---
title: Token-Zählung
url: https://platform.claude.com/docs/de/build-with-claude/token-counting
description: Zähle die Token in einer Nachricht, bevor du sie an Claude sendest. Nutze Token-Zählungen, um Ratenlimits und Kosten zu verwalten, Entscheidungen zum Modell-Routing zu treffen und Prompts auf eine Ziellänge anzupassen.
featureMetadata:
  status: ga
  zdr:
    eligibility: eligible
    note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
  supportedPlatforms:
    Claude API: ga
    Claude Platform on AWS: ga
    Amazon Bedrock: ga
    Google Cloud: ga
    Microsoft Foundry: ga
---

Mit „token counting“ (Token-Zählung) kannst du die Anzahl der Token in einer Nachricht ermitteln, bevor du sie an Claude sendest. Das hilft dir, fundierte Entscheidungen über deine Prompts und deine Nutzung zu treffen. Mit der Token-Zählung kannst du:

* Ratenlimits und Kosten proaktiv verwalten
* Intelligente Entscheidungen zum Modell-Routing treffen
* Prompts auf eine bestimmte Länge optimieren

***

## So zählst du Nachrichten-Token

Der Endpunkt für die [Token-Zählung](https://platform.claude.com/docs/de/api/messages/count_tokens) akzeptiert dieselbe strukturierte Liste von Eingaben wie beim Erstellen einer Nachricht, einschließlich Unterstützung für System-Prompts, [Tools](https://platform.claude.com/docs/de/agents-and-tools/tool-use/overview), [Bilder](https://platform.claude.com/docs/de/build-with-claude/vision) und [PDFs](https://platform.claude.com/docs/de/build-with-claude/pdf-support). Die Antwort enthält die Gesamtzahl der Eingabe-Token.

Dieser Endpunkt gibt für einige Eingaben, die die Messages API akzeptiert, einen `invalid_request_error` zurück: [Server-Tools](https://platform.claude.com/docs/de/agents-and-tools/tool-use/server-tools) wie Websuche, Web-Abruf, Codeausführung und Tool-Suche (jedes Server-Tool außer dem [Advisor-Tool](https://platform.claude.com/docs/de/agents-and-tools/tool-use/advisor-tool)), den [MCP-Connector](https://platform.claude.com/docs/de/agents-and-tools/mcp-connector) sowie `image`- oder `document`-Blöcke mit einer `url`- oder `file`-Quelle. Sende Bilder und PDFs als base64, um sie zu zählen. Bei Anfragen, die Server-Tools oder MCP-Server verwenden, meldet die Antwort der Messages API die verwendeten Token in ihrem `usage`-Objekt.

<Note>
  Die Token-Zählung ist eine **Schätzung**. In manchen Fällen kann die tatsächliche Anzahl der beim Erstellen einer Nachricht verwendeten Eingabe-Token geringfügig abweichen.

  Token-Zählungen können Token enthalten, die von Anthropic automatisch für Systemoptimierungen hinzugefügt werden. **Vom System hinzugefügte Token werden dir nicht in Rechnung gestellt**. Die Abrechnung spiegelt nur deine Inhalte wider.
</Note>

### Unterstützte Modelle

Alle [aktiven Modelle](https://platform.claude.com/docs/de/models/overview) unterstützen die Token-Zählung.

<Note>
  Claude 4.7 und neuere Modelle sowie Claude Mythos Preview verwenden einen neueren Tokenizer. Derselbe Eingabetext erzeugt ungefähr 30 Prozent mehr Token als bei früheren Modellen. Der genaue Anstieg hängt vom Inhalt und von der Art des Workloads ab. Zähle Prompts erneut mit dem Modell, das du verwenden möchtest, anstatt Zählungen wiederzuverwenden, die mit früheren Modellen gemessen wurden.
</Note>

### Token in einfachen Nachrichten zählen

<CodeGroup>
  ```bash cURL
  curl https://api.anthropic.com/v1/messages/count_tokens \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "content-type: application/json" \
    -H "anthropic-version: 2023-06-01" \
    -d '{
      "model": "claude-opus-5-5",
      "system": "You are a scientist",
      "messages": [{
        "role": "user",
        "content": "Hello, Claude"
      }]
    }'
  ```

  ```bash CLI
  ant messages count-tokens \
    --model claude-opus-5-5 \
    --system "You are a scientist" \
    --message '{role: user, content: "Hello, Claude"}'
  ```

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

  response = client.messages.count_tokens(
      model="claude-opus-5-5",
      system="You are a scientist",
      messages=[{"role": "user", "content": "Hello, Claude"}],
  )

  print(response.json())
  ```

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

  const response = await client.messages.countTokens({
    model: "claude-opus-5-5",
    system: "You are a scientist",
    messages: [
      {
        role: "user",
        content: "Hello, Claude"
      }
    ]
  });

  console.log(response);
  ```

  ```csharp C#
  using System;
  using System.Threading.Tasks;
  using Anthropic;
  using Anthropic.Models.Messages;

  AnthropicClient client = new();

  var parameters = new MessageCountTokensParams
  {
      Model = Model.ClaudeOpus5_5,
      System = "You are a scientist",
      Messages = [new() { Role = Role.User, Content = "Hello, Claude" }]
  };

  var response = await client.Messages.CountTokens(parameters);
  Console.WriteLine(response);
  ```

