Support in the post-AI era is a completely different job... the number of times I've learned about a feature that was shipped and available, and I have never heard of it, is happening a little bit too often... I can't tell y'all what I just tested, but this is how I feel
I sneak myself into the beta use of Parse Light and can finally talk about this!
It's faster, cheaper, and the parse quality is also better than the previous light version (how?!). It powers the feature request flow I've built, saving me so much time and effort that I don't need to worry about file format support, layout, or OCR for images. Give it a try and hit support up (<- me π) if you have any questions!
today, we're launching Light Parse
Extend can now parse documents up to 70% cheaper than other solutions
- light parse starts at $0.00625 per page, and scales down significantly with volume discounts
- it's SOTA on Databricks OfficeQA Pro (a 3rd party agent benchmark) among all non-agentic parsing providers
our ML/AI team trained smaller and more efficient layout, table, and form vision models to enable significant cost reduction without impacting accuracy on many types of documents
live today for all users!
today, we're launching Light Parse
Extend can now parse documents up to 70% cheaper than other solutions
- light parse starts at $0.00625 per page, and scales down significantly with volume discounts
- it's SOTA on Databricks OfficeQA Pro (a 3rd party agent benchmark) among all non-agentic parsing providers
our ML/AI team trained smaller and more efficient layout, table, and form vision models to enable significant cost reduction without impacting accuracy on many types of documents
live today for all users!
we're throwing a office warming party!
come check out our beautiful new space in NYC next to Union Square
(rumor has it there will be a cocktail menu with document themed drinks)