DE

DeepSeek-OCR

Vision modelOCR modelDeepSeek OCRDeepSeek OCR

DeepSeek-OCR

Release date: 2025-10-20Updated: 2026-06-14 23:13:18.4461,614
Parameters
3B
Context length
No data
Chinese support
Not supported
Reasoning ability

DeepSeek-OCR is an AI model published by DeepSeek-AI, released on 2025-10-20, for Vision model, with 3B parameters, requiring about 6.67 GB storage, under the MIT License license.

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

DeepSeek-OCR

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
No data
Max output length
No data
Model type
Vision model
Modality (in / out)
Text, Image → Text
Release date
2025-10-20
Model file size
6.67 GB
MoE architecture
No
Total params / Active params
3B / N/A
Knowledge cutoff
No data
DeepSeek-OCR

Open source & experience

Code license
Weights license
MIT License- 免费商用授权
Live demo
No live demo
DeepSeek-OCR

Official resources

DataLearnerAI blog
No blog post yet
DeepSeek-OCR

API details

API speed
3/5
No public API pricing yet.
DeepSeek-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

DeepSeek-OCR

Publisher

DeepSeek-OCR

Model Overview

DeepSeek-OCR is an AI model published by DeepSeek-AI, released on 2025-10-20, for Vision model, with 3B parameters, requiring about 6.67 GB storage, under the MIT License license.

DataLearner on WeChat

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

DataLearner WeChat QR code