DeepSeek logo

DeepSeek · Language Model

DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

163,840 tokens

Overview

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

DeepSeek V3.1 is available in OmnyChat. 163,840 token context window. Reasoning mode.

Key capabilities

  • 163,840 token context window
  • Reasoning mode

Using this model

In OmnyChat

Use DeepSeek V3.1 in OmnyChat and compare its results with other language models on the same task.

Best for: Chat and comparing answers on your own prompts.

Frequently asked questions

How do I use DeepSeek V3.1?

Open chat in OmnyChat and select DeepSeek V3.1. Model access and usage depend on your plan.

What does DeepSeek V3.1 support in OmnyChat?

163,840 token context window. Reasoning mode.

Related models