यह पेज क्या बताता है
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...
- DeepSeek · deepseek/deepseek-chat-v3.1
- text->text · China model route
- 32,768 context · $0.15 input