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

  response, err := client.Messages.CountTokens(context.TODO(), anthropic.MessageCountTokensParams{
  	Model: anthropic.ModelClaudeOpus5_5,
  	System: anthropic.MessageCountTokensParamsSystemUnion{
  		OfString: anthropic.String("You are a scientist"),
  	},
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Hello, Claude")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }

  fmt.Println(response)
  ```

  ```java Java
  import com.anthropic.models.messages.MessageCountTokensParams;
  import com.anthropic.models.messages.MessageTokensCount;
  // ...

  public class CountTokensExample {

    public static void main(String[] args) {
      AnthropicClient client = AnthropicOkHttpClient.fromEnv();

      MessageCountTokensParams params = MessageCountTokensParams.builder()
        .model(Model.CLAUDE_OPUS_5_5)
        .system("You are a scientist")
        .addUserMessage("Hello, Claude")
        .build();

      MessageTokensCount count = client.messages().countTokens(params);
      System.out.println(count);
    }
  }
  ```

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

  $response = $client->messages->countTokens(
      messages: [
          ['role' => 'user', 'content' => 'Hello, Claude']
      ],
      model: 'claude-opus-5-5',
      system: 'You are a scientist',
  );

  echo json_encode($response);
  ```

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

  response = client.messages.count_tokens(
    model: "claude-opus-5-5",
    system: "You are a scientist",
    messages: [
      { role: "user", content: "Hello, Claude" }
    ]
  )

  puts response
  ```
</CodeGroup>

```json Output
{ "input_tokens": 14 }
```

### Token in Nachrichten mit Tools zählen

<Note>
  Die Token-Zählung unterstützt Client-Tools und das [Advisor-Tool](https://platform.claude.com/docs/de/agents-and-tools/tool-use/advisor-tool). Anfragen, die andere [Server-Tools](https://platform.claude.com/docs/de/agents-and-tools/tool-use/server-tools) enthalten, geben einen Fehler zurück. Beim Advisor-Tool umfasst die Zählung nur den ersten Sampling-Aufruf des Executors.
</Note>

<CodeGroup>
  ```bash cURL
  curl https://api.anthropic.com/v1/messages/count_tokens \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "content-type: application/json" \
    -H "anthropic-version: 2023-06-01" \
    -d '{
      "model": "claude-opus-5-5",
      "tools": [
        {
          "name": "get_weather",
          "description": "Get the current weather in a given location",
          "input_schema": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              }
            },
            "required": ["location"]
          }
        }
      ],
      "messages": [
        {
          "role": "user",
          "content": "What'\''s the weather like in San Francisco?"
        }
      ]
    }'
  ```

  ```bash CLI
  ant messages count-tokens <<'YAML'
  model: claude-opus-5-5
  tools:
    - name: get_weather
      description: Get the current weather in a given location
      input_schema:
        type: object
        properties:
          location:
            type: string
            description: The city and state, e.g. San Francisco, CA
        required:
          - location
  messages:
    - role: user
      content: What's the weather like in San Francisco?
  YAML
  ```

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

  response = client.messages.count_tokens(
      model="claude-opus-5-5",
      tools=[
          {
              "name": "get_weather",
              "description": "Get the current weather in a given location",
              "input_schema": {
                  "type": "object",
                  "properties": {
                      "location": {
                          "type": "string",
                          "description": "The city and state, e.g. San Francisco, CA",
                      }
                  },
                  "required": ["location"],
              },
          }
      ],
      messages=[{"role": "user", "content": "What's the weather like in San Francisco?"}],
  )

  print(response.json())
  ```

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

  const response = await client.messages.countTokens({
    model: "claude-opus-5-5",
    tools: [
      {
        name: "get_weather",
        description: "Get the current weather in a given location",
        input_schema: {
          type: "object",
          properties: {
            location: {
              type: "string",
              description: "The city and state, e.g. San Francisco, CA"
            }
          },
          required: ["location"]
        }
      }
    ],
    messages: [{ role: "user", content: "What's the weather like in San Francisco?" }]
  });

  console.log(response);
  ```

  ```csharp C#
  using System;
  using System.Collections.Generic;
  using System.Text.Json;
  using System.Threading.Tasks;
  using Anthropic;
  using Anthropic.Models.Messages;

