---
title: 快速模式
url: https://platform.claude.com/docs/zh-TW/build-with-claude/fast-mode
description: 從支援的 Claude 模型獲得最高 2.5 倍的每秒輸出 token 數。
featureMetadata:
  betaHeader: fast-mode-2026-02-01
  zdr:
    eligibility: eligible
    note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). 使用相同的 Messages API 端點，但推論速度更快。無論速度設定為何，ZDR 皆適用。
  supportedModels:
    - claude-fable-5-2
    - claude-mythos-5-2
    - claude-opus-5-5
    - claude-opus-5
    - claude-opus-4-8
  supportedPlatforms:
    Claude API:
      availability: stable
      note: '移除日期：2026 年 11 月 30 日。移除後，對 `claude-opus-4-8` 發出且搭配 `speed: "fast"` 的請求將會傳回錯誤。若要繼續使用快速模式，請遷移至 Claude Opus 5.5。請參閱[從 Claude Opus 4.8 遷移至 Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8)。'
    Claude Models on Google Cloud (Anthropic managed): stable
    Claude Models on Google Cloud (Google managed): stable
    Microsoft Foundry:
      availability: stable
      note: 在 Microsoft Foundry 上，快速模式有自己的模型 ID，以 `-fast` 結尾。請將請求傳送至快速模式模型的部署，並省略 `speed`。
  details:
    - 快速模式在 Claude Opus 5 上處於研究預覽階段，在 Claude Opus 4.8 上已被棄用，且在這兩個模型上都需要 `fast-mode-2026-02-01` beta 標頭。
---

**API 支援**：用法因產品而異。

* **Messages API**：在請求上設定 `speed: "fast"`。
* **Managed Agents**：在代理的模型物件上設定 `speed`，例如 `{"id": "claude-opus-5-5", "speed": "fast"}`。

「Fast mode」（快速模式）以進階定價提供最高 2.5 倍的每秒輸出 token 數。在您的請求中設定 `speed: "fast"` 即可選擇加入。快速模式可在 Claude Fable 5.2、Claude Mythos 5.2 和 Claude Opus 5.5 上使用。快速模式在 Claude Opus 5 上處於研究預覽階段，在 Claude Opus 4.8 上已被棄用。

## 快速模式的運作方式

快速模式以更快的推論配置執行相同的模型。智慧或能力不會有任何變化。

* 與標準速度相比，每秒輸出 token 數最高可提升 2.5 倍
* 速度優勢集中在「output tokens per second」（每秒輸出 token 數），即 OTPS，而非「time to first token」（首個 token 產生時間），即 TTFT
* 相容於 [串流](https://platform.claude.com/docs/zh-TW/build-with-claude/streaming)，在串流中 OTPS 的提升最為明顯

## 基本用法

快速模式僅適用於支援的模型。詳情請參閱[可用性](https://platform.claude.com/docs/zh-TW/build-with-claude/fast-mode#feature-availability)，包括哪些模型需要 beta 標頭。

