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.

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 Not supported Batch predictions
Usage types	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-west2
	ML processing	United States Multi-region
Quota limits	us-west2: Max output: 32,768 Context length: 163,840
Pricing	See Pricing.