  AnthropicClient client = new();

  var parameters = new MessageCountTokensParams
  {
      Model = Model.ClaudeOpus5_5,
      Tools =
      [
          new MessageCountTokensTool(new Tool()
          {
              Name = "get_weather",
              Description = "Get the current weather in a given location",
              InputSchema = new InputSchema()
              {
                  Properties = new Dictionary<string, JsonElement>
                  {
                      ["location"] = JsonSerializer.SerializeToElement(new { type = "string", description = "The city and state, e.g. San Francisco, CA" }),
                  },
                  Required = ["location"],
              },
          }),
      ],
      Messages = [new() { Role = Role.User, Content = "What's the weather like in San Francisco?" }]
  };

  var count = await client.Messages.CountTokens(parameters);
  Console.WriteLine(count);
  ```

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

  response, err := client.Messages.CountTokens(context.TODO(), anthropic.MessageCountTokensParams{
  	Model: anthropic.ModelClaudeOpus5_5,
  	Tools: []anthropic.MessageCountTokensToolUnionParam{
  		{OfTool: &anthropic.ToolParam{
  			Name:        "get_weather",
  			Description: anthropic.String("Get the current weather in a given location"),
  			InputSchema: anthropic.ToolInputSchemaParam{
  				Properties: map[string]any{
  					"location": map[string]any{
  						"type":        "string",
  						"description": "The city and state, e.g. San Francisco, CA",
  					},
  				},
  				Required: []string{"location"},
  			},
  		}},
  	},
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("What's the weather like in San Francisco?")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }

  jsonData, _ := json.MarshalIndent(response, "", "  ")
  fmt.Println(string(jsonData))
  ```

  ```java Java
  import com.anthropic.models.messages.MessageCountTokensParams;
  import com.anthropic.models.messages.MessageTokensCount;
  // ...
      AnthropicClient client = AnthropicOkHttpClient.fromEnv();

      InputSchema schema = InputSchema.builder()
        .properties(
          JsonValue.from(
            Map.of(
              "location",
              Map.of(
                "type",
                "string",
                "description",
                "The city and state, e.g. San Francisco, CA"
              )
            )
          )
        )
        .putAdditionalProperty("required", JsonValue.from(List.of("location")))
        .build();

      MessageCountTokensParams params = MessageCountTokensParams.builder()
        .model(Model.CLAUDE_OPUS_5_5)
        .addTool(
          Tool.builder()
            .name("get_weather")
            .description("Get the current weather in a given location")
            .inputSchema(schema)
            .build()
        )
        .addUserMessage("What's the weather like in San Francisco?")
        .build();

      MessageTokensCount count = client.messages().countTokens(params);
      System.out.println(count);
  ```

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

  $response = $client->messages->countTokens(
      messages: [
          ['role' => 'user', 'content' => "What's the weather like in San Francisco?"]
      ],
      model: 'claude-opus-5-5',
      tools: [
          [
              'name' => 'get_weather',
              'description' => 'Get the current weather in a given location',
              'input_schema' => [
                  'type' => 'object',
                  'properties' => [
                      'location' => [
                          'type' => 'string',
                          'description' => 'The city and state, e.g. San Francisco, CA'
                      ]
                  ],
                  'required' => ['location']
              ]
          ]
      ],
  );

  echo json_encode($response, JSON_PRETTY_PRINT);
  ```

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

  response = client.messages.count_tokens(
    model: "claude-opus-5-5",
    tools: [
      {
        name: "get_weather",
        description: "Get the current weather in a given location",
        input_schema: {
          type: "object",
          properties: {
            location: {
              type: "string",
              description: "The city and state, e.g. San Francisco, CA"
            }
          },
          required: ["location"]
        }
      }
    ],
    messages: [
      { role: "user", content: "What's the weather like in San Francisco?" }
    ]
  )

  puts response
  ```
</CodeGroup>

```json Output
{ "input_tokens": 403 }
```

### Token in Nachrichten mit Bildern zählen

<CodeGroup>
  ```bash cURL
  #!/bin/sh

  IMAGE_URL="https://platform.claude.com/docs/images/vision-example.jpg"
  IMAGE_MEDIA_TYPE="image/jpeg"
  IMAGE_BASE64=$(curl -s "$IMAGE_URL" | base64 | tr -d '\n')

  curl https://api.anthropic.com/v1/messages/count_tokens \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "content-type: application/json" \
    -d @- <<EOF
  {
    "model": "claude-opus-5-5",
    "messages": [
      {"role": "user", "content": [
        {"type": "image", "source": {
          "type": "base64",
          "media_type": "$IMAGE_MEDIA_TYPE",
          "data": "$IMAGE_BASE64"
        }},
        {"type": "text", "text": "Describe this image"}
      ]}
    ]
  }
  EOF
  ```

  ```bash CLI
  IMAGE_URL="https://platform.claude.com/docs/images/vision-example.jpg"
  curl -s "$IMAGE_URL" -o ./vision-example.jpg

  ant messages count-tokens <<'YAML'
  model: claude-opus-5-5
  messages:
    - role: user
      content:
        - type: image
          source:
            type: base64
            media_type: image/jpeg
            data: "@./vision-example.jpg"
        - type: text
          text: Describe this image
  YAML
  ```

  ```python Python
  import base64
  import httpx2

  image_url = "https://platform.claude.com/docs/images/vision-example.jpg"
  image_media_type = "image/jpeg"
  image_data = base64.standard_b64encode(httpx2.get(image_url).content).decode("utf-8")

  client = anthropic.Anthropic()

  response = client.messages.count_tokens(
      model="claude-opus-5-5",
      messages=[
          {
              "role": "user",
              "content": [
                  {
                      "type": "image",
                      "source": {
                          "type": "base64",
                          "media_type": image_media_type,
                          "data": image_data,
                      },
                  },
                  {"type": "text", "text": "Describe this image"},
              ],
          }
      ],
  )
  print(response.json())
  ```