<CodeGroup>
  ```bash cURL
  curl https://api.anthropic.com/v1/messages \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2026-10-21" \
    -H "content-type: application/json" \
    -d '{
      "model": "claude-opus-5-5",
      "max_tokens": 4096,
      "speed": "fast",
      "messages": [{
        "role": "user",
        "content": "Refactor this module to use dependency injection"
      }]
    }'
  ```

  ```bash CLI
  ant messages create <<'YAML'
  model: claude-opus-5-5
  max_tokens: 4096
  speed: fast
  messages:
    - role: user
      content: Refactor this module to use dependency injection
  YAML
  ```

  ```python Python
  client = anthropic.Anthropic()

  response = client.messages.create(
      model="claude-opus-5-5",
      max_tokens=4096,
      speed="fast",
      messages=[
          {"role": "user", "content": "Refactor this module to use dependency injection"}
      ],
  )

  for block in response.content:
      if block.type == "text":
          print(block.text)
  ```

  ```typescript TypeScript
  const client = new Anthropic();

  const response = await client.messages.create({
    model: "claude-opus-5-5",
    max_tokens: 4096,
    speed: "fast",
    messages: [
      {
        role: "user",
        content: "Refactor this module to use dependency injection"
      }
    ]
  });

  const textBlock = response.content.find((block) => block.type === "text");
  console.log(textBlock?.text);
  ```

  ```csharp C#
  AnthropicClient client = new();

  var response = await client.Messages.Create(new MessageCreateParams
  {
      Model = Model.ClaudeOpus5_5,
      MaxTokens = 4096,
      Speed = Speed.Fast,
      Messages = [
          new UserMessageParam { Content = "Refactor this module to use dependency injection" }
      ],
  });

  foreach (var block in response.Content)
  {
      if (block.TryPickText(out var textBlock))
      {
          Console.WriteLine(textBlock.Text);
      }
  }
  ```

  ```go Go
  client := anthropic.NewClient()

  response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
  	Model:     anthropic.ModelClaudeOpus5_5,
  	MaxTokens: 4096,
  	Speed:     anthropic.MessageNewParamsSpeedFast,
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Refactor this module to use dependency injection")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }
  for _, block := range response.Content {
  	if textBlock, ok := block.AsAny().(anthropic.TextBlock); ok {
  		fmt.Println(textBlock.Text)
  	}
  }
  ```

  ```java Java
  AnthropicClient client = AnthropicOkHttpClient.fromEnv();

  Message response = client.messages().create(
      MessageCreateParams.builder()
          .model(Model.CLAUDE_OPUS_5_5)
          .maxTokens(4096L)
          .speed(MessageCreateParams.Speed.FAST)
          .addUserMessage("Refactor this module to use dependency injection")
          .build());

  response.content().stream()
      .flatMap(block -> block.text().stream())
      .forEach(textBlock -> IO.println(textBlock.text()));
  ```

  ```php PHP
  $client = new Client();

  $response = $client->messages->create(
      model: Model::CLAUDE_OPUS_5_5,
      maxTokens: 4096,
      speed: 'fast',
      messages: [
          ['role' => 'user', 'content' => 'Refactor this module to use dependency injection'],
      ],
  );

  foreach ($response->content as $block) {
      if ($block instanceof \Anthropic\Messages\TextBlock) {
          echo $block->text, PHP_EOL;
      }
  }
  ```

  ```ruby Ruby
  client = Anthropic::Client.new

  response = client.messages.create(
    model: Anthropic::Model::CLAUDE_OPUS_5_5,
    max_tokens: 4096,
    speed: "fast",
    messages: [{ role: "user", content: "Refactor this module to use dependency injection" }]
  )

  response.content.each do |block|
    puts block.text if block.is_a?(Anthropic::Models::TextBlock)
  end
  ```
</CodeGroup>

在 [Microsoft Foundry 中的 Claude](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-microsoft-foundry) 上，快速模式有自己的模型 ID，且速度由部署決定。請將快速模式請求傳送到快速模式模型的部署，並省略 `speed`：

| 模型                | 快速模式模型 ID                |
| ----------------- | ------------------------ |
| Claude Fable 5.2  | `claude-fable-5-2-fast`  |
| Claude Mythos 5.2 | `claude-mythos-5-2-fast` |
| Claude Opus 5.5   | `claude-opus-5-5-fast`   |

在標準模型（例如 `claude-opus-5-5`）的部署上設定 `speed` 的請求會傳回錯誤。

## 速率限制

快速模式有專屬的「rate limit」（速率限制），與標準速率限制分開。當您超過快速模式的速率限制時，API 會傳回 `429` 錯誤，並附帶 `retry-after` 標頭，指出何時會有可用容量。在 [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/google-managed#rate-limits) 上，速率限制和配額由 Google Cloud 管理。

