DeepSeek 发布 DeepSeek-V4-Pro，重点升级 Agent 能力并已在 app/web 的 Expert Mode 和 API 上线，模型名不变。V4-Pro 与 V4-Flash 支持灵活推理档位，简单任务用 low、日常 Agent 工作流用 high、复杂任务用 max。同时原生支持 OpenAI Responses API，针对 Codex 优化并提供一键设置，详情见 API 文档。
发布方直接给出 Agent 能力升级、可调推理档位和 OpenAI Responses API 兼容，读者可对照判断是否切换日常模型。
We’re launching DeepSeek-V4-Pro today! 🚀
🔷 Major Agent upgrades with strong production gains!
🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, max for complex tasks.
🔷 Native OpenAI Responses API support, optimized for Codex with one-click setup.
V4 Pro is now available on app/web. Try it via “Expert Mode”.
V4 Pro is also available via API. Model names remain unchanged—please refer to the API docs for setup details.
来源：DeepSeek · x.com