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

  const imageUrl = "https://platform.claude.com/docs/images/vision-example.jpg";
  const imageMediaType = "image/jpeg";
  const imageArrayBuffer = await (await fetch(imageUrl)).arrayBuffer();
  const imageData = Buffer.from(imageArrayBuffer).toString("base64");

  const response = await anthropic.messages.countTokens({
    model: "claude-opus-5-5",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "image",
            source: {
              type: "base64",
              media_type: imageMediaType,
              data: imageData
            }
          },
          {
            type: "text",
            text: "Describe this image"
          }
        ]
      }
    ]
  });
  console.log(response);
  ```

  ```csharp C#
  using System;
  using System.Collections.Generic;
  using System.Net.Http;
  using System.Threading.Tasks;
  using Anthropic;
  using Anthropic.Models.Messages;

  AnthropicClient client = new();

  string imageUrl = "https://platform.claude.com/docs/images/vision-example.jpg";

  using HttpClient httpClient = new();
  byte[] imageBytes = await httpClient.GetByteArrayAsync(imageUrl);
  string imageData = Convert.ToBase64String(imageBytes);

  var parameters = new MessageCountTokensParams
  {
      Model = Model.ClaudeOpus5_5,
      Messages =
      [
          new()
          {
              Role = Role.User,
              Content = new MessageParamContent(new List<ContentBlockParam>
              {
                  new ContentBlockParam(new ImageBlockParam(
                      new ImageBlockParamSource(new Base64ImageSource()
                      {
                          Data = imageData,
                          MediaType = MediaType.ImageJpeg,
                      })
                  )),
                  new ContentBlockParam(new TextBlockParam("Describe this image")),
              }),
          }
      ]
  };

  var count = await client.Messages.CountTokens(parameters);
  Console.WriteLine(count);
  ```

  ```go Go
  imageURL := "https://platform.claude.com/docs/images/vision-example.jpg"

  req, err := http.NewRequest("GET", imageURL, nil)
  if err != nil {
  	log.Fatal(err)
  }
  req.Header.Set("User-Agent", "AnthropicDocsBot/1.0")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
  	log.Fatal(err)
  }
  defer resp.Body.Close()

  imageBytes, err := io.ReadAll(resp.Body)
  if err != nil {
  	log.Fatal(err)
  }
  imageData := base64.StdEncoding.EncodeToString(imageBytes)

  client := anthropic.NewClient()

  response, err := client.Messages.CountTokens(context.TODO(), anthropic.MessageCountTokensParams{
  	Model: anthropic.ModelClaudeOpus5_5,
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(
  			anthropic.NewImageBlockBase64("image/jpeg", imageData),
  			anthropic.NewTextBlock("Describe this image"),
  		),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }

  fmt.Println(response)
  ```

  ```java Java
  import com.anthropic.models.messages.Base64ImageSource;
  // ...
  import com.anthropic.models.messages.MessageCountTokensParams;
  import com.anthropic.models.messages.MessageTokensCount;
  // ...
      AnthropicClient client = AnthropicOkHttpClient.fromEnv();

      String imageUrl =
        "https://platform.claude.com/docs/images/vision-example.jpg";
      String imageMediaType = "image/jpeg";

      HttpClient httpClient = HttpClient.newHttpClient();
      HttpRequest request = HttpRequest.newBuilder().uri(URI.create(imageUrl)).build();
      byte[] imageBytes = httpClient
        .send(request, HttpResponse.BodyHandlers.ofByteArray())
        .body();
      String imageBase64 = Base64.getEncoder().encodeToString(imageBytes);

      ContentBlockParam imageBlock = ContentBlockParam.ofImage(
        ImageBlockParam.builder()
          .source(
            Base64ImageSource.builder()
              .mediaType(Base64ImageSource.MediaType.IMAGE_JPEG)
              .data(imageBase64)
              .build()
          )
          .build()
      );

      ContentBlockParam textBlock = ContentBlockParam.ofText(
        TextBlockParam.builder().text("Describe this image").build()
      );

      MessageCountTokensParams params = MessageCountTokensParams.builder()
        .model(Model.CLAUDE_OPUS_5_5)
        .addUserMessageOfBlockParams(List.of(imageBlock, textBlock))
        .build();

      MessageTokensCount count = client.messages().countTokens(params);
      System.out.println(count);
  ```

  ```php PHP
  $imageUrl = "https://platform.claude.com/docs/images/vision-example.jpg";
  $imageMediaType = "image/jpeg";
  $imageData = base64_encode(file_get_contents($imageUrl));

  $client = new Client();

