DeepSeek V3.1
A
AI Socratic
DeepSeek released DeepSeek V3.1 on August 21, 2025. The registry currently records it as open weights.
Model publication
deepseek-ai
DeepSeek V3.1Open the source for DeepSeek V3.1
Open weights
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 training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
- Licence
- mit
- Architecture
- DeepseekV3ForCausalLM
- Parameters
- 685B
- Context
- 163.8K tokens
- Artifact format
- safetensors
- Quantization
- fp8 8-bit
- Download size
- 641 GB
Hardware to run it (inference, estimated)
766 GB VRAM minimum · 957 GB recommended · 957 GB system RAM · 642 GB storage
Estimated from parameter count and stored precision; verify against the selected runtime and context length.
Benchmarks
No benchmark observation recorded for this model.
About the Authors
A