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/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 keyFrequently 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
DeepSeek V4 FlashV4 Flash open-weight, aggressive pricing with 1M context. Cache hit drops input to $0.0028. Replaces DeepSeek Chat V3.
DeepSeek V4 ProV4 Pro with reasoning + non-reasoning modes. Cache hit $0.003625. Replaces DeepSeek Reasoner R1.
DeepSeek V3DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tok
DeepSeek V3 0324DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/d
DeepSeek V3.1DeepSeek-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 ba
DeepSeek V3.1 TerminusDeepSeek-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, inc