Claude Fable 5.2、Claude Mythos 5.2 和 Claude Opus 5.5 具有預設的快速模式速率限制。預設限制適用於 Start、Build 和 Scale [用量層級](https://platform.claude.com/docs/zh-TW/api/rate-limits)。您無需為這些模型申請快速模式存取權。處於評估層級的組織在升級到 Start、Build 或 Scale 層級後，即可在這些模型上使用快速模式。

回應中包含指示您快速模式速率限制狀態的標頭：

| 標頭                                       | 說明                   |
| ---------------------------------------- | -------------------- |
| `anthropic-fast-input-tokens-limit`      | 每分鐘快速模式輸入 token 數上限  |
| `anthropic-fast-input-tokens-remaining`  | 剩餘的快速模式輸入 token 數    |
| `anthropic-fast-input-tokens-reset`      | 快速模式輸入 token 限制重設的時間 |
| `anthropic-fast-output-tokens-limit`     | 每分鐘快速模式輸出 token 數上限  |
| `anthropic-fast-output-tokens-remaining` | 剩餘的快速模式輸出 token 數    |
| `anthropic-fast-output-tokens-reset`     | 快速模式輸出 token 限制重設的時間 |

若要查看您的快速模式速率限制，請前往 Claude Console 中的[速率限制](https://platform.claude.com/usage/limits)頁面。

## 檢查使用了哪種速度

回應的 `usage` 物件包含一個 `speed` 欄位，指出使用了哪種速度，即 `"fast"` 或 `"standard"`。在[不支援快速模式的模型](https://platform.claude.com/docs/zh-TW/build-with-claude/fast-mode#feature-availability)上請求 `speed: "fast"` 會傳回錯誤，超過快速模式的速率限制或容量時也會傳回錯誤（`429` 或 `529`）。當帶有 `speed: "fast"` 的請求成功時，`usage.speed` 為 `"fast"`。Claude Opus 4.6 是例外：帶有 `speed: "fast"` 和 `fast-mode-2026-02-01` beta 標頭的請求不會傳回錯誤，而是會成功，但以標準速度執行。在這種情況下，`usage.speed` 會顯示 `"standard"`。在 Claude Models on Google Cloud (Anthropic managed) 上，帶有 `speed: "fast"` 的 Claude Opus 4.6 請求即使附帶標頭也會傳回 `400` 錯誤。

