Skip to content

DeepSeek · OCR

DeepSeek-OCR

DeepSeek 🇨🇳OCRDeepSeek familyOpen weights. One of its sources says the weights are publicly available.
From Neosantara's listing:
DeepSeek OCR model for extracting text from images with high accuracy. Supports URLs and base64 images.
Max context
8K
Listings
5
Providers
5

Evidence and sources

Sources: Neosantara Inference data, Models.dev data, Hugging FacePrimary data from Neosantara Inference from Models.dev: name, weights availability from Hugging Face: release date

Advantages and trade-offs

Compared with 10 representative OCR models

Advantages

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

Vision

Listings

 Baidudeepseek-ocrSource: Baidu QianfanNot published by the provider—
 Neosantaradeepseek-ocrSource: Neosantara Inference dataNot published by the provider——
 Novita AInovita/deepseek/deepseek-ocrSource: LiteLLM data8K$0.03$0.03—

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

OCR

OCR ArenaSource: OCR Arena data · Nov 2026

Other

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark

Around the web

  • DeepSeek
    Welcome to our team — we are dedicated to exploring the essence of AGI, and …Welcome to our team — we are dedicated to exploring the essence of AGI, and embrace all who are passionate about AI. View Positions → 🎉 The official API for DeepSeek-V4-Flash has launched for public…

    deepseek.com

  • DeepSeek
    Welcome to our team — we are dedicated to exploring the essence of AGI, and …Welcome to our team — we are dedicated to exploring the essence of AGI, and embrace all who are passionate about AI. View Positions → 🎉 The official API for DeepSeek-V4-Flash has launched for public…

    deepseek.com

  • DeepSeek
    Section: > DeepSeek Chat with DeepSeek AI – your intelligent assistant for coding, content creation, …Section: > DeepSeek Chat with DeepSeek AI – your intelligent assistant for coding, content creation, file reading, and more ... (DeepSeek)助力编程代码开发、创意写作、文件处理 Section: > DeepSeek Chat with DeepSeek AI …

    download.deepseek.com

  • deepseek-v3.2 Model by Deepseek-ai | NVIDIA NIM
    DeepSeek-V3.2 Technical Report DeepSeek-V3.2-Exp Base Model DeepSeek Chat Interface DeepSeek Discord Community Olympiad Case Files …DeepSeek-V3.2 Technical Report DeepSeek-V3.2-Exp Base Model DeepSeek Chat Interface DeepSeek Discord Community Olympiad Case Files - IMO 2025, IOI 2025, ICPC World Finals, CMO 2025 submissions DeepSe…

    build.nvidia.com

  • DeepSeek | Langflow Documentation
    DeepSeek model to use. Default: deepseek-chat . api_base · String · Input parameter. Base URL …DeepSeek model to use. Default: deepseek-chat . api_base · String · Input parameter. Base URL for API requests. Default: https://api.deepseek.com . api_key · SecretString · Input parameter. Your Deep…

    docs.langflow.org

  • DeepSeek Platform
    🎉 The official API for DeepSeek-V4-Flash has launched for public beta, with significantly enhanced agent …🎉 The official API for DeepSeek-V4-Flash has launched for public beta, with significantly enhanced agent capabilities; the V4-Pro version remains unchanged for now. Click for details . Build your ap…

    platform.deepseek.com

  • deepseek-ai/DeepSeek-V3.1-Base · Hugging Face
    Docker Model Runner How to use deepseek-ai/DeepSeek-V3.1-Base with Docker Model Runner: docker model run hf.co/deepseek-ai/DeepSeek-V3.1-Base …Docker Model Runner How to use deepseek-ai/DeepSeek-V3.1-Base with Docker Model Runner: docker model run hf.co/deepseek-ai/DeepSeek-V3.1-Base Browse Quantizations to use this model in llama.cpp , Oll…

    huggingface.co

  • DeepSeek models | Together AI
    Browse modelsDeploy own model new Chat DeepSeek V4 Pro new Chat DeepSeek V4 Flash 0731 …Browse modelsDeploy own model new Chat DeepSeek V4 Pro new Chat DeepSeek V4 Flash 0731 Chat DeepSeek-V3-0324 Chat DeepSeek-R1-0528 Chat DeepSeek R1 Distilled Llama 70B Free Chat DeepSeek-R1-0528 Thro…

    together.ai

  • deepseek-ai/DeepSeek-V3 - Demo - DeepInfra
    Tier · Input · Output Flex (0.8×) Learn More · $0.256 · $0.712 per 1M …Tier · Input · Output Flex (0.8×) Learn More · $0.256 · $0.712 per 1M tokens DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token…

    deepinfra.com

  • DeepSeek - Wikipedia
    Discontinued · DeepSeek-V2, DeepSeek-V2-Chat DeepSeek-V2-Lite, DeepSeek-V2-Lite-Chat DeepSeek-Coder-V2 DeepSeek-V2.5 · Developed multi-head latent attention (MLA). Also …Discontinued · DeepSeek-V2, DeepSeek-V2-Chat DeepSeek-V2-Lite, DeepSeek-V2-Lite-Chat DeepSeek-Coder-V2 DeepSeek-V2.5 · Developed multi-head latent attention (MLA). Also used mixture of experts (MoE). …

    en.m.wikipedia.org

Also known as: deepseek-ai/deepseek-ocr, novita/deepseek/deepseek-ocr

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works