# 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 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.

## Model Information

- **Organization**: [DeepSeek](/llm.txt)
- **Slug**: deepseek-chat-v3-1
- **Available at Providers**: 11
- **Release Date**: August 21, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIMLAPI](/llm/aimlapi.txt) | DeepSeek V3.1 |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | DeepSeek V3.1 | 0.15 | 0.75 |  | [View](https://openrouter.ai/deepseek/deepseek-chat-v3.1) |
| [ValorGPT](/llm/valorgpt.txt) | DeepSeek V3.1 |  |  |  | [View](https://www.valorgpt.com/models/deepseek-deepseek-chat-v3.1) |
| [Yupp](/llm/yupp.txt) | DeepSeek V3.1 Thinking (OpenRouter) |  |  |  |  |
| [ZenMUX](/llm/zenmux.txt) | DeepSeek: DeepSeek V3.1 | 0.28 | 1.11 |  |  |
| [LangDB](/llm/langdb.txt) | deepseek-chat-v3.1 |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | DeepSeek: DeepSeek V3.1 | 0.15 | 0.75 |  |  |
| [RedPill](/llm/redpill.txt) | DeepSeek V3.1 | 1.00 | 2.50 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/deepseek/deepseek-chat-v3.1 |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | deepseek-chat-v3.1 | 0.17 | 0.83 |  |  |
| [Writingmate](/llm/writingmate.txt) | DeepSeek: DeepSeek V3.1 |  |  |  | [View](https://writingmate.ai/models/deepseek/deepseek-chat-v3.1) |

---

[← Back to all providers](/llm.txt)