Split File (Sync)

POST

/split

POST

/split

1 import { ExtendClient, ExtendEnvironment } from "extend-ai";
2 
3 async function main() {
4     const client = new ExtendClient({
5         environment: ExtendEnvironment.Production,
6         token: "YOUR_TOKEN_HERE",
7     });
8     await client.split({
9         file: {
10             url: "https://example.com/multi-document.pdf",
11         },
12         config: {
13             splitClassifications: [
14                 {
15                     id: "invoice",
16                     type: "invoice",
17                     description: "An invoice or bill for goods or services",
18                 },
19                 {
20                     id: "receipt",
21                     type: "receipt",
22                     description: "A receipt confirming payment",
23                 },
24                 {
25                     id: "other",
26                     type: "other",
27                     description: "Any other document type",
28                 },
29             ],
30         },
31     });
32 }
33 main();

1 {
2   "object": "split_run",
3   "id": "splr_Xj8mK2pL9nR4vT7qY5wZ",
4   "splitter": {
5     "object": "splitter",
6     "id": "spl_Xj8mK2pL9nR4vT7qY5wZ",
7     "name": "Invoice Packet Splitter",
8     "createdAt": "2024-03-21T16:45:00Z",
9     "updatedAt": "2024-03-21T16:45:00Z"
10   },
11   "splitterVersion": {
12     "object": "splitter_version",
13     "id": "splv_xK9mLPqRtN3vS8wF5hB2cQ",
14     "description": "Updated split rules for multi-invoice packets",
15     "version": "draft",
16     "splitterId": "spl_Xj8mK2pL9nR4vT7qY5wZ",
17     "createdAt": "2024-03-21T16:45:00Z"
18   },
19   "status": "PROCESSING",
20   "output": {
21     "splits": [
22       {
23         "type": "invoice",
24         "observation": "Pages 1-3 contain an invoice from Acme Corp",
25         "identifier": "INV-2024-001",
26         "startPage": 1,
27         "endPage": 3,
28         "classificationId": "invoice",
29         "id": "splt_xK9mLPqRtN3vS8wF5hB2cQ",
30         "fileId": "file_xK9mLPqRtN3vS8wF5hB2cQ",
31         "name": "string"
32       }
33     ],
34     "isExternal": true
35   },
36   "initialOutput": {
37     "splits": [
38       {
39         "type": "invoice",
40         "observation": "Pages 1-3 contain an invoice from Acme Corp",
41         "identifier": "INV-2024-001",
42         "startPage": 1,
43         "endPage": 3,
44         "classificationId": "invoice",
45         "id": "splt_xK9mLPqRtN3vS8wF5hB2cQ",
46         "fileId": "file_xK9mLPqRtN3vS8wF5hB2cQ",
47         "name": "string"
48       }
49     ],
50     "isExternal": true
51   },
52   "reviewedOutput": {
53     "splits": [
54       {
55         "type": "invoice",
56         "observation": "Pages 1-3 contain an invoice from Acme Corp",
57         "identifier": "INV-2024-001",
58         "startPage": 1,
59         "endPage": 3,
60         "classificationId": "invoice",
61         "id": "splt_xK9mLPqRtN3vS8wF5hB2cQ",
62         "fileId": "file_xK9mLPqRtN3vS8wF5hB2cQ",
63         "name": "string"
64       }
65     ],
66     "isExternal": true
67   },
68   "failureReason": "PARSING_ERROR",
69   "failureMessage": "string",
70   "metadata": {},
71   "reviewed": false,
72   "edited": false,
73   "config": {
74     "splitClassifications": [
75       {
76         "id": "my_unique_id",
77         "type": "invoice",
78         "description": "An invoice is a document that lists the items purchased and the total amount due."
79       }
80     ],
81     "baseProcessor": "splitting_performance",
82     "baseVersion": "string",
83     "splitRules": "string",
84     "advancedOptions": {
85       "splitIdentifierRules": "string",
86       "splitMethod": "high_precision",
87       "splitExcelDocumentsBySheetEnabled": false,
88       "pageRanges": [
89         {
90           "start": 1,
91           "end": 10
92         },
93         {
94           "start": 20,
95           "end": 30
96         }
97       ],
98       "pageOverlapEnabled": false
99     },
100     "parseConfig": {
101       "target": "markdown",
102       "chunkingStrategy": {
103         "type": "page",
104         "options": {
105           "minCharacters": 500,
106           "maxCharacters": 10000
107         }
108       },
109       "engine": "parse_performance",
110       "engineVersion": "latest",
111       "blockOptions": {
112         "figures": {
113           "enabled": true,
114           "figureImageClippingEnabled": true
115         },
116         "tables": {
117           "targetFormat": "html",
118           "tableHeaderContinuationEnabled": false,
119           "cellBlocksEnabled": false,
120           "agentic": {
121             "enabled": false,
122             "customInstructions": "string"
123           },
124           "enabled": true
125         },
126         "text": {
127           "signatureDetectionEnabled": false,
128           "agentic": {
129             "enabled": false,
130             "customInstructions": "string"
131           }
132         }
133       },
134       "advancedOptions": {
135         "pageRotationEnabled": true,
136         "pageRanges": [
137           {
138             "start": 1,
139             "end": 10
140           },
141           {
142             "start": 20,
143             "end": 30
144           }
145         ],
146         "excelParsingMode": "basic",
147         "excelSkipHiddenContent": false,
148         "verticalGroupingThreshold": 1,
149         "returnOcr": {
150           "words": false
151         }
152       }
153     }
154   },
155   "file": {
156     "object": "file",
157     "id": "file_xK9mLPqRtN3vS8wF5hB2cQ",
158     "name": "Invoices.pdf",
159     "type": "PDF",
160     "parentFileId": "file_Zk9mNP12Qw4yTv8BdR3H",
161     "metadata": {
162       "pageCount": 30,
163       "parentSplit": {
164         "id": "string",
165         "type": "Invoice",
166         "identifier": "other_2_9",
167         "startPage": 1,
168         "endPage": 10
169       }
170     },
171     "createdAt": "2024-03-21T16:45:00Z",
172     "updatedAt": "2024-03-21T16:45:00Z"
173   },
174   "parseRunId": "pr_Xj8mK2pL9nR4vT7qY5wZ",
175   "dashboardUrl": "https://dashboard.extend.ai/runs/splr_Xj8mK2pL9nR4vT7qY5wZ",
176   "usage": {
177     "credits": 10
178   },
179   "createdAt": "2024-03-21T16:45:00Z",
180   "updatedAt": "2024-03-21T16:45:00Z"
181 }

