---
title: Conteggio dei token
url: https://platform.claude.com/docs/it/build-with-claude/token-counting
description: Conta i token in un messaggio prima di inviarlo a Claude. Usa i conteggi dei token per gestire limiti di velocità e costi, prendere decisioni di instradamento dei modelli e adattare i prompt a una lunghezza target.
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
---

Il "token counting" (conteggio dei token) ti consente di determinare il numero di token in un messaggio prima di inviarlo a Claude. Questo ti aiuta a prendere decisioni informate sui tuoi prompt e sul tuo utilizzo. Con il conteggio dei token, puoi:

* Gestire in modo proattivo i "rate limits" (limiti di velocità) e i costi
* Prendere decisioni intelligenti di instradamento dei modelli
* Ottimizzare i prompt per una lunghezza specifica

***

## Come contare i token di un messaggio

L'endpoint di [conteggio dei token](https://platform.claude.com/docs/it/api/messages/count_tokens) accetta lo stesso elenco strutturato di input usato per creare un messaggio, incluso il supporto per "system prompts" (prompt di sistema), [strumenti](https://platform.claude.com/docs/it/agents-and-tools/tool-use/overview), [immagini](https://platform.claude.com/docs/it/build-with-claude/vision) e [PDF](https://platform.claude.com/docs/it/build-with-claude/pdf-support). La risposta contiene il numero totale di token di input.

Questo endpoint restituisce un `invalid_request_error` per alcuni input che la Messages API accetta: gli [strumenti server](https://platform.claude.com/docs/it/agents-and-tools/tool-use/server-tools) come la ricerca web, il recupero web, l'esecuzione di codice e la ricerca di strumenti (tutti gli strumenti server tranne lo [strumento advisor](https://platform.claude.com/docs/it/agents-and-tools/tool-use/advisor-tool)), il [connettore per il "Model Context Protocol", o MCP](https://platform.claude.com/docs/it/agents-and-tools/mcp-connector), e i blocchi `image` o `document` con una sorgente `url` o `file`. Invia immagini e PDF in base64 per contarli. Per le richieste che usano strumenti server o server MCP, la risposta della Messages API riporta i token utilizzati nel suo oggetto `usage`.

<Note>
  Il conteggio dei token è una **stima**. In alcuni casi, il numero effettivo di token di input utilizzati durante la creazione di un messaggio potrebbe differire di una piccola quantità.

  I conteggi dei token possono includere token aggiunti automaticamente da Anthropic per ottimizzazioni di sistema. **Non ti vengono addebitati i token aggiunti dal sistema**. La fatturazione riflette solo i tuoi contenuti.
</Note>

### Modelli supportati

Tutti i [modelli attivi](https://platform.claude.com/docs/it/models/overview) supportano il conteggio dei token.

<Note>
  I modelli Claude 4.7 e successivi e Claude Mythos Preview utilizzano un tokenizer più recente. Lo stesso testo di input produce circa il 30 percento di token in più rispetto ai modelli precedenti. L'aumento esatto dipende dal contenuto e dalla forma del carico di lavoro. Riconta i prompt rispetto al modello che intendi utilizzare anziché riutilizzare i conteggi misurati su modelli precedenti.
</Note>

### Contare i token in messaggi di base

<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 }
```

### Contare i token in messaggi con strumenti

<Note>
  Il conteggio dei token supporta gli strumenti client e lo [strumento advisor](https://platform.claude.com/docs/it/agents-and-tools/tool-use/advisor-tool). Le richieste che includono altri [strumenti server](https://platform.claude.com/docs/it/agents-and-tools/tool-use/server-tools) restituiscono un errore. Per lo strumento advisor, il conteggio copre solo la prima chiamata di campionamento dell'esecutore.
</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 }
```

