skip to content
gigarouter gigarouter
models / vision-language · coming soon

DeepSeek OCR 2

deepseek-ai/DeepSeek-OCR-2

published Jan 2026 · updated Feb 2026

DeepSeek OCR 2 is a vision-language model that performs optical character recognition and document understanding using a novel encoder (DeepEncoder V2) that dynamically reorders visual tokens based on causal reasoning.

est. price
~$0.626
/ 1k images · estimated, set at launch
API providers
0
downloads / mo
3.3M
license
apache-2.0

specs

TaskOCR / Document Understanding
ArchitectureDeepEncoder V2 with causal visual token reordering
Dynamic Resolution(0-6)x768x768 + 1x1024x1024 pixels
Visual Tokens(0-6)x144 + 256 tokens

about this model

DeepSeek-OCR-2 is a vision-language model (VLM) that performs optical character recognition and document understanding by dynamically reordering visual tokens based on causal reasoning, inspired by human visual perception.

Core Innovation

Conventional VLMs process visual tokens in a rigid raster-scan order. DeepSeek-OCR-2 introduces DeepEncoder V2, which endows the encoder with causal reasoning capabilities to intelligently reorder visual tokens prior to LLM content interpretation. This enables two-cascaded 1D causal reasoning structures for effective 2D image understanding, particularly for complex layouts.

Benchmark Performance

On the olmOCR-bench, DeepSeek-OCR-2 achieves the following scores:

BenchmarkScore
Overall76.3
Arxiv Math82.0
Old Scans Math72.0
Table Tests77.4
Old Scans33.8
Multi Column79.0
Long Tiny Text90.7

On OmniDocBench, it surpasses GOT-OCR2.0 (256 tokens/page) using only 100 vision tokens, and outperforms MinerU2.0 (6000+ tokens per page) while utilizing fewer than 800 tokens. In production, it can generate training data at a scale of 200k+ pages per day on a single A100-40G.

Model Capabilities

Supports dynamic resolution with a default mode of (0-6)×768×768 + 1×1024×1024, producing (0-6)×144 + 256 visual tokens. Two main prompt modes are available: for document conversion use <image>\n<|grounding|>Convert the document to markdown.; for OCR without layouts use <image>\nFree OCR.

DeepSeek-OCR 2 visual causal flow diagram

For further details, see the paper on arXiv.

best for

FAQ

What is DeepSeek OCR 2 best for?

It excels at OCR and document understanding, particularly converting documents to markdown while preserving layout, and achieving high accuracy with fewer visual tokens than prior models.

How does it compare to other OCR models?

On OmniDocBench it surpasses GOT-OCR2.0 (256 tokens/page) using only 100 vision tokens and outperforms MinerU2.0 (6000+ tokens per page) with fewer than 800 tokens.

What are the input and output formats?

Input: an image plus a prompt (e.g., "<image>\n<|grounding|>Convert the document to markdown."). Output: extracted text or markdown.

How can I call it via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key, specifying the model name "deepseek-ai/DeepSeek-OCR-2" in the request.

What license is the model released under?

The model card does not specify a license; please check the official repository or contact DeepSeek AI for current licensing terms.

not yet live

We're benchmarking and onboarding DeepSeek OCR 2 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related vision-language models

compare all →