# deepseek-v3.1-terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. 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. 

## Model Information

- **Organization**: [DeepSeek](/llm.txt)
- **Slug**: deepseek-v3-1-terminus
- **Available at Providers**: 36
- **Release Date**: September 22, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | DeepSeek-V3.1-Terminus | 0.56 | 1.68 |  | [View](https://aihubmix.com/model/DeepSeek-V3.1-Terminus) |
| [Helicone](/llm/helicone.txt) | DeepSeek V3.1 Terminus | 0.27 | 1.00 |  | [View](https://www.helicone.ai/model/deepseek-v3.1-terminus) |
| [Nvidia](/llm/nvidia.txt) | deepseek-v3.1-terminus | 0.00 | 0.00 | Yes | [View](https://build.nvidia.com/deepseek-ai/deepseek-v3.1-terminus) |
| [Abacus](/llm/abacus.txt) | DeepSeek V3.1 Terminus | 0.27 | 1.00 |  |  |
| [Novita AI](/llm/novita.txt) | deepseek-v3.1-terminus | 0.27 | 1.00 |  |  |
| [SiliconFlow](/llm/siliconflow.txt) | DeepSeek-V3.1-Terminus | 0.27 | 1.00 |  | [View](https://www.siliconflow.com./models/deepseek-v3-1-terminus) |
| [Nano-GPT](/llm/nanogpt.txt) | DeepSeek V3.1 Terminus |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | DeepSeek V3.1 Terminus (Thinking) |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | DeepSeek V3.1 Terminus | 0.21 | 0.79 |  | [View](https://openrouter.ai/deepseek/deepseek-v3.1-terminus) |
| [ValorGPT](/llm/valorgpt.txt) | DeepSeek V3.1 Terminus |  |  |  | [View](https://www.valorgpt.com/models/deepseek-deepseek-v3.1-terminus) |
| [ValorGPT](/llm/valorgpt.txt) | DeepSeek V3.1 Terminus (exacto) |  |  |  | [View](https://www.valorgpt.com/models/deepseek-deepseek-v3.1-terminus-exacto) |
| [Vercel AI Gateway](/llm/vercel.txt) | DeepSeek V3.1 Terminus | 0.27 | 1.00 |  |  |
| [Yupp](/llm/yupp.txt) | DeepSeek V3.1 Terminus Thinking (OpenRouter) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | DeepSeek V3.1 Terminus (Chutes AI) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Deepseek V3.1 Terminus (Sambanova) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | DeepSeek V3.1 Chat (OpenRouter) |  |  |  |  |
| [Atlas Cloud](/llm/atlascloud.txt) | DeepSeek V3.1 Terminus | 0.21 | 0.80 |  | [View](https://www.atlascloud.ai/models/deepseek-ai/DeepSeek-V3.1-Terminus) |
| [DeepInfra](/llm/deepinfra.txt) | DeepSeek-V3.1-Terminus | 0.21 | 0.79 |  |  |
| [Routeway](/llm/routeway.txt) | DeepSeek: DeepSeek V3.1 Terminus | 0.23 | 0.64 |  | [View](https://routeway.ai/models) |
| [LangDB](/llm/langdb.txt) | deepseek-v3.1-terminus |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | DeepSeek: DeepSeek V3.1 Terminus (exacto) | 0.21 | 0.79 |  |  |
| [Kilo Code](/llm/kilocode.txt) | DeepSeek: DeepSeek V3.1 Terminus | 0.21 | 0.79 |  | [View](https://kilo.ai/models/deepseek/deepseek-v3.1-terminus) |
| [GMI Cloud](/llm/gmi.txt) | DeepSeek-V3.1-Terminus | 0.27 | 1.00 |  |  |
| [SambaNova AI](/llm/sambanova.txt) | DeepSeek-V3.1-Terminus | 3.00 | 4.50 |  |  |
| [302.AI](/llm/302ai.txt) | Pro/deepseek-ai/DeepSeek-V3.1-Terminus | 0.57 | 1.72 |  | [View](https://302ai-en.apifox.cn/api-252564719) |
| [302.AI](/llm/302ai.txt) | deepseek/deepseek-v3.1-terminus | 0.57 | 1.72 |  | [View](https://302ai-en.apifox.cn/api-308032503) |
| [Together AI](/llm/togetherai.txt) | Deepseek V3.1 Terminus | 0.00 | 0.00 |  |  |
| [StreamLake](/llm/streamlake.txt) | DeepSeek-V3.1-Terminus | 0.57 | 1.71 |  |  |
| [NetMind](/llm/netmind.txt) | DeepSeek-V3.1-Terminus | 0.22 | 8.00 |  |  |
| [Qiniu](/llm/qiniuai.txt) | DeepSeek/DeepSeek-V3.1-Terminus |  |  |  |  |
| [ApiYI](/llm/apiyi.txt) | deepseek-v3.1-terminus |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | deepseek-v3.1-terminus | 0.23 | 0.87 |  |  |
| [OpenRouter](/llm/openrouter.txt) | DeepSeek V3.1 Terminus (exacto) | 0.21 | 0.79 |  | [View](https://openrouter.ai/deepseek/deepseek-v3.1-terminus:exacto) |
| [Writingmate](/llm/writingmate.txt) | DeepSeek: DeepSeek V3.1 Terminus |  |  |  | [View](https://writingmate.ai/models/deepseek/deepseek-v3.1-terminus) |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/deepseek/deepseek-v3.1-terminus:exacto |  |  |  |  |
| [SiliconFlow (China)](/llm/siliconflowcn.txt) | Pro/deepseek-ai/DeepSeek-V3.1-Terminus | 0.27 | 1.00 |  |  |

---

[← Back to all providers](/llm.txt)