Skip to main content
POST
/
augment
/
text-parser
/api/v1/augment/text-parser
curl --request POST \
  --url https://api.venice.ai/api/v1/augment/text-parser \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form response_format=json
{
  "text": "<string>",
  "tokens": 123
}

Documentation Index

Fetch the complete documentation index at: https://docs.venice.ai/llms.txt

Use this file to discover all available pages before exploring further.

This is an experimental API. The request and response format may change without notice.
Upload a document file via multipart/form-data using the file field. Supported formats include PDF, DOCX, XLSX, and plain text files (up to 25MB). Set response_format to json (default) for structured output with extracted text and token count, or text for the raw extracted text. Privacy: Text parsing runs entirely in-memory on Venice’s infrastructure with zero data retention. Your documents are processed and immediately discarded — no content is stored or logged. Pricing: $0.01 per request.

​
Example (cURL)

curl -X POST https://api.venice.ai/api/v1/augment/text-parser \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -F "[email protected]" \
  -F "response_format=json"

Authorizations

​
Authorization
string
header
required

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

Body

multipart/form-data
​
file
file
required

The document file to parse. Supported formats: PDF, DOCX, PPTX, XLSX, and plain text files. Maximum size: 25MB.

​
response_format
enum<string>
default:json

The format of the response output. "json" returns structured JSON with text and token count, "text" returns only the extracted text.

Available options:
json,
text

Response

Text extraction completed successfully

Text parser response containing extracted text and token count.

​
text
string
required

The extracted text content from the document.

​
tokens
number
required

The token count of the extracted text.