "start": 1,
115             "end": 10
116           },
117           {
118             "start": 20,
119             "end": 30
120           }
121         ],
122         "excelParsingMode": "basic",
123         "excelSkipHiddenContent": false,
124         "excelUseRawCellValues": false,
125         "excelSkipCalculation": true,
126         "verticalGroupingThreshold": 1,
127         "returnOcr": {
128           "words": false
129         },
130         "alwaysConvertToPdf": false,
131         "enrichmentFormat": "xml",
132         "imageConversionQuality": "medium",
133         "formattingDetection": [
134           {
135             "type": "change_tracking"
136           }
137         ]
138       }
139     }
140   },
141   "extractor": {
142     "object": "extractor",
143     "id": "ex_Xj8mK2pL9nR4vT7qY5wZ",
144     "name": "Invoice Extractor",
145     "createdAt": "2024-03-21T16:45:00Z",
146     "updatedAt": "2024-03-21T16:45:00Z"
147   },
148   "extractorVersion": {
149     "object": "extractor_version",
150     "id": "exv_xK9mLPqRtN3vS8wF5hB2cQ",
151     "description": "Updated extraction fields for new invoice format",
152     "version": "draft",
153     "extractorId": "ex_Xj8mK2pL9nR4vT7qY5wZ",
154     "createdAt": "2024-03-21T16:45:00Z"
155   },
156   "file": {
157     "object": "file",
158     "id": "file_xK9mLPqRtN3vS8wF5hB2cQ",
159     "name": "Invoices.pdf",
160     "type": "PDF",
161     "parentFileId": "file_Zk9mNP12Qw4yTv8BdR3H",
162     "metadata": {
163       "pageCount": 30,
164       "parentSplit": {
165         "id": "string",
166         "type": "Invoice",
167         "identifier": "other_2_9",
168         "startPage": 1,
169         "endPage": 10
170       }
171     },
172     "createdAt": "2024-03-21T16:45:00Z",
173     "updatedAt": "2024-03-21T16:45:00Z"
174   },
175   "parseRunId": "pr_Xj8mK2pL9nR4vT7qY5wZ",
176   "dashboardUrl": "https://dashboard.extend.ai/runs/exr_Xj8mK2pL9nR4vT7qY5wZ",
177   "usage": {
178     "credits": 9,
179     "totalCredits": 15,
180     "breakdown": [
181       {
182         "object": "parse_run",
183         "id": "pr_3UZSj69pYZDKHFuuX57ic",
184         "credits": 6,
185         "charges": [
186           {
187             "product": "extraction_performance",
188             "unit": "page",
189             "quantity": 10,
190             "credits": 30
191           },
192           {
193             "product": "review_agent",
194             "unit": "page",
195             "quantity": 10,
196             "credits": 10
197           },
198           {
199             "product": "agentic_text_correction",
200             "unit": "page",
201             "quantity": 3,
202             "credits": 3,
203             "pages": [
204               2,
205               4,
206               7
207             ]
208           }
209         ]
210       }
211     ]
212   },
213   "createdAt": "2024-03-21T16:45:00Z",
214   "updatedAt": "2024-03-21T16:45:00Z"
215 }

Extract structured data from a file synchronously, waiting for the result before returning. This endpoint has a 5-minute timeout — if processing takes longer, the request will fail.

Note: This endpoint is intended for onboarding and testing only. For production workloads, use POST /extract_runs with polling or webhooks instead, as it provides better reliability for large files and avoids timeout issues.

The Extract endpoint allows you to extract structured data from files using an existing extractor, an inline configuration, or no configuration at all. When neither is provided, Extend automatically infers a schema from the document before extraction — no extractor or schema is required.

For more details, see the Extract File guide.

Extract structured data from a file synchronously, waiting for the result before returning. This endpoint has a **5-minute timeout** — if processing takes longer, the request will fail. **Note:** This endpoint is intended for onboarding and testing only. For production workloads, use `POST /extract_runs` with [polling or webhooks](https://docs.extend.ai/2026-02-09/general/async-processing) instead, as it provides better reliability for large files and avoids timeout issues. The Extract endpoint allows you to extract structured data from files using an existing extractor, an inline configuration, or no configuration at all. When neither is provided, Extend automatically infers a schema from the document before extraction — no extractor or schema is required. For more details, see the [Extract File guide](https://docs.extend.ai/2026-02-09/extraction/overview).

Authentication

AuthorizationBearer

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

Headers

x-extend-api-version"2026-02-09"OptionalDefaults to 2026-02-09

API version to use for the request. If you’re using an SDK, you can ignore this parameter. If you are not using an SDK and do not specify a version, you will either receive a 400 Bad Request or be set to a previous legacy version. See API Versioning for more details.

