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 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.

ChatDeepSeek164k tokens$0.5995 / $1.7986 · 1M

deepseek/deepseek-chat-v3.1

Context
164k tokens
Completion cap
161,000
Tools
Yes
JSON
Yes
Released
2025-08-21

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-chat-v3.1",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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 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. DeepSeek V3.1 runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-chat-v3.1.
Is DeepSeek V3.1 free?
No. Input is $0.5995 per 1M tokens and output is $1.7986 per 1M tokens on Geek Hub (markup included).
What is the context length of DeepSeek V3.1?
DeepSeek V3.1 has a 164k tokens context window. It supports up to 161,000 completion tokens.
Does DeepSeek V3.1 support tool calling and structured outputs?
DeepSeek V3.1 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 released?
DeepSeek V3.1 was released on 2025-08-21.

More models from DeepSeek