Skip to content

Document Parse

POST/v1/api/agentbody/document-parse

Parse a document at an HTTPS URL into Markdown and structured content. Supports PDFs, Word documents, and other common formats. Returns page count, metadata, and full Markdown extraction.

Request body

Call this sync operation at its vendor-qualified URL. The model identity is encoded in the path; only operation-specific input fields belong in the request body.

stringfile_urlrequired

The HTTPS URL of the document to parse.

stringfile_namerequired

Original filename with extension (used for format detection).

Optional<boolean>analysis_chart

Whether to analyze charts in the document.

Optional<boolean>merge_tables

Whether to merge split tables across pages.

Optional<boolean>relevel_titles

Whether to re-level heading hierarchy.

Response Schema

A synchronous completed response contains exactly one outputs item with only data. Failed and timeout responses contain error and never outputs.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

stringmodelrequired

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Contains exactly one item whose only field is data.

Optional<object | array>outputs[0].data

Operation-specific business payload. This reference uses an empty object when no safe example can be confirmed.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

API capabilities

array<string>capability_tagsrequired

Capabilities declared by the API registry.

Default: document-parsing, pdf, markdown

stringexecution_moderequired

Execution mode declared by the API registry.

Default: sync

pending response

{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"pending","model":"agentbody/document-parse"}

running response

{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"running","model":"agentbody/document-parse"}

completed response

{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"completed","model":"agentbody/document-parse","outputs":[{"data":{}}]}

failed response

{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"failed","model":"agentbody/document-parse","error":{"type":"upstream_error","message":"upstream request failed"}}

timeout response

{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"timeout","model":"agentbody/document-parse","error":{"type":"upstream_error","message":"upstream request failed"}}