DeepSeek 发布 V3.2 与 V3.2-Speciale 两款推理模型
DeepSeek-V3.2 Release | DeepSeek API Docs
DeepSeek 发布 DeepSeek-V3.2 与 DeepSeek-V3.2-Speciale 两款面向智能体的推理优先模型，V3.2 已在 App、Web 和 API 上线，Speciale 暂仅提供 API。V3.2 定位日常使用、推理与长度更均衡，官方称达到 GPT-5 水平；Speciale 主打极限推理能力，官方称可与 Gemini-3.0-Pro 竞争，并在 IMO、CMO、ICPC World Finals 和 IOI 2025 中取得金牌级成绩。V3.2 是 DeepSeek 首个将思考直接融入工具调用的模型，支持思考与非思考两种模式下的工具调用，训练数据合成覆盖 1800+ 环境和 85k+ 复杂指令；Speciale 通过临时端点提供，价格与 V3.2 相同，不支持工具调用，可用至 2025 年 12 月 15 日 15:59（UTC）。
正文
当前显示原文，中文全文译文尚未就绪。
DeepSeek-V3.2 Release 2025/12/01
🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents!
🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API; 🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now; 📄 Tech report: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf
🔹 V3.2: Balanced inference vs. length. Your daily driver at GPT-5 level performance; 🔹 V3.2-Speciale: Maxed-out reasoning capabilities. Rivals Gemini-3.0-Pro; 🥇 Gold-Medal Performance: V3.2-Speciale attains gold-level results in IMO, CMO, ICPC World Finals & IOI 2025
📝 Note: V3.2-Speciale dominates complex tasks but requires higher token usage. Currently API-only (no tool-use) to support community evaluation & research.
🔹 Introduces a new massive agent training data synthesis method covering 1,800+ environments & 85k+ complex instructions; 🔹 DeepSeek-V3.2 is our first model to integrate thinking directly into tool-use, and also supports tool-use in both thinking and non-thinking modes
🔹 V3.2: Same usage pattern as V3.2-Exp; 🔹 V3.2-Speciale: Served via a temporary endpoint: base_url="https://api.deepseek.com/v3.2_speciale_expires_on_20251215". Same pricing as V3.2, no tool calls, available until Dec 15th, 2025, 15:59 (UTC Time); 💡 V3.2 now supports Thinking in Tool-Use — details: https://api-docs.deepseek.com/guides/thinking_mode