<CodeGroup>
  ```bash cURL
  curl https://api.anthropic.com/v1/messages \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2026-10-21" \
    -H "content-type: application/json" \
    -d '{
      "model": "claude-opus-5-5",
      "max_tokens": 1024,
      "speed": "fast",
      "messages": [{"role": "user", "content": "Hello"}]
    }'
  ```

  ```bash CLI
  ant messages create <<'YAML'
  model: claude-opus-5-5
  max_tokens: 1024
  speed: fast
  messages:
    - role: user
      content: Hello
  YAML
  ```

  ```python Python
  client = anthropic.Anthropic()

  response = client.messages.create(
      model="claude-opus-5-5",
      max_tokens=1024,
      speed="fast",
      messages=[{"role": "user", "content": "Hello"}],
  )

  print(response.usage.speed)  # "fast" or "standard"
  ```

  ```typescript TypeScript
  const client = new Anthropic();

  const response = await client.messages.create({
    model: "claude-opus-5-5",
    max_tokens: 1024,
    speed: "fast",
    messages: [{ role: "user", content: "Hello" }]
  });

  console.log(response.usage.speed); // "fast" or "standard"
  ```

  ```csharp C#
  AnthropicClient client = new();

  var response = await client.Messages.Create(new MessageCreateParams
  {
      Model = Model.ClaudeOpus5_5,
      MaxTokens = 1024,
      Speed = Speed.Fast,
      Messages = [new UserMessageParam { Content = "Hello" }],
  });

  Console.WriteLine(response.Usage.Speed);  // "fast" or "standard"
  ```

  ```go Go
  client := anthropic.NewClient()

  response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
  	Model:     anthropic.ModelClaudeOpus5_5,
  	MaxTokens: 1024,
  	Speed:     anthropic.MessageNewParamsSpeedFast,
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Hello")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }
  fmt.Println(response.Usage.Speed) // "fast" or "standard"
  ```

  ```java Java
  AnthropicClient client = AnthropicOkHttpClient.fromEnv();

  MessageCreateParams params = MessageCreateParams.builder()
      .model(Model.CLAUDE_OPUS_5_5)
      .maxTokens(1024L)
      .speed(MessageCreateParams.Speed.FAST)
      .addUserMessage("Hello")
      .build();

  Message response = client.messages().create(params);
  IO.println(response.usage().speed().orElseThrow());  // "fast" or "standard"
  ```

  ```php PHP
  $client = new Client();

  $response = $client->messages->create(
      model: Model::CLAUDE_OPUS_5_5,
      maxTokens: 1024,
      speed: 'fast',
      messages: [['role' => 'user', 'content' => 'Hello']],
  );

  echo $response->usage->speed;  // "fast" or "standard"
  ```

  ```ruby Ruby
  client = Anthropic::Client.new

  response = client.messages.create(
    model: Anthropic::Model::CLAUDE_OPUS_5_5,
    max_tokens: 1024,
    speed: "fast",
    messages: [{ role: "user", content: "Hello" }]
  )

  puts(response.usage.speed)  # "fast" or "standard"
  ```
</CodeGroup>

```json Output
{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  // ...
  "usage": {
    "input_tokens": 8,
    "output_tokens": 12,
    "speed": "fast"
  }
}
```

若要追蹤整個組織的快速模式使用量與成本，請參閱[用量與成本分析 API](https://platform.claude.com/docs/zh-TW/manage-claude/usage-cost-analytics-api)。

## 重試與備援

### 自動重試

SDK 預設會自動重試快速模式的 `429` 錯誤最多 2 次（可透過 `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`) 設定），並在每次重試前等待 `retry-after` 標頭中的延遲時間。由於快速模式採用持續的 token 補充機制，`retry-after` 延遲通常很短，一旦有可用容量，請求就會成功。

### 退回標準速度

如果您希望退回標準速度而不是等待快速模式容量，請捕捉速率限制錯誤，並在不帶 `speed: "fast"` 的情況下重試。在 Microsoft Foundry 中的 Claude 上，速度由部署決定，因此請改為在標準模型的部署上重試。在初始的快速請求中將 `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`) 設為 `0`，以略過自動重試，並在遇到速率限制錯誤時立即失敗。

<Note>
  從快速速度退回標準速度會導致[提示快取](https://platform.claude.com/docs/zh-TW/build-with-claude/prompt-caching)未命中。不同速度的請求不會共用快取的前綴。
</Note>

由於將 `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`) 設為 `0` 也會停用其他暫時性錯誤（過載、內部伺服器錯誤）的重試，以下範例會在發生這些錯誤後重新傳送請求。

