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...
In / out price$0.25/$0.95per 1M tokens
Context
164K tokens
Parameters
684.5BMoE256 experts · 8 per token
Modalities
→
Released
Aug 21, 2025
0 up · 0 downCompare with another model
Net score over time
Oct 14 · 0Reviews (0)
Sign in to vote and write a review.
No reviews yet — be the first to review DeepSeek V3.1.