deepseek-v3.1-terminus
DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version and addresses user feedback (i.e. language consistency and agent upgrades).
| Provider | Source | Input Price ($/1M) | Output Price ($/1M) | Description | Free |
|---|---|---|---|---|---|
| vercel | vercel | Input: $0.27 | Output: $1.00 | DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version and addresses user feedback (i.e. language consistency and agent upgrades). | |
| nvidia | models-dev | Input: $0.00 | Output: $0.00 | Provider: Nvidia, Context: 128000, Output Limit: 8192 | |
| siliconflowcn | models-dev | Input: $0.27 | Output: $1.00 | Provider: SiliconFlow (China), Context: 164000, Output Limit: 164000 | |
| siliconflow | models-dev | Input: $0.27 | Output: $1.00 | Provider: SiliconFlow, Context: 164000, Output Limit: 164000 | |
| helicone | models-dev | Input: $0.27 | Output: $1.00 | Provider: Helicone, Context: 128000, Output Limit: 16384 | |
| synthetic | models-dev | Input: $1.20 | Output: $1.20 | Provider: Synthetic, Context: 128000, Output Limit: 128000 | |
| deepinfra | litellm | Input: $0.27 | Output: $1.00 | Source: deepinfra, Context: 163840 | |
| openrouter | openrouter | Input: $0.21 | Output: $0.79 | 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. Context: 163840 |