Skip to content

The platform

Parse

Turn a document into text, Markdown, HTML or JSON.

A parse job reads a document and returns its content in the format you choose. It is also the first step of an extraction: an extract job always works on a completed parse job.

curl -X POST "https://byteit.ai/v1/jobs/parse-jobs/" \
-H "X-API-Key: $BYTEIT_API_KEY" \
-F "file=@invoice.pdf" \
-F "nickname=invoice-march" \
-F "output_format=md"
output_format You get
txt Plain text. The default.
md Markdown.
html HTML.
json Structured JSON.
zip A ZIP archive.

You can also ask for another format when you download: the result endpoint takes an output_format override.

Send these in processing_options.

Option Default
parse_type auto. Also complex and handwritten.
languages Not set
page_range Not set
table_enrichment false
image_annotations false
force_image_annotations false

Poll the job’s status until it is completed, then download the result. See the Quickstart for the full loop.

curl https://byteit.ai/v1/jobs/$JOB_ID/result/ \
-H "X-API-Key: $BYTEIT_API_KEY" \
-o invoice.md