<CodeGroup exclude="shell:cURL, shell:CLI">
  ```python Python
  client = anthropic.Anthropic()


  def create_message_with_fast_fallback(max_retries=0, max_attempts=3, **params):
      try:
          return client.with_options(max_retries=max_retries).messages.create(**params)
      except anthropic.RateLimitError:
          if params.get("speed") == "fast":
              del params["speed"]
              return create_message_with_fast_fallback(max_retries=max_retries, **params)
          raise
      except (
          anthropic.APIStatusError,
          anthropic.APIConnectionError,
      ) as error:
          if isinstance(error, anthropic.APIStatusError) and error.status_code < 500:
              raise
          if max_attempts > 1:
              return create_message_with_fast_fallback(
                  max_retries=max_retries, max_attempts=max_attempts - 1, **params
              )
          raise


  message = create_message_with_fast_fallback(
      model="claude-opus-5-5",
      max_tokens=1024,
      messages=[{"role": "user", "content": "Hello"}],
      speed="fast",
      max_retries=0,
  )
  ```

  ```typescript TypeScript
  const client = new Anthropic();

  async function createMessageWithFastFallback(
    params: Anthropic.MessageCreateParamsNonStreaming,
    requestOptions?: Anthropic.RequestOptions,
    maxAttempts: number = 3
  ): Promise<Anthropic.Message> {
    try {
      return await client.messages.create(params, requestOptions);
    } catch (e) {
      if (e instanceof Anthropic.RateLimitError && params.speed === "fast") {
        const { speed, ...rest } = params;
        return createMessageWithFastFallback(rest);
      }
      if (
        e instanceof Anthropic.InternalServerError ||
        e instanceof Anthropic.APIConnectionError
      ) {
        if (maxAttempts > 1) {
          return createMessageWithFastFallback(params, undefined, maxAttempts - 1);
        }
      }
      throw e;
    }
  }

  const message = await createMessageWithFastFallback(
    {
      model: "claude-opus-5-5",
      max_tokens: 1024,
      messages: [{ role: "user", content: "Hello" }],
      speed: "fast"
    },
    { maxRetries: 0 }
  );
  ```

  ```csharp C#
  AnthropicClient client = new();

  async Task<Message> CreateMessageWithFastFallback(
      MessageCreateParams parameters,
      int? maxRetries = null,
      int maxAttempts = 3)
  {
      try
      {
          var requestClient = maxRetries is int retries
              ? client.WithOptions(options => options with { MaxRetries = retries })
              : client;
          return await requestClient.Messages.Create(parameters);
      }
      catch (AnthropicRateLimitException)
      {
          if (parameters.Speed is not null)
          {
              return await CreateMessageWithFastFallback(
                  parameters with { Speed = null });
          }
          throw;
      }
      catch (Anthropic5xxException)
      {
          if (maxAttempts > 1)
          {
              return await CreateMessageWithFastFallback(
                  parameters, maxAttempts: maxAttempts - 1);
          }
          throw;
      }
  }

  var message = await CreateMessageWithFastFallback(
      new MessageCreateParams
      {
          Model = Model.ClaudeOpus5_5,
          MaxTokens = 1024,
          Messages = [new UserMessageParam { Content = "Hello" }],
          Speed = Speed.Fast,
      },
      maxRetries: 0);
  ```

  ```go Go
  func createMessageWithFastFallback(
  	ctx context.Context,
  	client *anthropic.Client,
  	params anthropic.MessageNewParams,
  	maxAttempts int,
  	opts ...option.RequestOption,
  ) (*anthropic.Message, error) {
  	message, err := client.Messages.New(ctx, params, opts...)
  	if err != nil {
  		var apierr *anthropic.Error
  		if errors.As(err, &apierr) && apierr.StatusCode == 429 && params.Speed != "" {
  			params.Speed = ""
  			return createMessageWithFastFallback(ctx, client, params, maxAttempts)
  		}
  		if (errors.As(err, &apierr) && apierr.StatusCode >= 500) || !errors.As(err, &apierr) {
  			if maxAttempts > 1 {
  				return createMessageWithFastFallback(ctx, client, params, maxAttempts-1)
  			}
  		}
  		return nil, err
  	}
  	return message, nil
  }

