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...
What is 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...
Specifications
- Developer: DeepSeek
- Context window: 163.8K tokens
- Max output: 32.8K tokens
- Input modalities: text
- Output modalities: text
- Input price: $0.2100 per 1M tokens
- Output price: $0.7900 per 1M tokens
- Knowledge cutoff: 2025-03-31
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Use DeepSeek V3.1 with PromptLayer
PromptLayer lets teams manage, evaluate, and observe prompts that run on DeepSeek V3.1 alongside every other model in their stack. Version prompts, run evals across models, and ship safe rollouts from the same dashboard.
Ready to try it yourself? Sign up for PromptLayer and start managing your prompts in minutes.