Model Hubs & Serving

Dolphin

Document Image Parsing via Heterogeneous Anchor Prompting

Status
Generally available
Last checked
Checked · Oct 6, 2026
License
Open source
Pricing
Free tier · from $0
Visit Dolphin Compare with alternatives

What it is

Dolphin is a cutting-edge model for parsing document images using advanced prompting techniques, enhancing the accuracy and efficiency of document analysis tasks.

Dolphin stands out with its unique approach to heterogeneous anchor prompting, offering superior accuracy in parsing document images compared to traditional OCR methods.

When it fits — and when it doesn’t

A good fit for

  • Teams working on document analysis projects who require high accuracy in parsing

  • Researchers focusing on improving OCR technologies for diverse document types

Look elsewhere if

  • Projects requiring real-time processing of large volumes of documents due to computational demands

  • Applications needing minimal setup and configuration, as self-hosting requires technical expertise

Known weaknesses

Each one links to the public issue, changelog or docs page it came from, where we have one.

  1. 01

    Limited integrations with other document processing tools

    Lacks native support for popular libraries like PDF.js or DocuSign

  2. 02

    Performance issues with large document sets

    Processing times increase exponentially with the number of documents

What it does well

  • Advanced heterogeneous anchor prompting for document image parsing

  • High accuracy in document analysis tasks

  • Efficient processing of various document formats

Pricing

Free tier
YesOpen source — free to use
Paid from
$0
Model
Flat rate
Enterprise plan
No

Pricing not independently confirmed — check the vendor’s page.

Performance benchmarks

How Fast Is It?

Set up Dolphin

Setup steps, common gotchas and what to check after 30 days.

Open the setup guide →