  func main() {
  	client := anthropic.NewClient()
  	message, err := createMessageWithFastFallback(
  		context.TODO(),
  		&client,
  		anthropic.MessageNewParams{
  			Model:     anthropic.ModelClaudeOpus5_5,
  			MaxTokens: 1024,
  			Messages: []anthropic.MessageParam{
  				anthropic.NewUserMessage(anthropic.NewTextBlock("Hello")),
  			},
  			Speed: anthropic.MessageNewParamsSpeedFast,
  		},
  		3,
  		option.WithMaxRetries(0),
  	)
  	if err != nil {
  		panic(err)
  	}
  	fmt.Println(message)
  }
  ```

  ```java Java
  import com.anthropic.errors.InternalServerException;
  import com.anthropic.errors.RateLimitException;
  // ...
  // 停用 SDK 的自動重試，改由後續的 fallback（備援）邏輯處理
  AnthropicClient client =
      AnthropicOkHttpClient.builder()
          .fromEnv()
          .maxRetries(0)
          .build();

  Message createMessageWithFastFallback(
          MessageCreateParams params, int maxAttempts) {
      try {
          return client.messages().create(params);
      } catch (RateLimitException e) {
          if (params.speed().isPresent()) {
              MessageCreateParams retryParams = params.toBuilder()
                  .speed(Optional.empty())
                  .build();
              return createMessageWithFastFallback(retryParams, maxAttempts);
          }
          throw e;
      } catch (InternalServerException e) {
          if (maxAttempts > 1) {
              return createMessageWithFastFallback(params, maxAttempts - 1);
          }
          throw e;
      }
  }

  void main() {
      Message message = createMessageWithFastFallback(
          MessageCreateParams.builder()
              .model(Model.CLAUDE_OPUS_5_5)
              .maxTokens(1024L)
              .addUserMessage("Hello")
              .speed(MessageCreateParams.Speed.FAST)
              .build(),
          3);
      message.content().stream()
          .flatMap(block -> block.text().stream())
          .forEach(textBlock -> IO.println(textBlock.text()));
  }
  ```

  ```php PHP
  use Anthropic\Core\Exceptions\APIConnectionException;
  use Anthropic\Core\Exceptions\InternalServerException;
  use Anthropic\Core\Exceptions\RateLimitException;
  use Anthropic\Messages\Model;
  use Anthropic\RequestOptions;

  $client = new Client();

  function createMessageWithFastFallback(
      Client $client,
      array $params,
      ?RequestOptions $requestOptions = null,
      int $maxAttempts = 3,
  ) {
      try {
          return $client->messages->create(
              ...$params,
              requestOptions: $requestOptions,
          );
      } catch (RateLimitException $e) {
          if (isset($params['speed'])) {
              unset($params['speed']);
              return createMessageWithFastFallback($client, $params);
          }
          throw $e;
      } catch (InternalServerException | APIConnectionException $e) {
          if ($maxAttempts > 1) {
              return createMessageWithFastFallback(
                  $client, $params, maxAttempts: $maxAttempts - 1
              );
          }
          throw $e;
      }
  }

  $message = createMessageWithFastFallback(
      $client,
      [
          'model' => Model::CLAUDE_OPUS_5_5,
          'maxTokens' => 1024,
          'messages' => [['role' => 'user', 'content' => 'Hello']],
          'speed' => 'fast',
      ],
      RequestOptions::with(maxRetries: 0),
  );
  ```

  ```ruby Ruby
  client = Anthropic::Client.new

  def create_message_with_fast_fallback(client, request_options: {}, max_attempts: 3, **params)
    client.messages.create(**params, request_options: request_options)
  rescue Anthropic::Errors::RateLimitError
    raise unless params[:speed] == "fast"
    params.delete(:speed)
    create_message_with_fast_fallback(client, **params)
  rescue Anthropic::Errors::InternalServerError, Anthropic::Errors::APIConnectionError
    raise unless max_attempts > 1
    create_message_with_fast_fallback(client, max_attempts: max_attempts - 1, **params)
  end

  message = create_message_with_fast_fallback(
    client,
    model: Anthropic::Model::CLAUDE_OPUS_5_5,
    max_tokens: 1024,
    messages: [{ role: "user", content: "Hello" }],
    speed: "fast",
    request_options: { max_retries: 0 }
  )
  ```
</CodeGroup>

