DeepSeek: DeepSeek V3.1 (free)
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. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. 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.
DeepSeek: DeepSeek V3.1 (free)
Goto ChatEnter your question, AI will answer for you
Get Inspired
Try these example questions to see what DeepSeek: DeepSeek V3.1 (free) can do
Explain quantum computing in simple terms
如何解二次方程？
Какие ключевые различия между Python и JavaScript?
Erklären Sie das Konzept der Rekursion in der Programmierung
相対性理論とは何ですか？
Como funciona o aprendizado de máquina?
Quelles sont les meilleures pratiques pour l'accessibilité web ?
اشرح عملية التمثيل الضوئي
