Skip to main content
POST
Parse a document into normalized text and persist the result as a Parse resource that can later be retrieved via GET /v1/parses/{parse_id} or listed via GET /v1/parses.

Authorizations

Authorization
string
header
required

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

Body

application/json

Public create-parse request body.

document
MIMEData · object
required

The document to parse

model
string
default:retab-small

The model to use for parsing

table_parsing_format
enum<string>
default:html

Format used to render tables extracted from the document

Available options:
markdown,
yaml,
html,
json
instructions
string | null

Free-form instructions appended to the system prompt to steer the parse.

bust_cache
boolean
default:false

If true, skip the LLM cache and force a fresh completion

background
boolean
default:false

If true, run asynchronously: returns immediately with status 'queued' and an empty output. Poll GET /v1//{id} until status is terminal. Mutually exclusive with stream.

Response

Successful Response

A parse result: the per-page and full-document text extracted from a document.

id
string
required

Unique identifier of the parse

file
FileRef · object
required

Information about the parsed file

model
string
required

Model used for parsing

table_parsing_format
enum<string>
required

Format used to render tables extracted from the document

Available options:
markdown,
yaml,
html,
json
output
ParseOutput · object
required

The parsed document content

instructions
string | null

Free-form instructions supplied with the parse request.

status
enum<string>
default:pending

Lifecycle status. The synchronous path returns 'completed'. Background runs progress pending -> queued -> in_progress -> completed | failed | cancelled.

Available options:
pending,
queued,
in_progress,
completed,
failed,
cancelled
error
PrimitiveError · object | null

Error details when a background run fails; null otherwise. Always present so consumers can read it without an existence check.

usage
RetabUsage · object | null

Usage information for the parse operation

created_at
string<date-time> | null