NewsSeptember 22, 2025

DeepSeek-V3.1 is now DeepSeek-V3.1-Terminus

The latest update builds on V3.1's strengths while addressing key user feedback.

What's improved?

  • Language consistency: fewer CN/EN mix-ups & no more random chars.
  • Agent upgrades: stronger Code Agent & Search Agent performance.

DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version.

DeepSeek V3.1 Terminus Benchmark

Available now on: App / Web / API

Open-source weights here: DeepSeek-V3.1-Terminus - Hugging Face

Thanks to everyone for your feedback. It drives us to keep improving and refining the experience!

Related content

DeepSeek-V3.1 Release

DeepSeek-V3.1 introduces hybrid Think & Non-Think inference, faster thinking, stronger agent skills, Anthropic API support, and 128K context.

Read more

Introducing DeepSeek-V3.2-Exp

DeepSeek-V3.2-Exp debuts DeepSeek Sparse Attention (DSA) for faster, more efficient training & inference on long context, with API prices cut by 50%+.

Read more

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DeepSeek-V3.2 and V3.2-Speciale launch with world-leading reasoning, thinking in tool-use, and gold-medal performance in IMO, CMO, ICPC & IOI 2025.

Read more