自適應思考

自適應思考是在 Claude Opus 4.7、Claude Opus 4.6 和 Claude Sonnet 4.6 上使用擴展思考的推薦方式，也是 Claude Mythos Preview 上的預設模式（當 thinking 未設定時自動應用）。自適應思考不需要手動設定思考令牌預算，而是讓 Claude 根據每個請求的複雜性動態決定何時以及如何使用擴展思考。在 Claude Opus 4.7 上，自適應思考是唯一支援的思考模式；不再接受手動 thinking: {type: "enabled", budget_tokens: N}。

支援的模型

自適應思考在以下模型上受支援：

• Claude Mythos Preview (claude-mythos-preview)，自適應思考是預設值；不支援 thinking: {type: "disabled"}
• Claude Opus 4.7 (claude-opus-4-7)，自適應思考是唯一支援的思考模式。除非您在請求中明確設定 thinking: {type: "adaptive"}，否則思考處於關閉狀態；手動 thinking: {type: "enabled"} 會被拒絕並返回 400 錯誤。
• Claude Opus 4.6 (claude-opus-4-6)
• Claude Sonnet 4.6 (claude-sonnet-4-6)

自適應思考如何運作

在自適應模式中，思考對於模型是可選的。Claude 評估每個請求的複雜性，並決定是否以及如何使用擴展思考。在預設努力級別（high）下，Claude 幾乎總是會思考。在較低的努力級別下，Claude 可能會跳過簡單問題的思考。

自適應思考也會自動啟用交錯思考。這意味著 Claude 可以在工具呼叫之間進行思考，使其對代理工作流程特別有效。

如何使用自適應思考

在您的 API 請求中將 thinking.type 設定為 "adaptive"：

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=16000,
    thinking={"type": "adaptive"},
    messages=[
        {
            "role": "user",
            "content": "Explain why the sum of two even numbers is always even.",
        }
    ],
)

for block in response.content:
    if block.type == "thinking":
        print(f"\nThinking: {block.thinking}")
    elif block.type == "text":
        print(f"\nResponse: {block.text}")

自適應思考搭配努力參數

您可以將自適應思考與努力參數結合，以指導 Claude 進行多少思考。努力級別作為 Claude 思考分配的軟指導：

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=16000,
    thinking={"type": "adaptive"},
    output_config={"effort": "medium"},
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

print(response.content[0].text)

使用自適應思考進行串流

自適應思考與串流無縫協作。思考區塊透過 thinking_delta 事件進行串流，就像手動思考模式一樣：

client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-opus-4-7",
    max_tokens=16000,
    thinking={"type": "adaptive"},
    messages=[
        {
            "role": "user",
            "content": "What is the greatest common divisor of 1071 and 462?",
        }
    ],
) as stream:
    for event in stream:
        if event.type == "content_block_start":
            print(f"\nStarting {event.content_block.type} block...")
        elif event.type == "content_block_delta":
            if event.delta.type == "thinking_delta":
                print(event.delta.thinking, end="", flush=True)
            elif event.delta.type == "text_delta":
                print(event.delta.text, end="", flush=True)

自適應 vs 手動 vs 禁用思考

重要考慮事項

驗證變更

使用自適應思考時，先前的助手回合不需要以思考區塊開始。這比手動模式更靈活，手動模式中 API 強制執行啟用思考的回合以思考區塊開始。

提示快取

使用 adaptive 思考的連續請求保留提示快取斷點。但是，在 adaptive 和 enabled/disabled 思考模式之間切換會破壞訊息的快取斷點。系統提示和工具定義無論模式如何變更都保持快取。

調整思考行為

自適應思考的觸發行為是可提示的。如果 Claude 思考的頻率比您希望的多或少，您可以在系統提示中添加指導：

Extended thinking adds latency and should only be used when it
will meaningfully improve answer quality — typically for problems
that require multi-step reasoning. When in doubt, respond directly.

成本控制

使用 max_tokens 作為總輸出（思考 + 回應文本）的硬限制。effort 參數提供對 Claude 分配多少思考的額外軟指導。這兩者結合起來可以有效控制成本。

在 high 和 max 努力級別下，Claude 可能會進行更廣泛的思考，更可能耗盡 max_tokens 預算。如果您在回應中觀察到 stop_reason: "max_tokens"，請考慮增加 max_tokens 以給模型更多空間，或降低努力級別。

使用思考區塊

以下概念適用於所有支援擴展思考的模型，無論您使用自適應還是手動模式。

總結思考

With extended thinking enabled, the Messages API for Claude 4 models returns a summary of Claude's full thinking process. Summarized thinking provides the full intelligence benefits of extended thinking, while preventing misuse. This is the default behavior on Claude 4 models when the display field on the thinking configuration is unset or set to "summarized". On Claude Opus 4.7 and Claude Mythos Preview, display defaults to "omitted" instead, so you must set display: "summarized" explicitly to receive summarized thinking.

