DeepSeek-V3.1

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in hybrid thinking modes, tool calling, and thinking efficiency.

Managed API (MaaS) specifications

View model card in Model Garden

Model ID	deepseek-v3.1-maas
Launch stage	GA
Supported inputs & outputs	Inputs: Text, Documents Outputs: Text
Capabilities	Supported Batch predictions Function calling Structured output Not supported
Consumption options	Supported Dynamic shared quota Not supported Fixed quota Provisioned Throughput
Versions	deepseek-v3.1-maas Launch stage: GA Release date: August 28, 2025
Supported regions
	Model availability	United States us-central1
	ML processing	United States Multi-region
Limits	us-central1: Max output: 32,768 Context length: 163,840
Pricing	See Pricing.

Deploy as a self-deployed model

To self-deploy the model, navigate to the DeepSeek-V3.1 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.