Back to Models

DeepSeek: DeepSeek V3.1

deepseek-chat-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. It extends the DeepSeek-V3 base with a two-phase long-context...

Modalities

Input

text

Output

text
Pricing
Cost per 1 million tokens
Input
$0.18
Output
$0.9
Model Specs
Context Window
163,840
Max Output
163,840
Release Date
2025-08-21
Knowledge Cutoff
2025-07
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2025-08-21

Provider: