我们将 Claude Sonnet 5.5 的提示缓存读取价格从每百万 token 0.20 美元降至 0.10 美元：为基础输入价格的 0.05 倍，而非 0.1 倍。

我们已将 Claude Sonnet 5.5 上提示缓存读取的价格从每百万 token 0.20 美元降至 0.10 美元：为基础输入价格的 0.05 倍，而非 0.1 倍。缓存写入和所有其他价格保持不变。请参阅提示缓存定价。我们已推出 Claude Haiku 5.5（claude-haiku-5-5），这是我们能力最强的模型，专为高吞吐量和延迟敏感型工作负载调优。它具有 100 万 token 上下文窗口、128k 最大输出 token，以及带 effort 参数的自适应思考。它可在 Claude API、Amazon Bedrock 中的 Claude、AWS 上的 Claude Platform、Google Cloud 上的 Claude 以及 Microsoft Foundry 中的 Claude 上使用。请参阅 Claude Haiku 5.5 的新特性。为 Claude Haiku 4.5 编写的代码在 Claude Haiku 5.5 上可能会失效。手动扩展思考（budget_tokens）、采样参数 temperature、top_p 和 top_k，以及 assistant 消息预填充，均可能返回 400 错误。computer_20250124 也会返回 400 错误：请在 Claude API 和 Google Cloud 上使用 computer_toolset_20260801 工具集，或在 Amazon Bedrock 上使用 computer_20251124。在系统、工具或较早轮次发生更改后发回 thinking 块的请求也可能返回 400 错误。自适应思考默认开启，因此响应可能以 thinking 块开头，除非你将 thinking.display 设置为 "summarized"，否则其文本会被省略。同样的文本也会计入更多 token。请参阅各项更改的迁移指南。有关模型特定的提示模式，请参阅 Prompting Claude Haiku 5.5。Python 和 TypeScript SDK 现在包含浏览器使用工具和计算机使用工具的类（beta 版）。你继承其中一个类，并针对自己的浏览器或桌面自动化，为每个工具编写一个方法。SDK 会运行工具循环、你为浏览器设置的 URL 和文件策略，以及你的审批回调。请参阅使用 SDK 工具集进行浏览器和计算机使用。Claude Max 和 Team 计划现在包含每月 API 额度。要了解如何领取，请参阅 Max 和 Team 计划的 API 额度。在 Claude Managed Agents 中，网络受限的云环境现在也会将其 allowed_hosts 应用于 web_search 和 web_fetch 工具。对 allowed_hosts 不匹配的主机上的 URL 发起 web_fetch 调用，会向 agent 返回 url_not_allowed 错误结果。web_search 会省略来自此类主机的结果。当 allowed_hosts 未列出任何主机时，这两个工具都不会返回页面或搜索结果。allow_package_managers 和 allow_mcp_servers 不会为这些工具添加主机。要让这些工具访问某主机，请将其添加到 allowed_hosts，这也会将其开放给沙箱。不受限网络和自托管环境不会限制这些工具。请参阅环境网络。在网络受限的情况下，当启用的 Web 工具的 allowed_domains 包含不在 allowed_hosts 内的条目时，创建会话会失败并返回 400 错误。添加此类条目的会话更新也会如此。allowed_hosts 条目匹配一个精确主机，除非它以 *. 开头，因此 docs.example.com 不在 ["example.com"] 内。要修复该错误，请将该主机添加到 allowed_hosts，或从 allowed_domains 中移除该条目。请参阅限制 Web 搜索和 Web 抓取域。在 Claude Managed Agents 中，web_fetch 工具现在仅抓取已在会话中出现过的 URL，例如在用户消息的文本中、在 web_search 结果中，或在 web_fetch 先前返回的页面中。这降低了数据外泄的风险。仅出现在 Claude 自身输出、agent 的系统提示、附加文档或 bash、read 或 MCP 工具等工具输出中的 URL 不算数：对其发起 web_fetch 调用会向 agent 返回 url_not_in_prior_context 错误结果。要让 agent 抓取某个 URL，请在 user.message 事件的文本中发送它。

We’ve lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See Prompt caching pricing. We’ve launched Claude Haiku 5.5 (claude-haiku-5-5), our most capable model tuned for high-volume and latency-sensitive work. It has a 1M token context window, 128k max output tokens, and adaptive thinking with the effort parameter. It’s available on the Claude API, Claude in Amazon Bedrock, Claude Platform on AWS, Claude on Google Cloud, and Claude in Microsoft Foundry. See What’s new in Claude Haiku 5.5. Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (budget_tokens), the sampling parameters temperature, top_p, and top_k, and assistant message prefill can each return a 400 error. computer_20250124 also returns a 400 error: use the computer_toolset_20260801 toolset on the Claude API and Google Cloud, or computer_20251124 on Amazon Bedrock. A request that sends thinking blocks back after a change to system, tools, or earlier turns can also return a 400 error. Adaptive thinking is on by default, so a response can begin with thinking blocks, and their text is omitted unless you set thinking.display to "summarized". The same text also counts as more tokens. See the migration guide for each change. For model-specific prompting patterns, see Prompting Claude Haiku 5.5. The Python and TypeScript SDKs now include classes, in beta, for the browser use tool and the computer use tool. You subclass one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback. See Browser and computer use with the SDK toolsets. Claude Max and Team plans now include monthly API credits. To learn how to claim them, see API credits for Max and Team plans. In Claude Managed Agents, a cloud environment with limited networking now also applies its allowed_hosts to the web_search and web_fetch tools. A web_fetch call for a URL on a host that allowed_hosts does not match returns a url_not_allowed error result to the agent. web_search omits results from such hosts. When allowed_hosts lists no hosts, neither tool returns a page or a search result. allow_package_managers and allow_mcp_servers add no hosts for these tools. To let the tools reach a host, add it to allowed_hosts, which also opens it to the sandbox. unrestricted networking and self-hosted environments do not limit these tools. See Environment networking. With limited networking, creating a session fails with a 400 error when an enabled web tool’s allowed_domains has an entry not within allowed_hosts. So does a session update that adds such an entry. An allowed_hosts entry matches one exact host unless it starts with *., so docs.example.com is not within ["example.com"]. To fix the error, add the host to allowed_hosts or remove the entry from allowed_domains. See Restrict web search and web fetch domains. In Claude Managed Agents, the web_fetch tool now fetches only URLs that have already appeared in the session, for example in the text of a user message, in a web_search result, or in a page that web_fetch returned earlier. This reduces the risk of data exfiltration. A URL that appears only in Claude’s own output, the agent’s system prompt, an attached document, or the output of a tool such as bash, read, or an MCP tool does not count: a web_fetch call for it returns a url_not_in_prior_context error result to the agent. To let the agent fetch a URL, send it in the text of a user.message event.