uploads

Get a pre-signed URL to upload large files (.docx/PDF/HTML/MD/RTF) without bloating agent context.

Returns a short-lived (5-minute) PUT URL plus a curl example. **If you have shell access (Bash tool), execute the returned `curl_example` yourself to push the file directly to cloud storage — do NOT paste the curl command back to the user expecting them to run it manually. Only fall back to returning the curl text when shell execution is genuinely unavailable.** Bytes never pass through the agent's context window either way. After upload completes, call process_uploaded_document with the upload_id to trigger parsing. For files <100KB where token cost is trivial, upload_document_base64 still works inline. Max file size: 100 MB. Supported formats: .pdf, .docx, .txt, .rtf, .md, .html, .htm.

POST

/

v1

/

uploads

Get a pre-signed URL to upload large files (.docx/PDF/HTML/MD/RTF) without bloating agent context.

curl --request POST \
  --url https://api.example.com/v1/uploads \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "filename": "<string>",
  "content_type": "<string>",
  "size_bytes": 123,
  "purpose": "document"
}
'

{
  "upload_id": "<string>",
  "upload_url": "<string>",
  "expires_at": "<string>",
  "expires_in_seconds": 123,
  "max_size_bytes": 123,
  "curl_example": "<string>"
}

Authorizations

Authorization

string

header

required

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

Headers

authorization

string | null

Body

application/json

filename

string

required

Original filename including extension (e.g. 'contract.docx'). Used downstream for file-type detection.

Maximum string length: 255

content_type

string

required

MIME type the agent will PUT with (e.g. 'application/vnd.openxmlformats-officedocument.wordprocessingml.document' for .docx).

Maximum string length: 200

size_bytes

integer

required

File size in bytes. Must be > 0 and <= 104857600 (100 MB).

Required range: x <= 104857600

purpose

enum<string>

default:document

What the upload will be used for. document = the active editable doc; attachment = read-only AI-searchable reference; export-html = HTML payload destined for Mode C of POST /v1/documents/export.

Available options:

document,

attachment,

export-html

Response

Successful Response

upload_id

string

required

upload_url

string

required

expires_at

string

required

expires_in_seconds

integer

required

max_size_bytes

integer

required

curl_example

string

required

Parse an uploaded file into structured HTML with chunk IDs for targeted AI editing.Fetches the file uploaded via request_upload_url and runs the same parsing pipeline as upload_document_base64. Returns structured HTML with unique chunk IDs on every paragraph, heading, table, row, and cell — enabling the AI to make targeted structural edits via chat ("remove row 3 of the pricing table" works). Tables, borders, shading, alternating row colors, fonts, and inline styling preserved on edit and export. Counts as one billable operation. Specify parse_mode='document' to load as the active editable document, or parse_mode='attachment' to load as read-only AI-searchable reference.

Get a pre-signed URL to upload large files (.docx/PDF/HTML/MD/RTF) without bloating agent context.

curl --request POST \
  --url https://api.example.com/v1/uploads \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "filename": "<string>",
  "content_type": "<string>",
  "size_bytes": 123,
  "purpose": "document"
}
'

{
  "upload_id": "<string>",
  "upload_url": "<string>",
  "expires_at": "<string>",
  "expires_in_seconds": 123,
  "max_size_bytes": 123,
  "curl_example": "<string>"
}