[Models](/models)/[Text Extraction](/models?category=text_extraction)/baidu/Unlimited-OCR

HFOCRmit

# Unlimited-OCR

by baidu

One-shot long-horizon OCR for multi-page documents and PDFs

2.9Mdl/month

4,133likes

3.3Bparams

[HuggingFace](https://huggingface.co/baidu/Unlimited-OCR)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`baidu/Unlimited-OCR`

## Deploy Unlimited-OCR

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

Unlimited-OCR is Baidu's 3B vision-language OCR model built for one-shot parsing of long documents. Rather than reading a page at a time, it ingests multi-page images and PDFs in a single pass with a 32K-token context, preserving layout, reading order, tables, and formatting instead of returning a flat bag of words. It extends the DeepSeek-OCR line of compressed-token OCR with multi-page parsing and n-gram repetition guards, and runs efficiently under vLLM or SGLang.

On Mixpeek, Unlimited-OCR powers the OCR extractor when the goal is faithful structured text from whole documents (contracts, reports, scanned decks) so an agent can search the recovered text, tables, and headings, not just raw pixels. Layout-preserving output makes downstream chunking and section-aware retrieval far cleaner than character-level OCR.

## Architecture

3B-parameter vision-language transformer (BF16) with a compressed-vision-token design that maps document images to a small token budget, then decodes structured text with a 32,768-token context. Two input modes trade resolution for cost (gundam 640px, base 1024px); custom n-gram repetition avoidance stabilizes long-form decoding. Served via Transformers, vLLM, and SGLang.

## How it runs

.dataflow-R15f6b .df-packets-static{display:none} @media (prefers-reduced-motion: reduce){ .dataflow-R15f6b .df-packets-anim{display:none} .dataflow-R15f6b .df-packets-static{display:inline} .dataflow-R15f6b .df-toggle{display:none} }

Pause

Inference INPUT MODEL OUTPUT Image object Text object Unlimited-OCR mp.inference Text vector Vector store MVS Unlimited-OCR → embeddings, indexed for search

Unlimited-OCR takes image and text, and Mixpeek indexes what it emits.

## Mixpeek SDK Integration

IngestRetrieve

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so Unlimited-OCR runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace\_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns\_your\_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API\_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection\_id: "col\_your\_collection",
      documents: \[
        {
          document\_id: "asset-00412",
          // The model produces text, so it lands in payload. Give the
          // collection a text vector index and embed that text to make it
          // searchable rather than only filterable.
          payload: { extracted\_text: modelOutput, source\_key: "archive/2026/asset-00412" },
          vectors: { "text-embedding": embeddingOfModelOutput },
        },
      \],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// universal\_extractor@v1 runs google/gemini-embedding-2
// (3072-d) over a bucket, with no inference of your own.

## Capabilities

*   One-shot multi-page document and PDF parsing
*   Layout, reading-order, table, and formula preservation
*   32K-token long-context decoding
*   Multilingual OCR under an MIT license

## Use Cases on Mixpeek

Index scanned contracts, reports, and slide decks as searchable structured text

Recover tables and headings for section-aware chunking before retrieval

Give agents faithful document text instead of raw page images

High-volume PDF ingestion where per-page OCR is too slow

## Common Pipeline Companions

[

Alibaba-NLP/gme-Qwen2-VL-2B-Instruct

Embed recovered document text + page images for hybrid search

](/model/Alibaba-NLP/gme-Qwen2-VL-2B-Instruct)[

Qwen/Qwen3-Reranker-4B

Rerank OCR-recovered passages for precise answers

](/model/Qwen/Qwen3-Reranker-4B)

## Explore on Mixpeek

[

More Text Extraction models

Compare alternatives in this category

](/models?category=text_extraction)[

Best Document AI Platforms

Hand-picked tools & platforms compared

](/curated-lists/best-document-ai-platforms)[

OCR & Document AI Internals

Deep-dive technical guide

](/guides/ocr-document-ai-internals)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

FrameworkHF

Organizationbaidu

FeatureOCR

Outputtext + bbox

Modalitiesvideo, image, document

RetrieverText-in-Image

Parameters3.3B

Licensemit

Downloads/mo2.9M

Likes4,133

[

### Research Paper

Unlimited-OCR (Baidu)

arxiv.org](https://huggingface.co/baidu/Unlimited-OCR)

### Build a pipeline with Unlimited-OCR

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

### Alternative Models

[

microsoft/trocr-large-printed

OCR

](/model/microsoft/trocr-large-printed)[

PaddlePaddle/paddleocr

OCR

](/model/PaddlePaddle/paddleocr)[

zai-org/GLM-OCR

OCR

](/model/zai-org/GLM-OCR)[

lightonai/LightOnOCR-2-1B

OCR

](/model/lightonai/LightOnOCR-2-1B)

### Related in Text Extraction

[

microsoft/codebert-base

Code Extraction

](/model/microsoft/codebert-base)[

Salesforce/codet5p-110m-embedding

Code Extraction

](/model/Salesforce/codet5p-110m-embedding)[

nomic-ai/nomic-embed-code

Code Extraction

](/model/nomic-ai/nomic-embed-code)[

Salesforce/SFR-Embedding-Code-2B\_R

Code Extraction

](/model/Salesforce/SFR-Embedding-Code-2B_R)