Workers AI 上线 DeepSeek V4 Flash/Pro，支持百万 token 上下文
Workers AI - DeepSeek V4 Flash and Pro now available on Workers AI
开发者若在 Workers AI 上跑长上下文或代理任务，这次百万 token 上下文是实打实的能力跃迁，建议直接试用 V4 Flash 或 Pro，注意需 Paid 计划或预付费额度。
@cf/deepseek-ai/deepseek-v4-pro-0813 and @cf/deepseek-ai/deepseek-v4-flash-0731 are now available on Workers AI.
@cf/deepseek-ai/deepseek-v4-pro-0813 和 @cf/deepseek-ai/deepseek-v4-flash-0731 现已在 Workers AI 上可用。
DeepSeek V4 Flash and DeepSeek V4 Pro are the first Workers AI models with a full one million (1,048,576) token context window. Use them for long-horizon agentic workflows, large codebases, and multi-step reasoning that exceed the context limits of every other model hosted on the platform.
DeepSeek V4 Flash 和 DeepSeek V4 Pro 是首批在 Workers AI 上提供完整一百万（1,048,576）token 上下文窗口的模型。可将它们用于长时程的智能体工作流、大型代码库以及超出平台上所有其他模型上下文限制的多步推理。
DeepSeek V4 Flash is the faster, lower-cost sibling. This release supersedes the preview version with substantially enhanced agentic capabilities.
DeepSeek V4 Flash 是速度更快、成本更低的同类产品。此版本取代了预览版，并大幅增强了智能体能力。
Key capabilities:
主要能力：
- Reasoning: Both models support thinking mode for complex, step-by-step problem-solving.
- Function calling: Build agents that invoke tools and APIs across multiple conversation turns.
- Long context: Both models support a full 1,048,576 token context window.
- 推理：两个模型均支持思考模式，用于复杂的分步问题求解。
- 函数调用：构建可在多轮对话中调用工具和 API 的智能体。
- 长上下文：两个模型均支持完整的 1,048,576 token 上下文窗口。
Both models require the Workers Paid plan or prepaid AI Gateway credits.
这两个模型均需要 Workers 付费计划或预付费的 AI Gateway 积分。
Use these models through the Workers AI binding (env.AI.run()), the REST API, the OpenAI-compatible endpoint, or AI Gateway.
可通过 Workers AI 绑定（env.AI.run()）、REST API、兼容 OpenAI 的端点或 AI Gateway 使用这些模型。
For more information, refer to the DeepSeek V4 Pro model page, the DeepSeek V4 Flash model page, and pricing.
更多信息，请参阅 DeepSeek V4 Pro 模型页面、DeepSeek V4 Flash 模型页面以及定价。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力