## 注意事項

* **Batch API：** 快速模式無法與 [Batch API](https://platform.claude.com/docs/zh-TW/build-with-claude/batch-processing) 一起使用。
* **Priority Tier：** 快速模式無法與 [Priority Tier](https://platform.claude.com/docs/zh-TW/api/service-tiers) 承諾一起使用。

## 定價

快速模式的定價是在整個「context window」（上下文視窗）範圍內以標準費率乘上倍數計算，包括超過 200k 輸入 token 的請求。在 Claude Models on Google Cloud (Google managed) 上，快速模式的價格由 Google Cloud 設定。請參閱[雲端平台定價](https://platform.claude.com/docs/zh-TW/about-claude/pricing#cloud-platform-pricing)。

| 模型                              | 輸入             | 輸出             |
| ------------------------------- | -------------- | -------------- |
| Claude Fable 5.2                | $16 USD / MTok | $80 USD / MTok |
| Claude Mythos 5.2               | $16 USD / MTok | $80 USD / MTok |
| Claude Opus 5.5                 | $8 USD / MTok  | $40 USD / MTok |
| Claude Opus 5 / Claude Opus 4.8 | $10 USD / MTok | $50 USD / MTok |

快速模式定價會與其他定價修正因子疊加：

* [提示快取倍數](https://platform.claude.com/docs/zh-TW/about-claude/pricing#prompt-caching)會在快速模式定價之上套用。
* [資料駐留](https://platform.claude.com/docs/zh-TW/manage-claude/data-residency)倍數會在快速模式定價之上套用。

如需完整的定價詳情，請參閱[定價](https://platform.claude.com/docs/zh-TW/about-claude/pricing#fast-mode-pricing)頁面。

## 可用性

快速模式在特定模型上可供使用或處於研究預覽階段或已棄用，且具備零資料保留和HIPAA 就緒資格。

### API 支援

快速模式僅適用於以下模型。如果您先前在較早的模型上使用快速模式，請[遷移到支援快速模式的模型](https://platform.claude.com/docs/zh-TW/models/opus-5-5/migration-guide)。

若要在 Claude Opus 5 上使用快速模式，請聯繫您的客戶經理或[加入候補名單](https://claude.com/fast-mode)。

#### [Messages API](https://platform.claude.com/docs/zh-TW/build-with-claude/working-with-messages)

* 可用性：可用
* 用法：在請求上設定 `speed: "fast"`。

| 狀態              | 雲端平台                                                                                                                                                                                                                                                                                                                               | 模型                                                                                                                                                                           |
| --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 可用              | Claude API, [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/zh-TW/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/zh-TW/models/mythos-5-2/overview) |
| 可用<sup>1</sup>  | [Microsoft Foundry (hosted on Anthropic)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-microsoft-foundry)                                                                                                                                                                                                    | [Claude Fable 5.2](https://platform.claude.com/docs/zh-TW/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/zh-TW/models/mythos-5-2/overview) |
| 可用              | Claude API, [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/anthropic-managed)                                                                                                                                                          | [Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/models/opus-5-5/overview)                                                                                           |
| 可用<sup>1</sup>  | [Microsoft Foundry (hosted on Azure)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-microsoft-foundry)                                                                                                                                                                                                        | [Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/models/opus-5-5/overview)                                                                                           |
| 研究預覽            | Claude API                                                                                                                                                                                                                                                                                                                         | [Claude Opus 5](https://platform.claude.com/docs/zh-TW/models/opus-5/overview)                                                                                               |
| 已棄用<sup>2</sup> | Claude API                                                                                                                                                                                                                                                                                                                         | [Claude Opus 4.8](https://platform.claude.com/docs/zh-TW/models/opus-4-8/overview)                                                                                           |