API version to use for the request. If you're using an SDK, you can ignore this parameter. If you are not using an SDK and do not specify a version, you will either receive a `400 Bad Request` or be set to a previous legacy version. See [API Versioning](https://docs.extend.ai/2026-02-09/api-reference/api-versioning) for more details.

Request

This endpoint expects an object.

fileobjectRequired

The file to be extracted from. Files can be provided as a URL, Extend file ID, or raw text.

extractorobjectOptional

Reference to an existing extractor. Mutually exclusive with config — provide one or the other, or omit both to have Extend infer a schema from the document.

configobjectOptional

Inline extract configuration. Mutually exclusive with extractor — provide one or the other, or omit both to have Extend infer a schema from the document.

metadatamap from strings to anyOptional

An optional object that can be passed in to identify the run. It will be returned back to you in the response and webhooks. Maximum size is 10KB.

To categorize 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.

An optional object that can be passed in to identify the run. It will be returned back to you in the response and webhooks. Maximum size is 10KB. To categorize 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.

Response

Successfully extracted data from file

objectenum

The type of object. Will always be "extract_run".

idstring

The unique identifier for this extract run.

Example: "exr_Xj8mK2pL9nR4vT7qY5wZ"

statusenum

The status of a processor run (extract, classify, or split):

"PENDING" - The run has been created and is waiting to be processed
"PROCESSING" - The run is in progress
"PROCESSED" - The run completed successfully
"FAILED" - The run failed
"CANCELLED" - The run was cancelled

outputobject or map from strings to objects or null

The final output, either reviewed or initial. This is a union of two possible shapes:

JSON Schema output: The current output format, returned for runs created with a JSON Schema config.
Legacy output: A legacy output format from a previous API version. This shape is only returned for runs that were originally created with a legacy config.

Availability: Present when status is "PROCESSED".

initialOutputobject or map from strings to objects or null

The initial output from the extract run, before any review edits.

Availability: Present when reviewed is true.

reviewedOutputobject or map from strings to objects or null

The output after human review.

Availability: Present when reviewed is true.

failureReasonstring or null

The reason for failure.

Availability: Present when status is "FAILED".

Possible values include:

ABORTED - The run was aborted by the user
INTERNAL_ERROR - An unexpected internal error occurred
FAILED_TO_PROCESS_FILE - Failed to process the file (e.g., OCR failure, file access issues)
INVALID_PROCESSOR - The processor configuration is invalid
INVALID_CONFIGURATION - The provided configuration is incompatible with the selected model
PARSING_ERROR - Failed to parse the extraction output
PRE_PROCESSING_FAILURE - An error occurred during preprocessing (e.g., chunking)
POST_PROCESSING_FAILURE - An error occurred during postprocessing
OUT_OF_CREDITS - Insufficient credits to run the extraction
SCHEMA_GENERATION_FAILED - Automatic schema inference failed (only applies when schema is omitted). The file could not be parsed or a schema could not be generated from it.

Note: Additional failure reasons may be added in the future. Your integration should handle unknown values gracefully.

failureMessagestring or null

A detailed message about the failure.

Availability: Present when status is "FAILED".

metadatamap from strings to any or null

Any metadata that was provided when creating the extract run.

Availability: Present when metadata was provided during creation.

reviewedboolean

Indicates whether the run has been reviewed by a human.

editedboolean

Indicates whether the run results have been edited during review.

editsmap from strings to objects or null

Details of edits made during review.

Availability: Present when edited is true.

configobject

The configuration used for this extract run. This is a union of two possible shapes:

JSON Schema config: The current config format. All runs created through this API version use this shape.
Legacy config: A fields-array config from a previous API version. This shape is only returned when retrieving runs that were originally created with the legacy format. This API version does not support creating runs with legacy configs.

extractorobject or null

The extractor that was used for this run.

Availability: Present when an extractor reference was provided. Not present when using inline config.

extractorVersionobject or null

The version of the extractor that was used for this run.

Availability: Present when an extractor reference was provided. Not present when using inline config.

fileobject or null

The file that was processed. null when the file could not be accessed or processed (for example a run that failed during file ingestion, or a multi-file batch run).

parseRunIdstring or null

The ID of the parse run that was used for this extract run.

Availability: Present when a parse run was created.

dashboardUrlstring

The URL to view the extract run in the Extend dashboard.

usageobject or null

Usage credits consumed by this extract run.

Availability: Present when status is "PROCESSED". Will not be returned for runs created before October 7, 2025 or for customers on legacy billing systems.

createdAtstringformat: "date-time"

The time (in UTC) at which the object was created. Will follow the RFC 3339 format.

Example: "2024-03-21T16:45:00Z"

updatedAtstringformat: "date-time"

The time (in UTC) at which the object was last updated. Will follow the RFC 3339 format.

Example: "2024-03-21T16:45:00Z"

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

429

Too Many Requests Error

500

Internal Server Error