Skip to main content
The Text Parser API extracts text from a document without running model inference. Use it when your application needs to inspect, store, index, or reuse document content before sending it to a model. Supported inputs include PDF, DOCX, PPTX, XLSX, and plain text files up to 25 MB.

​
Parse a Document

Upload the file as multipart/form-data:
The default json response format returns the extracted text and its token count. Use response_format=text when you only need the extracted text.

​
Text Parser or Chat File Input?

Both features extract document content, but they serve different workflows:

​
Typical Pipeline

1

Parse the file

Upload the source document and request a JSON response.
2

Inspect the output

Check the token count against the target model’s context window. Trim or split large documents before inference.
3

Use the text

Add it to a chat prompt, generate embeddings for retrieval, or save it in your own data store.
Parsing runs in memory with zero data retention. Venice processes the uploaded document and immediately discards it without storing or logging its content.
The Text Parser API is experimental. Its request and response format may change without notice.