  $response = $client->messages->countTokens(
      messages: [
          [
              'role' => 'user',
              'content' => [
                  [
                      'type' => 'image',
                      'source' => [
                          'type' => 'base64',
                          'media_type' => $imageMediaType,
                          'data' => $imageData
                      ]
                  ],
                  ['type' => 'text', 'text' => 'Describe this image']
              ]
          ]
      ],
      model: 'claude-opus-5-5',
  );
  print_r($response);
  ```

  ```ruby Ruby
  require "base64"
  require "net/http"

  image_url = "https://platform.claude.com/docs/images/vision-example.jpg"
  image_media_type = "image/jpeg"

  uri = URI(image_url)
  image_data = Base64.strict_encode64(Net::HTTP.get(uri))

  client = Anthropic::Client.new

  response = client.messages.count_tokens(
    model: "claude-opus-5-5",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "image",
            source: {
              type: "base64",
              media_type: image_media_type,
              data: image_data
            }
          },
          { type: "text", text: "Describe this image" }
        ]
      }
    ]
  )
  puts response
  ```
</CodeGroup>

```json Output
{ "input_tokens": 1028 }
```

Ein eingebetteter Bildblock, der [`"oversized_image": "error"`](https://platform.claude.com/docs/de/build-with-claude/vision-coordinates#oversized-image-error) setzt, wird beim Zählen genau so abgelehnt, wie ihn die Messages API ablehnen würde.

### Token in Nachrichten mit Thinking zählen

<Note>
  Weitere Details findest du unter [Nachdenken und das Kontextfenster](https://platform.claude.com/docs/de/build-with-claude/thinking#thinking-and-the-context-window).

  * Thinking-Blöcke aus **vorherigen** Assistenten-Turns zählen bei Modellen, die [alle vorherigen Turns beibehalten](https://platform.claude.com/docs/de/build-with-claude/thinking#thinking-block-preservation-by-model), zu deinen Eingabe-Token; bei Modellen, die nur den letzten Turn beibehalten, entfernt die API sie und sie zählen **nicht**
  * Thinking im **aktuellen** Assistenten-Turn **zählt** zu deinen Eingabe-Token
</Note>

<CodeGroup>
  ```bash cURL
  curl https://api.anthropic.com/v1/messages/count_tokens \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "content-type: application/json" \
    -H "anthropic-version: 2023-06-01" \
    -d '{
      "model": "claude-opus-5-5",
      "thinking": {
        "type": "adaptive"
      },
      "messages": [
        {
          "role": "user",
          "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?"
        },
        {
          "role": "assistant",
          "content": [
            {
              "type": "thinking",
              "thinking": "This is a nice number theory question. Lets think about it step by step...",
              "signature": "EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV..."
            },
            {
              "type": "text",
              "text": "Yes, there are infinitely many prime numbers p such that p mod 4 = 3..."
            }
          ]
        },
        {
          "role": "user",
          "content": "Can you write a formal proof?"
        }
      ]
    }'
  ```

  ```bash CLI
  ant messages count-tokens <<'YAML'
  model: claude-opus-5-5
  thinking:
    type: adaptive
  messages:
    - role: user
      content: Are there an infinite number of prime numbers such that n mod 4 == 3?
    - role: assistant
      content:
        - type: thinking
          thinking: >-
            This is a nice number theory question. Lets think about it step by step...
          signature: >-
            EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV...
        - type: text
          text: Yes, there are infinitely many prime numbers p such that p mod 4 = 3...
    - role: user
      content: Can you write a formal proof?
  YAML
  ```

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

  response = client.messages.count_tokens(
      model="claude-opus-5-5",
      thinking={"type": "adaptive"},
      messages=[
          {
              "role": "user",
              "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?",
          },
          {
              "role": "assistant",
              "content": [
                  {
                      "type": "thinking",
                      "thinking": "This is a nice number theory question. Let's think about it step by step...",
                      "signature": "EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV...",
                  },
                  {
                      "type": "text",
                      "text": "Yes, there are infinitely many prime numbers p such that p mod 4 = 3...",
                  },
              ],
          },
          {"role": "user", "content": "Can you write a formal proof?"},
      ],
  )

  print(response.json())
  ```

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

  const response = await client.messages.countTokens({
    model: "claude-opus-5-5",
    thinking: { type: "adaptive" },
    messages: [
      {
        role: "user",
        content: "Are there an infinite number of prime numbers such that n mod 4 == 3?"
      },
      {
        role: "assistant",
        content: [
          {
            type: "thinking",
            thinking:
              "This is a nice number theory question. Let's think about it step by step...",
            signature:
              "EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV..."
          },
          {
            type: "text",
            text: "Yes, there are infinitely many prime numbers p such that p mod 4 = 3..."
          }
        ]
      },
      {
        role: "user",
        content: "Can you write a formal proof?"
      }
    ]
  });

  console.log(response);
  ```

  ```csharp C#
  using System;
  using System.Threading.Tasks;
  using System.Collections.Generic;
  using Anthropic;
  using Anthropic.Models.Messages;

