DeepSeek V3.1
DeepSeek V3.1 is a large language model made by DeepSeek, added to the catalog on 21 Aug 2025. It has a context window of 163,840 tokens and costs $0.25 per 1M input tokens and $0.95 per 1M output tokens. It accepts text and produces text. Typical uses: enhance research workflows with advanced reasoning, improve code generation efficiency and integrate structured tool calling in projects.
Price checked ยท source: OpenRouter
What DeepSeek V3.1 is
DeepSeek V3.1, developed by deepseek and released in August 2025, is a text-to-text model that offers a large context window of up to 163,840 tokens. It supports both thinking and non-thinking modes, allowing users to customize reasoning behavior. With its hybrid reasoning capabilities, the model excels in tool use, code generation, and reasoning efficiency. DeepSeek V3.1 is designed for research, coding, and agentic workflows, making it a versatile choice for various applications. The model supports structured tool calling and integrates seamlessly into workflows that require advanced text processing.
Key features
- Hybrid reasoning modes with prompt templates
- Supports up to 163,840 tokens
- Efficient FP8 microscaling for inference
- Customizable reasoning behavior
- Structured tool calling and code agents
Typical uses
- Enhance research workflows with advanced reasoning
- Improve code generation efficiency
- Integrate structured tool calling in projects
- Facilitate agentic workflows in various domains
DeepSeek V3.1 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.25 |
| Output, per 1M tokens | $0.95 |
| Cached input read, per 1M tokens | $0.13 |
No price change since it was added on 21 Aug 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0004 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0070 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0094 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.039 |
DeepSeek V3.1 specifications
| Model id | deepseek/deepseek-chat-v3.1 |
|---|---|
| Version | deepseek-chat-v3.1 |
| Context window | 163,840 tokensAbout 122,880 English words |
| Max output | 147,456 tokens |
| Knowledge cutoff | 2025-03-31 |
| Added to catalog | 21 Aug 2025 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
Artificial intelligence promises to profoundly reshape human existence for the better. In work, AI will automate mundane tasks, liberating us to focus on strategic, creative, and interpersonal roles, fostering greater job satisfaction and innovation. For leisure, hyper-personalised AI assistants will curate unique entertainment, travel, and learning experiences, maximising our precious free time and expanding our horizons. Most excitingly, AI is set to democratise creativity itself. It will act as a collaborative partner, breaking down technical barriers and enabling anyone to compose music, generate art, or write stories, transforming consumers into creators. This fusion of human imagination with machine capability will unlock unprecedented forms of artistic expression, fundamentally upending how we create, work, and play.
Compare DeepSeek V3.1
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.