DeepSeek Launches V3.1 Model

DeepSeek Launches V3.1 Model

21 August 2025

DeepSeek has launched its latest AI model, the V3.1, featuring advancements in reasoning, coding, and tool use. The model supports both 'thinking' (chain-of-thought reasoning) and 'non-thinking' (direct) generation modes, switchable via a chat template. This hybrid approach marks a shift in research focus towards the 'agent era'.

The V3.1 boasts 671B total parameters, with 37B activated per token, utilising a Mixture-of-Experts (MoE) design to lower inference costs. It has a 128K token context window and was trained using FP8 microscaling for efficient arithmetic on next-gen hardware. DeepSeek claims the model can deliver answers faster than its previous R1 model. The company will adjust the costs for using the model's API starting September 6.

DeepSeek's V3.1 is available on Hugging Face and supports multi-turn conversations with explicit tokens for system prompts, user queries, and assistant responses. Benchmarks show strong performance across general knowledge, coding, maths, and tool use.

AI generated content may differ from the original.

Published on 21 August 2025
aigptdeepseekmachinelearningopensourcechina
  • DeepSeek V3.1 Model Unveiled

    DeepSeek V3.1 Model Unveiled

    Read more about DeepSeek V3.1 Model Unveiled
  • OpenAI Releases Open Source Models

    OpenAI Releases Open Source Models

    Read more about OpenAI Releases Open Source Models
  • OpenAI Releases Open Models

    OpenAI Releases Open Models

    Read more about OpenAI Releases Open Models
  • Zhipu AI unveils GLM-4.5

    Zhipu AI unveils GLM-4.5

    Read more about Zhipu AI unveils GLM-4.5
DeepSeek Launches V3.1 Model