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 Omny. 163,840 token context window. Reasoning mode.
What it can do
- 163,840 token context window
- Reasoning mode
Using it in Omny
Use DeepSeek V3.1 in Omny and compare its results with other language models on the same task.
Best for: Chat and comparing answers on your own prompts.
Questions
How do I use DeepSeek V3.1?
Open chat in Omny and select DeepSeek V3.1. Model access and usage depend on your plan.
What does DeepSeek V3.1 support in Omny?
163,840 token context window. Reasoning mode.