DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs

ChatDeepSeek164k tokens$0.2834 / $0.4142 · 1M

deepseek/deepseek-v3.2

Context
164k tokens
Completion cap
163,840
Tools
Yes
JSON
Yes
Released
2025-12-01

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-v3.2",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is DeepSeek V3.2?
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs DeepSeek V3.2 runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-v3.2.
Is DeepSeek V3.2 free?
No. Input is $0.2834 per 1M tokens and output is $0.4142 per 1M tokens on Geek Hub (markup included).
What is the context length of DeepSeek V3.2?
DeepSeek V3.2 has a 164k tokens context window. It supports up to 163,840 completion tokens.
Does DeepSeek V3.2 support tool calling and structured outputs?
DeepSeek V3.2 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was DeepSeek V3.2 released?
DeepSeek V3.2 was released on 2025-12-01.

More models from DeepSeek