DeepSeek V3.1
by 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 training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
Specifications
Technical details and pricing.
Benchmarks
10 benchmark scores from Artificial Analysis.
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Frequently Asked Questions
What is DeepSeek V3.1 good for?
Use DeepSeek V3.1 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.
How much does DeepSeek V3.1 cost?
Pricing is based on usage. Current rates are $0.59/1M tokens for input and $1.69/1M tokens for output.
Can I try DeepSeek V3.1 for free?
Yes. You can start a chat instantly and test the model before deciding on a plan.
Does DeepSeek V3.1 support images or audio?
DeepSeek V3.1 focuses on text-based tasks.
Similar Models
Other models you might want to explore.
Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.