1. 在 Microsoft Foundry 上，快速模式有自己的模型 ID，以 `-fast` 結尾。請將請求傳送至快速模式模型的部署，並省略 `speed`。
2. 移除日期：2026 年 11 月 30 日。移除後，對 `claude-opus-4-8` 發出且搭配 `speed: "fast"` 的請求將會傳回錯誤。若要繼續使用快速模式，請遷移至 Claude Opus 5.5。請參閱[從 Claude Opus 4.8 遷移至 Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8)。

#### [Managed Agents](https://platform.claude.com/docs/zh-TW/managed-agents/overview)

* 可用性：可用
* 用法：在代理的模型物件上設定 `speed`，例如 `{"id": "claude-opus-5-5", "speed": "fast"}`。

| 狀態              | 雲端平台                                                                                                                                                                      | 模型                                                                                 |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
| 可用              | Claude API, [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | [Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/models/opus-5-5/overview) |
| 研究預覽            | Claude API                                                                                                                                                                | [Claude Opus 5](https://platform.claude.com/docs/zh-TW/models/opus-5/overview)     |
| 已棄用<sup>1</sup> | Claude API                                                                                                                                                                | [Claude Opus 4.8](https://platform.claude.com/docs/zh-TW/models/opus-4-8/overview) |

1. 移除日期：2026 年 11 月 30 日。移除後，對 `claude-opus-4-8` 發出且搭配 `speed: "fast"` 的請求將會傳回錯誤。若要繼續使用快速模式，請遷移至 Claude Opus 5.5。請參閱[從 Claude Opus 4.8 遷移至 Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8)。

### 必要的 Beta 標頭

[Beta 標頭概覽](https://platform.claude.com/docs/zh-TW/api/beta-headers)

Beta 標頭可讓您在實驗性功能與新模型能力成為標準 API 的一部分之前搶先存取。

| 標頭                     | 模型                                                                                                                                                                 |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `fast-mode-2026-02-01` | [Claude Opus 5](https://platform.claude.com/docs/zh-TW/models/opus-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/zh-TW/models/opus-4-8/overview) |

### 資料處理

[資料處理概覽](https://platform.claude.com/docs/zh-TW/manage-claude/api-and-data-retention#feature-eligibility)

| 項目   | 零資料保留                                                                                                                                    | HIPAA |
| ---- | ---------------------------------------------------------------------------------------------------------------------------------------- | ----- |
| 狀態   | 符合資格（不含 [涵蓋的模型](https://platform.claude.com/docs/zh-TW/manage-claude/api-and-data-retention#model-specific-data-retention-requirements)） | 符合資格  |
| 詳細資訊 | 使用相同的 Messages API 端點，但推論速度更快。無論速度設定為何，ZDR 皆適用。                                                                                          | —     |

適用端點：

* `/v1/messages` 搭配 `speed: "fast"`

## 後續步驟

<CardGroup cols={2}>
  <Card title="結構化輸出" icon="code-brackets" href="https://platform.claude.com/docs/zh-TW/build-with-claude/structured-outputs">
    從代理工作流程中取得經過驗證的 JSON 結果。
  </Card>

  <Card title="定價" icon="calculator" href="https://platform.claude.com/docs/zh-TW/about-claude/pricing#fast-mode-pricing">
    了解 Anthropic 針對模型和功能的定價結構。
  </Card>

  <Card title="Effort" icon="gauge" href="https://platform.claude.com/docs/zh-TW/build-with-claude/effort">
    使用 effort 參數控制 Claude 回應時使用的 token 數量，在回應的完整度與 token 效率之間取得平衡。
  </Card>

  <Card title="串流訊息" icon="arrow-right" href="https://platform.claude.com/docs/zh-TW/build-with-claude/streaming">
    使用伺服器傳送事件以增量方式串流 Messages API 回應，包括文字、工具使用和擴展思考的增量內容。
  </Card>
</CardGroup>
