Unlimited OCR
Ranked 6 of 11 OCR models by recommenders
Recommended for reading very long documents in one pass with a clever sliding-window attention design, and essentially free to run on a decent computer.
Recommended for reading very long documents in one pass with a clever sliding-window attention design, and essentially free to run on a decent computer.
7 people gave an opinion
- recommend it
- 7
- criticize it
- 0
- approval share
- 100%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 7 people recommend itNeeds 10 or more, not met.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Clever attention design for long documents
“I also think the attention approach (always attend to the image/prefix, with a sliding window for local context) is neat!”
Comment from 24 Jun 2026 in “Unlimited OCR: One-Shot Long-Horizon Parsing” “found a clever architectural hack to stop AI from hoarding memory when reading long documents”
Comment from 23 Jun 2026 in “Unlimited OCR: One-Shot Long-Horizon Parsing” Good results in people's own testing
“it seems to be working very well from the small parts I have double checked”
Comment from 23 Jun 2026 in “Unlimited OCR: One-Shot Long-Horizon Parsing” “the 'Unlimited OCR' model is very good”
Comment from 30 Jun 2026 in “Claude Code Is Steganographically Marking Requests” Competitive with Mistral OCR
“This looks more promising than what Mistral just launched”
Comment from 23 Jun 2026 in “Unlimited OCR: One-Shot Long-Horizon Parsing” “I gave it a whirl and it does seem pretty competitive”
Comment from 4 Jul 2026 in “Leanstral 1.5: Proof Abundance for All”
Other OCR models people recommend
The four most recommended other OCR models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Mistral OCR | 69 | 40 | 63% | 12 | — | — |
| PaddleOCR | 19 | 4 | 83% | 8 | — | Approved |
| GLM-OCR | 16 | 4 | 80% | 7 | — | Approved |
| DeepSeek-OCR | 12 | 4 | 75% | 9 | — | Approved |
| Unlimited OCRThis page | 7 | 0 | 100% | 3 | — | — |
What people said
All 7 comments that mention it, newest first. Each links to the original comment.
“essentially free to run on a decent computer, other than electricity costs”
“I gave it a whirl and it does seem pretty competitive”
“the 'Unlimited OCR' model is very good”
“I also think the attention approach (always attend to the image/prefix, with a sliding window for local context) is neat!”
“This looks more promising than what Mistral just launched”
“it seems to be working very well from the small parts I have double checked”
“found a clever architectural hack to stop AI from hoarding memory when reading long documents”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.