DataLearner logo
UN

Unlimited-OCR

Vision modelOCR model

Unlimited-OCR

Release date: 2026-06-22Updated: 2026-07-17 21:57:55.3551,185
Live demoGitHubHugging FaceCompare
Parameters
3.336B
Context length
32K
Chinese support
Supported
Reasoning ability

Unlimited-OCR is a vision model from Baidu, released on 2026-06-22. It accepts text and image input and returns text output. The cataloged parameter count is 3.336B, with 500M active parameters per inference. The recorded context window is 32K, and the recorded maximum output is 32K. Cataloged capabilities include Multilingual and OCR model. The checkpoint is listed under the MIT license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Unlimited-OCR

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
32K tokens
Max output length
32K tokens
Model type
Vision model
Modality (in / out)
Text, Image → Text
Release date
2026-06-22
Model file size
6.67 GB BF16 safetensors
MoE architecture
Yes
Total params / Active params
3.336B / 500M
Knowledge cutoff
No data
Unlimited-OCR

Open source & experience

Code license
MIT License
Weights license
MIT License- Commercial use permitted
GitHub repo
https://github.com/baidu/Unlimited-OCR
Hugging Face
https://huggingface.co/baidu/Unlimited-OCR
Live demo
No live demo
Unlimited-OCR

Official resources

Paper
Paper
DataLearnerAI blog
No blog post yet
Unlimited-OCR

API details

API speed
4/5
No public API pricing yet.
Unlimited-OCR

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Unlimited-OCR

Publisher

Unlimited-OCR

Model Overview

Unlimited-OCR is a vision model from Baidu, released on 2026-06-22.

It accepts text and image input and produces text output. Its cataloged capabilities include Multilingual and OCR model. The cataloged parameter count is 3.336B, with 500M active parameters per inference. The recorded context window is 32K, and the recorded maximum output is 32K.

The checkpoint is listed under the MIT license, with the license link included in the model references. The page links 3 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

Unlimited-OCR

FAQ

What is Unlimited-OCR?

Unlimited-OCR is a vision model from Baidu, released on 2026-06-22. It accepts text and image input and returns text output. The cataloged parameter count is 3.336B, with 500M active parameters per inference. The recorded context window is 32K, and the recorded maximum output is 32K. Cataloged capabilities include Multilingual and OCR model. The checkpoint is listed under the MIT license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does Unlimited-OCR support?

The current model record lists text and image as input and text as output.

What are the main recorded specifications for Unlimited-OCR?

The cataloged parameter count is 3.336B, with 500M active parameters per inference. The recorded context window is 32K, and the recorded maximum output is 32K. Fields without a source-backed value remain undisclosed.

Why is no API price shown for Unlimited-OCR?

Open-weight OCR checkpoint; no first-party hosted price published.

Why are no benchmark results shown for Unlimited-OCR?

Official ParseBench/OCR metrics are not represented by the current benchmark catalog.

Is Unlimited-OCR open source?

The checkpoint is listed under the MIT license, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code