AI model · DeepSeek
DeepSeek V3.1
Model ID: deepseek/deepseek-chat-v3.1
- Input
- $0.25 per 1M tokens
- Output
- $0.95 per 1M tokens
- Context
- 164K tokens at once
- Max output
- 33K tokens per reply
- Released
- 21 Aug 2025 DeepSeek
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
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...
Sources
- DeepSeek: DeepSeek V3.1 on OpenRouter — read 2 Oct 2026