Some or all of the information on this page might not apply to Cloud de Confiance by S3NS. See Differences from Google Cloud for more details.

DeepSeek-OCR

Caution: As of July 21, 2026, the deepseek-ocr-maas endpoint is deprecated and will be retired on October 21, 2026. For more information, see Open model deprecations.

DeepSeek-OCR is a comprehensive Optical Character Recognition (OCR) model that analyzes 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

Pricing

Model ID	`deepseek-ocr-maas`
Modalities	Text Input and output Image Input only Audio Not supported Video Not supported
Capabilities	Function calling Not supported Structured output Not supported Thinking Not supported
Consumption options	Provisioned Throughput Supported Batch inference Not supported Pay-as-you-go Standard PayGo Supported Fixed quota Not supported
Supported regions	Model availability	United States: `us-central1`
Supported regions	ML processing	Multi-region: `us`
Quotas	`us-central1`: 8,192 maximum output, 8,192 context length
Versions	`DeepSeek-OCR` Launch stage: GA Release date: October 23, 2025

Deploy as a self-deployed model

To self-deploy the model, navigate to the DeepSeek-OCR model card in the Model Garden console and click Deploy model. For more information about deploying and using partner models, see Deploy a partner model and make prediction requests.