DeepSeek: DeepSeek V3.1
- by deepseek
- deepseek/deepseek-chat-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...
What the numbers mean
- Context window163,840 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 120,000 words, or 246 pages.
- Max output147,456 tokens
- The longest single reply it can write: about 110,000 words.
- Input price$0.25 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$0.95 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
- Knowledge cutoff2025-03-31
- The last date its training data covers. It does not know about anything after that unless you put it in the prompt.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltyinclude_reasoninglogit_biaslogprobs