  AnthropicClient client = new();

  var parameters = new MessageCountTokensParams
  {
      Model = Model.ClaudeOpus5_5,
      Thinking = new ThinkingConfigAdaptive(),
      Messages =
      [
          new()
          {
              Role = Role.User,
              Content = "Are there an infinite number of prime numbers such that n mod 4 == 3?"
          },
          new()
          {
              Role = Role.Assistant,
              Content = new MessageParamContent(new List<ContentBlockParam>
              {
                  new ContentBlockParam(new ThinkingBlockParam()
                  {
                      Thinking = "This is a nice number theory question. Let's think about it step by step...",
                      Signature = "EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV...",
                  }),
                  new ContentBlockParam(new TextBlockParam("Yes, there are infinitely many prime numbers p such that p mod 4 = 3...")),
              }),
          },
          new()
          {
              Role = Role.User,
              Content = "Can you write a formal proof?"
          }
      ]
  };

  var response = await client.Messages.CountTokens(parameters);
  Console.WriteLine(response);
  ```

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

  thinkingBlock := anthropic.NewThinkingBlock(
  	"EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV...",
  	"This is a nice number theory question. Let's think about it step by step...",
  )

  textBlock := anthropic.NewTextBlock(
  	"Yes, there are infinitely many prime numbers p such that p mod 4 = 3...",
  )

  response, err := client.Messages.CountTokens(context.TODO(), anthropic.MessageCountTokensParams{
  	Model: anthropic.ModelClaudeOpus5_5,
  	Thinking: anthropic.ThinkingConfigParamUnion{
  		OfAdaptive: &anthropic.ThinkingConfigAdaptiveParam{},
  	},
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Are there an infinite number of prime numbers such that n mod 4 == 3?")),
  		anthropic.NewAssistantMessage(thinkingBlock, textBlock),
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Can you write a formal proof?")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }

  fmt.Printf("%+v\n", response)
  ```

  ```java Java
  import com.anthropic.models.messages.MessageCountTokensParams;
  import com.anthropic.models.messages.MessageTokensCount;
  // ...
  import com.anthropic.models.messages.ThinkingBlockParam;
  import com.anthropic.models.messages.ThinkingConfigAdaptive;
  // ...
      AnthropicClient client = AnthropicOkHttpClient.fromEnv();

      List<ContentBlockParam> assistantBlocks = List.of(
        ContentBlockParam.ofThinking(
          ThinkingBlockParam.builder()
            .thinking(
              "This is a nice number theory question. Let's think about it step by step..."
            )
            .signature(
              "EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV..."
            )
            .build()
        ),
        ContentBlockParam.ofText(
          TextBlockParam.builder()
            .text("Yes, there are infinitely many prime numbers p such that p mod 4 = 3...")
            .build()
        )
      );

      MessageCountTokensParams params = MessageCountTokensParams.builder()
        .model(Model.CLAUDE_OPUS_5_5)
        .thinking(ThinkingConfigAdaptive.builder().build())
        .addUserMessage("Are there an infinite number of prime numbers such that n mod 4 == 3?")
        .addAssistantMessageOfBlockParams(assistantBlocks)
        .addUserMessage("Can you write a formal proof?")
        .build();

      MessageTokensCount count = client.messages().countTokens(params);
      System.out.println(count);
  ```

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

  $response = $client->messages->countTokens(
      messages: [
          [
              'role' => 'user',
              'content' => 'Are there an infinite number of prime numbers such that n mod 4 == 3?'
          ],
          [
              'role' => 'assistant',
              'content' => [
                  [
                      'type' => 'thinking',
                      'thinking' => 'This is a nice number theory question. Let\'s think about it step by step...',
                      'signature' => 'EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV...'
                  ],
                  [
                      'type' => 'text',
                      'text' => 'Yes, there are infinitely many prime numbers p such that p mod 4 = 3...'
                  ]
              ]
          ],
          [
              'role' => 'user',
              'content' => 'Can you write a formal proof?'
          ]
      ],
      model: 'claude-opus-5-5',
      thinking: ['type' => 'adaptive'],
  );

  echo json_encode($response);
  ```

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

  response = client.messages.count_tokens(
    model: "claude-opus-5-5",
    thinking: {
      type: "adaptive"
    },
    messages: [
      {
        role: "user",
        content: "Are there an infinite number of prime numbers such that n mod 4 == 3?"
      },
      {
        role: "assistant",
        content: [
          {
            type: "thinking",
            thinking: "This is a nice number theory question. Let's think about it step by step...",
            signature: "EuYBCkQYAiJAgCs1le6/Pol5Z4/JMomVOouGrWdhYNsH3ukzUECbB6iWrSQtsQuRHJID6lWV..."
          },
          {
            type: "text",
            text: "Yes, there are infinitely many prime numbers p such that p mod 4 = 3..."
          }
        ]
      },
      {
        role: "user",
        content: "Can you write a formal proof?"
      }
    ]
  )

  puts response
  ```
</CodeGroup>

```json Output
{ "input_tokens": 88 }
```

