[Models](/models)/[Text Extraction](/models?category=text_extraction)/lightonai/LightOnOCR-2-1B

HFOCRApache-2.0

# LightOnOCR-2-1B

by lightonai

State-of-the-art 1B-parameter end-to-end multilingual OCR with bounding box localization

730Kdl/month

1Bparams

[HuggingFace](https://huggingface.co/lightonai/LightOnOCR-2-1B)[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

`lightonai/LightOnOCR-2-1B`

## Deploy LightOnOCR-2-1B

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

LightOnOCR-2-1B is a 1B-parameter vision-language model that sets the top score on OlmOCR-Bench (83.2) while being compact enough for efficient deployment. Built on a native-resolution ViT initialized from Mistral-Small-3.1, it handles page images up to 1540px on the longest edge with particularly strong performance on ArXiv papers, scanned documents with math, and complex tables.

On Mixpeek, LightOnOCR-2-1B extracts text from documents, scanned pages, and images with high accuracy, powering full-text search across document collections. An image-localization variant adds bounding box predictions without degrading OCR quality.

## Architecture

Three-component VLM: native-resolution Vision Transformer (initialized from Mistral-Small-3.1) as encoder, multimodal projector, and language model decoder. Accepts page images up to 1540px longest edge. Optional bounding box localization via coordinate tokens introduced during pretraining and refined with RLVR.

## Mixpeek SDK Integration

IngestRetrieve

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so LightOnOCR-2-1B 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

*   Top score on OlmOCR-Bench (83.2) among 1B-class models
*   Native-resolution processing up to 1540px
*   Multilingual OCR with strong French and scientific document support
*   Optional bounding box localization variant
*   Apache 2.0 open-source

## Use Cases on Mixpeek

High-accuracy document digitization for scanned archives and PDFs

Scientific paper and technical document text extraction

Multilingual document search across enterprise content libraries

## Benchmarks

Dataset

Metric

Score

Source

OlmOCR-Bench

Score

83.2

LightOn AI, 2025: LightOnOCR paper

ArXiv papers subset

Score

Best in class

LightOn AI, 2025: LightOnOCR paper

## Performance

Input SizeUp to 1540px longest edge

GPU Latency~25ms / page (A100)

CPU Latency~320ms / page

GPU Throughput~40 pages/sec (A100)

GPU Memory~2.2 GB

## Common Pipeline Companions

[

BAAI/bge-m3

Embed extracted text for multilingual search

](/model/BAAI/bge-m3)[

microsoft/layoutlmv3-base

Layout analysis for document structure

](/model/microsoft/layoutlmv3-base)

## 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

Organizationlightonai

FeatureOCR

Outputtext + bbox

Modalitiesvideo, image, document

RetrieverText-in-Image

Parameters1B

LicenseApache-2.0

Downloads/mo730K

[

### Research Paper

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

arxiv.org](https://arxiv.org/abs/2601.14251)

### Build a pipeline with LightOnOCR-2-1B

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)[

deepseek-ai/DeepSeek-OCR-2

OCR

](/model/deepseek-ai/DeepSeek-OCR-2)

### 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)