Here are some important considerations for summarized thinking:

• You're charged for the full thinking tokens generated by the original request, not the summary tokens.
• The billed output token count will not match the count of tokens you see in the response.
• On Claude 4 models, the first few lines of thinking output are more verbose, providing detailed reasoning that's particularly helpful for prompt engineering purposes. Claude Mythos Preview summarizes from the first token, so its thinking blocks do not show this verbose preamble.
• As Anthropic seeks to improve the extended thinking feature, summarization behavior is subject to change.
• Summarization preserves the key ideas of Claude's thinking process with minimal added latency, enabling a streamable user experience and easy migration from Claude Sonnet 3.7 to Claude 4 and later models.
• Summarization is processed by a different model than the one you target in your requests. The thinking model does not see the summarized output.

控制思考顯示

The display field on the thinking configuration controls how thinking content is returned in API responses. It accepts two values:

• "summarized": Thinking blocks contain summarized thinking text. See Summarized thinking for details. This is the default on Claude Opus 4.6, Claude Sonnet 4.6, and earlier Claude 4 models.
• "omitted": Thinking blocks are returned with an empty thinking field. The signature field still carries the encrypted full thinking for multi-turn continuity (see Thinking encryption). This is the default on Claude Opus 4.7 and Claude Mythos Preview.

Setting display: "omitted" is useful when your application doesn't surface thinking content to users. The primary benefit is faster time-to-first-text-token when streaming: The server skips streaming thinking tokens entirely and delivers only the signature, so the final text response begins streaming sooner.

Here are some important considerations for omitted thinking:

• You're still charged for the full thinking tokens. Omitting reduces latency, not cost.
• If you pass thinking blocks back in multi-turn conversations, pass them unchanged. The server decrypts the signature to reconstruct the original thinking for prompt construction (see Preserving thinking blocks). Any text you place in the thinking field of a round-tripped omitted block is ignored.
• display is invalid with thinking.type: "disabled" (there is nothing to display).
• When using thinking.type: "adaptive" and the model skips thinking for a simple request, no thinking block is produced regardless of display.

thinking = {
    "type": "adaptive",
    "display": "summarized",
}

有關 display: "omitted" 的程式碼範例和串流行為，請參閱擴展思考頁面上的控制思考顯示。那裡的範例使用 type: "enabled"；使用自適應思考時，請使用：

thinking = {"type": "adaptive", "display": "omitted"}

思考加密

Full thinking content is encrypted and returned in the signature field. This field is used to verify that thinking blocks were generated by Claude when passed back to the API.

Here are some important considerations on thinking encryption:

• When streaming responses, the signature is added via a signature_delta inside a content_block_delta event just before the content_block_stop event.
• signature values are significantly longer in Claude 4 models than in previous models.
• The signature field is an opaque field and should not be interpreted or parsed.
• signature values are compatible across platforms (Claude APIs, Amazon Bedrock, and Vertex AI). Values generated on one platform will be compatible with another.

定價

For complete pricing information including base rates, cache writes, cache hits, and output tokens, see the pricing page.

The thinking process incurs charges for:

• Tokens used during thinking (output tokens)
• Thinking blocks from prior assistant turns kept in context: only the last turn on earlier Opus/Sonnet models and all Haiku models; all turns by default on Opus 4.5+ and Sonnet 4.6+ (input tokens)
• Standard text output tokens

When using summarized thinking:

• Input tokens: Tokens in your original request (excludes thinking tokens from previous turns)
• Output tokens (billed): The original thinking tokens that Claude generated internally
• Output tokens (visible): The summarized thinking tokens you see in the response
• No charge: Tokens used to generate the summary

When using display: "omitted":

• Input tokens: Tokens in your original request (same as summarized)
• Output tokens (billed): The original thinking tokens that Claude generated internally (same as summarized)
• Output tokens (visible): Zero thinking tokens (the thinking field is empty)

其他主題

擴展思考頁面涵蓋了幾個主題的更多詳細資訊，包括特定於模式的程式碼範例：

• 工具使用與思考：自適應思考適用相同的規則：保留工具呼叫之間的思考區塊，並注意當思考處於活動狀態時 tool_choice 的限制。
• 提示快取：使用自適應思考時，使用相同思考模式的連續請求保留快取斷點。在 adaptive 和 enabled/disabled 模式之間切換會破壞訊息的快取斷點（系統提示和工具定義保持快取）。
• 上下文視窗：思考令牌如何與 max_tokens 和上下文視窗限制互動。

後續步驟