Split a document 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 /split_runs with polling or webhooks instead, as it provides better reliability for large files and avoids timeout issues.

The Split endpoint allows you to split documents into multiple parts using an existing splitter or an inline configuration.

For more details, see the Split File guide.

Split a document 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 /split_runs` with [polling or webhooks](https://docs.extend.ai/2026-02-09/developers/async-processing) instead, as it provides better reliability for large files and avoids timeout issues. The Split endpoint allows you to split documents into multiple parts using an existing splitter or an inline configuration. For more details, see the [Split File guide](https://docs.extend.ai/2026-02-09/product/splitting/configuring-a-splitter).

Authentication

AuthorizationBearer

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

Request

This endpoint expects an object.

fileobjectRequired

The file to be split. Files can be provided as a URL or an Extend file ID.

splitterobjectOptional

Reference to an existing splitter. One of splitter or config must be provided.

configobjectOptional

Inline splitter configuration. One of splitter or config must be provided.

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 split file

objectenum

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

Allowed values:

idstring

The unique identifier for this split run.

Example: "splr_Xj8mK2pL9nR4vT7qY5wZ"

splitterobject or null

The splitter that was used for this run.

Availability: Present when a splitter reference was provided. Not present when using inline config.

splitterVersionobject or null

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

Availability: Present when a splitter reference was provided. Not present when using inline config.

statusenum

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

"PROCESSING" - The run is in progress
"PROCESSED" - The run completed successfully
"FAILED" - The run failed
"CANCELLED" - The run was cancelled

The status of a processor run (extract, classify, or split): * `"PROCESSING"` - The run is in progress * `"PROCESSED"` - The run completed successfully * `"FAILED"` - The run failed * `"CANCELLED"` - The run was cancelled

Allowed values:

outputobject or null

The final output, either reviewed or initial.

Availability: Present when status is "PROCESSED".

initialOutputobject or null

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

Availability: Present when reviewed is true.

reviewedOutputobject 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 splitting output
PRE_PROCESSING_FAILURE - An error occurred during preprocessing
POST_PROCESSING_FAILURE - An error occurred during postprocessing
OUT_OF_CREDITS - Insufficient credits to run the splitter

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

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 splitting output * `PRE_PROCESSING_FAILURE` - An error occurred during preprocessing * `POST_PROCESSING_FAILURE` - An error occurred during postprocessing * `OUT_OF_CREDITS` - Insufficient credits to run the splitter **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 split 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.

configobject

The configuration used for this split run.

fileobject

The file that was processed.

parseRunIdstring or null

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

Availability: Present when a parse run was created.

dashboardUrlstring

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

usageobject or null

Usage credits consumed by this run.

Availability: Present when status is "PROCESSED".

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"

Split File (Sync)

Authentication

Headers

Request

Response

Errors