### Token in Nachrichten mit PDFs zählen

<Note>
  Die Token-Zählung unterstützt base64-kodierte PDFs mit denselben [PDF-Anforderungen](https://platform.claude.com/docs/de/build-with-claude/pdf-support#check-pdf-requirements) wie die Messages API. Dieser Endpunkt unterstützt keine `url`- oder `file`-Dokumentquellen.
</Note>

<CodeGroup>
  ```bash cURL
  curl https://api.anthropic.com/v1/messages/count_tokens \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "content-type: application/json" \
    -H "anthropic-version: 2023-06-01" \
    -d @- <<EOF
  {
    "model": "claude-opus-5-5",
    "messages": [{
      "role": "user",
      "content": [
        {
          "type": "document",
          "source": {
            "type": "base64",
            "media_type": "application/pdf",
            "data": "$PDF_BASE64"
          }
        },
        {
          "type": "text",
          "text": "Please summarize this document."
        }
      ]
    }]
  }
  EOF
  ```

  ```bash CLI
  ant messages count-tokens <<'YAML'
  model: claude-opus-5-5
  messages:
    - role: user
      content:
        - type: document
          source:
            type: base64
            media_type: application/pdf
            data: "@./document.pdf"
        - type: text
          text: Please summarize this document.
  YAML
  ```

  ```python Python
  import base64
  import anthropic

  client = anthropic.Anthropic()

  with open("/path/to/document.pdf", "rb") as pdf_file:
      pdf_base64 = base64.standard_b64encode(pdf_file.read()).decode("utf-8")

  response = client.messages.count_tokens(
      model="claude-opus-5-5",
      messages=[
          {
              "role": "user",
              "content": [
                  {
                      "type": "document",
                      "source": {
                          "type": "base64",
                          "media_type": "application/pdf",
                          "data": pdf_base64,
                      },
                  },
                  {"type": "text", "text": "Please summarize this document."},
              ],
          }
      ],
  )

  print(response.json())
  ```

  ```typescript TypeScript
  import { readFile } from "node:fs/promises";

  const client = new Anthropic();

  const pdfBase64 = await readFile("/path/to/document.pdf", { encoding: "base64" });

  const response = await client.messages.countTokens({
    model: "claude-opus-5-5",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "document",
            source: {
              type: "base64",
              media_type: "application/pdf",
              data: pdfBase64
            }
          },
          {
            type: "text",
            text: "Please summarize this document."
          }
        ]
      }
    ]
  });

  console.log(response);
  ```

  ```csharp C#
  using System;
  using System.IO;
  using System.Threading.Tasks;
  using System.Collections.Generic;
  using Anthropic;
  using Anthropic.Models.Messages;

  AnthropicClient client = new();

  byte[] pdfBytes = await File.ReadAllBytesAsync("/path/to/document.pdf");
  string pdfBase64 = Convert.ToBase64String(pdfBytes);

  var parameters = new MessageCountTokensParams
  {
      Model = Model.ClaudeOpus5_5,
      Messages =
      [
          new()
          {
              Role = Role.User,
              Content = new MessageParamContent(new List<ContentBlockParam>
              {
                  new ContentBlockParam(new DocumentBlockParam(
                      new DocumentBlockParamSource(new Base64PdfSource()
                      {
                          Data = pdfBase64,
                      })
                  )),
                  new ContentBlockParam(new TextBlockParam("Please summarize this document.")),
              }),
          }
      ]
  };

  var count = await client.Messages.CountTokens(parameters);
  Console.WriteLine(count);
  ```

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

  pdfBytes, err := os.ReadFile("/path/to/document.pdf")
  if err != nil {
  	log.Fatal(err)
  }
  pdfBase64 := base64.StdEncoding.EncodeToString(pdfBytes)

  response, err := client.Messages.CountTokens(context.TODO(), anthropic.MessageCountTokensParams{
  	Model: anthropic.ModelClaudeOpus5_5,
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(
  			anthropic.NewDocumentBlock(anthropic.Base64PDFSourceParam{
  				Data: pdfBase64,
  			}),
  			anthropic.NewTextBlock("Please summarize this document."),
  		),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }

  fmt.Println(response)
  ```

  ```java Java
  import com.anthropic.models.messages.Base64PdfSource;
  // ...
  import com.anthropic.models.messages.DocumentBlockParam;
  import com.anthropic.models.messages.MessageCountTokensParams;
  import com.anthropic.models.messages.MessageTokensCount;
  // ...
      AnthropicClient client = AnthropicOkHttpClient.fromEnv();

      byte[] fileBytes = Files.readAllBytes(Path.of("/path/to/document.pdf"));
      String pdfBase64 = Base64.getEncoder().encodeToString(fileBytes);

      ContentBlockParam documentBlock = ContentBlockParam.ofDocument(
        DocumentBlockParam.builder()
          .source(Base64PdfSource.builder().data(pdfBase64).build())
          .build()
      );

      ContentBlockParam textBlock = ContentBlockParam.ofText(
        TextBlockParam.builder().text("Please summarize this document.").build()
      );

      MessageCountTokensParams params = MessageCountTokensParams.builder()
        .model(Model.CLAUDE_OPUS_5_5)
        .addUserMessageOfBlockParams(List.of(documentBlock, textBlock))
        .build();

