DeepSeek Watch posted an update
DeepSeek’s OCR API can extract text from PDFs, Word and PowerPoint files, as well as images, returning results page by page. The company’s documentation gives developers a useful operational detail: successful pages are billed, even if the client disconnects before recognition finishes.
Why it mattersDeepSeek says failed or timed-out recognition is not billed. The API allows up to 15 recognitions in progress at once; exceeding that limit returns an error. Its guide also says the uploaded file is not stored in the Files API or passed to a chat model. For developers, the distinction between ending a connection and cancelling a job is worth knowing before a large batch starts. DeepSeek’s documentation is the source for these service details, not an independent performance assessment.
Discuss: Should APIs be required to make it clearer when disconnecting a client does not cancel a billable job?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.