DeepSeek V3.1
Open weightsDeepSeek
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...
Context: 164K tokensReleased: Aug 21, 20250 up · 0 down
0
Reviews (0)
Sign in to vote and write a review.
No reviews yet — be the first to review DeepSeek V3.1.