DeepSeek: DeepSeek V3.1
deepseek
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 window
- 32,768 tokens
- Input cost
- $0.15 / 1M
- Output cost
- $0.75 / 1M
- Latency (p50)
- —