DeepSeek V3.1

DeepSeek · deepseek/deepseek-chat-v3.1

← Back to leaderboard

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...

open weightstexttext->text

Context

Max context: 163840
Max output: 32768

Pricing

Input / 1M: 0.21
Output / 1M: 0.79
Blend / 1M: 0.50

Quality

Quality index:

Provider

Provider: DeepSeek
Moderated: no