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 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.

ChatDeepSeek164k tokens$0.2943 / $1.0901 · 1M

deepseek/deepseek-v3.1-terminus

Context
164k tokens
Completion cap
32,768
Tools
Yes
JSON
Yes
Released
2025-09-22

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3.1-terminus",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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 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. DeepSeek V3.1 Terminus runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-v3.1-terminus.
Is DeepSeek V3.1 Terminus free?
No. Input is $0.2943 per 1M tokens and output is $1.0901 per 1M tokens on Geek Hub (markup included).
What is the context length of DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus has a 164k tokens context window. It supports up to 32,768 completion tokens.
Does DeepSeek V3.1 Terminus support tool calling and structured outputs?
DeepSeek V3.1 Terminus accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was DeepSeek V3.1 Terminus released?
DeepSeek V3.1 Terminus was released on 2025-09-22.

More models from DeepSeek