DeepSeek-OCR

DeepSeek-OCR is a comprehensive Optical Character Recognition (OCR) model thatanalyzes and understands complex documents. It excels at challenging OCR tasks,including recognizing mathematical formulas and processing text that is curved,rotated, or overlapping.

Managed API (MaaS) specifications

View model card in Model Garden

Model IDdeepseek-ocr-maas
Launch stageGA
Supported inputs & outputs
  • Inputs:
    Text,Documents,Images
  • Outputs:
    Text
Capabilities
Consumption options
Versions
  • DeepSeek-OCR
    • Launch stage: GA
    • Release date: October 23, 2025
Supported regions

Model availability

  • United States
    • us-central1

ML processing

  • United States
    • Multi-region
Limits

us-central1:

  • Max output: 8,192
  • Context length: 8,192

PricingSeePricing.

Deploy as a self-deployed model

To self-deploy the model, navigate to theDeepSeek-OCR model card in the Model Gardenconsole and clickDeploy model. For more information about deploying andusing partner models, seeDeploy a partner model and make predictionrequests.

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-02-19 UTC.