DeepSeek V3.1
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...
The figures
- Made by
- DeepSeek
- Model ID
- deepseek/deepseek-chat-v3.1
- Input
- $0.25 per million tokens
- Output
- $0.95 per million tokens
- Context window
- 164K tokens
- Longest answer
- 33K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 21 Aug 2025
Read on 3 Oct 2026.