      MessageTokensCount count = client.messages().countTokens(params);
      System.out.println(count);
  ```

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

  $pdfBase64 = base64_encode(file_get_contents("/path/to/document.pdf"));

  $response = $client->messages->countTokens(
      messages: [
          [
              'role' => 'user',
              'content' => [
                  [
                      'type' => 'document',
                      'source' => [
                          'type' => 'base64',
                          'media_type' => 'application/pdf',
                          'data' => $pdfBase64
                      ]
                  ],
                  [
                      'type' => 'text',
                      'text' => 'Please summarize this document.'
                  ]
              ]
          ]
      ],
      model: 'claude-opus-5-5',
  );

  echo json_encode($response);
  ```

  ```ruby Ruby
  require "base64"

  client = Anthropic::Client.new

  pdf_base64 = Base64.strict_encode64(File.binread("/path/to/document.pdf"))

  response = client.messages.count_tokens(
    model: "claude-opus-5-5",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "document",
            source: {
              type: "base64",
              media_type: "application/pdf",
              data: pdf_base64
            }
          },
          {
            type: "text",
            text: "Please summarize this document."
          }
        ]
      }
    ]
  )

  puts response
  ```
</CodeGroup>

```json Output
{ "input_tokens": 2188 }
```

***

## Token-Zählungen bei Claude Fable- und Claude Mythos-Modellen

Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5 und Claude Mythos 5 teilen sich den mit Claude Opus 4.7 eingeführten Tokenizer. Ein Prompt wird auf allen vier gleich gezählt und liegt etwa 30 Prozent höher als bei Modellen vor Claude Opus 4.7 (der genaue Anstieg hängt vom Inhalt ab). Der Endpunkt für die Token-Zählung zählt mit dem Tokenizer des `model`, das du übergibst. Um den Unterschied für deinen Workload zu messen, zähle dieselbe Anfrage zweimal, einmal mit deinem aktuellen Modell und einmal mit dem Modell, zu dem du wechseln möchtest, und vergleiche die beiden `input_tokens`-Werte.

<Note>
  **Abrechnung und Migration:** Nutzung und Abrechnung bei diesen Modellen spiegeln die Zählungen dieses Tokenizers wider. Wenn du von einem Modell vor Claude Opus 4.7 migrierst, verwende keine auf dem älteren Modell gemessenen Token-Zählungen wieder, um Kosten oder die Passung ins Kontextfenster abzuschätzen. Zähle deine Prompts mit der `model`-ID, die du verwenden möchtest (zum Beispiel `"claude-fable-5-1"`).
</Note>

***

## Preise und Ratenlimits

Die Token-Zählung ist **kostenlos nutzbar**, unterliegt aber Ratenlimits für Anfragen pro Minute, die auf deiner [Nutzungsstufe](https://platform.claude.com/docs/de/api/rate-limits#rate-limits) basieren. Wenn du höhere Limits benötigst, verwende **Request tier increase** auf der Seite [Ratenlimits](https://platform.claude.com/usage/limits).

| Nutzungsstufe | Anfragen pro Minute (RPM) |
| ------------- | ------------------------- |
| Start         | 5.000                     |
| Build         | 10.000                    |
| Scale         | 20.000                    |

<Note>
  Token-Zählung und Nachrichtenerstellung haben getrennte und voneinander unabhängige Ratenlimits. Die Nutzung des einen wird nicht auf die Limits des anderen angerechnet.
</Note>

***

## FAQ

<AccordionGroup>
  <Accordion title="Verwendet die Token-Zählung Prompt-Caching?">
    Nein, die Token-Zählung liefert eine Schätzung, ohne Caching-Logik zu verwenden. Du kannst zwar `cache_control`-Blöcke in deiner Token-Zählungsanfrage angeben, aber Prompt-Caching findet nur bei der tatsächlichen Nachrichtenerstellung statt.
  </Accordion>
</AccordionGroup>

***

## Nächste Schritte

<CardGroup cols={2}>
  <Card title="Nachrichten-Token zählen" icon="code" href="https://platform.claude.com/docs/de/api/messages/count_tokens">
    Lies die vollständige API-Referenz für den Endpunkt zur Token-Zählung.
  </Card>

  <Card title="Kontextfenster" icon="arrows-maximize" href="https://platform.claude.com/docs/de/build-with-claude/context-windows">
    Nutze Token-Zählungen, um Prompts innerhalb des Kontextfensters eines Modells zu halten.
  </Card>

  <Card title="Ratenlimits" icon="gauge" href="https://platform.claude.com/docs/de/api/rate-limits">
    Prüfe Token-Zählungen, bevor du eine Anfrage sendest, um innerhalb deiner Nutzungsstufe zu bleiben.
  </Card>

  <Card title="Prompt-Caching" icon="database" href="https://platform.claude.com/docs/de/build-with-claude/prompt-caching">
    Reduziere Kosten und Latenz bei wiederholten Prompts, indem du Prompt-Präfixe cachst.
  </Card>
</CardGroup>