### Contare i token in messaggi con immagini

<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 }
```

Un blocco immagine incorporato che imposta [`"oversized_image": "error"`](https://platform.claude.com/docs/it/build-with-claude/vision-coordinates#oversized-image-error) viene rifiutato al momento del conteggio esattamente come lo rifiuterebbe la Messages API.

### Contare i token in messaggi con thinking

<Note>
  Consulta [Ragionamento e finestra di contesto](https://platform.claude.com/docs/it/build-with-claude/thinking#thinking-and-the-context-window) per maggiori dettagli.

  * I blocchi di ragionamento dei turni **precedenti** dell'assistente vengono conteggiati nei tuoi token di input sui modelli che [conservano tutti i turni precedenti](https://platform.claude.com/docs/it/build-with-claude/thinking#thinking-block-preservation-by-model); sui modelli che conservano solo l'ultimo turno, l'API li rimuove e **non** vengono conteggiati
  * Il ragionamento del turno **corrente** dell'assistente **viene** conteggiato nei tuoi token di input
</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 }
```

### Contare i token in messaggi con PDF

<Note>
  Il conteggio dei token supporta i PDF codificati in base64 con gli stessi [requisiti per i PDF](https://platform.claude.com/docs/it/build-with-claude/pdf-support#check-pdf-requirements) della Messages API. Questo endpoint non supporta le sorgenti di documenti `url` o `file`.
</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 }
```

***

## Conteggi dei token sui modelli Claude Fable e Claude Mythos

Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5 e Claude Mythos 5 condividono il tokenizer introdotto con Claude Opus 4.7. Un prompt produce lo stesso conteggio su tutti e quattro, e circa il 30 percento in più rispetto ai modelli precedenti a Claude Opus 4.7 (l'aumento esatto dipende dal contenuto). L'endpoint di conteggio dei token conta secondo il tokenizer del `model` che passi. Per misurare la differenza per il tuo carico di lavoro, conta la stessa richiesta due volte, una con il tuo modello attuale e una con il modello a cui intendi passare, e confronta i due valori di `input_tokens`.

<Note>
  **Fatturazione e migrazione:** L'utilizzo e la fatturazione su questi modelli riflettono i conteggi di questo tokenizer. Quando migri da un modello precedente a Claude Opus 4.7, non riutilizzare i conteggi dei token misurati sul modello più vecchio per stimare i costi o l'adattamento alla finestra di contesto. Conta i tuoi prompt con l'ID `model` che intendi utilizzare (ad esempio, `"claude-fable-5-1"`).
</Note>

***

## Prezzi e limiti di velocità

Il conteggio dei token è **gratuito** ma è soggetto a limiti di velocità in richieste al minuto basati sul tuo [livello di utilizzo](https://platform.claude.com/docs/it/api/rate-limits#rate-limits). Se hai bisogno di limiti più elevati, usa **Request tier increase** nella pagina [Limiti di velocità](https://platform.claude.com/usage/limits).

| Livello di utilizzo | Richieste al minuto (RPM) |
| ------------------- | ------------------------- |
| Start               | 5.000                     |
| Build               | 10.000                    |
| Scale               | 20.000                    |

<Note>
  Il conteggio dei token e la creazione di messaggi hanno limiti di velocità separati e indipendenti. L'utilizzo di uno non incide sui limiti dell'altro.
</Note>

***

## Domande frequenti

<AccordionGroup>
  <Accordion title="Il conteggio dei token utilizza la cache dei prompt?">
    No, il conteggio dei token fornisce una stima senza utilizzare la logica di caching. Sebbene tu possa fornire blocchi `cache_control` nella tua richiesta di conteggio dei token, la "prompt caching" (cache dei prompt) avviene solo durante l'effettiva creazione del messaggio.
  </Accordion>
</AccordionGroup>

***

## Passaggi successivi

<CardGroup cols={2}>
  <Card title="Contare i token di un messaggio" icon="code" href="https://platform.claude.com/docs/it/api/messages/count_tokens">
    Leggi il riferimento API completo per l'endpoint di conteggio dei token.
  </Card>

  <Card title="Finestre di contesto" icon="arrows-maximize" href="https://platform.claude.com/docs/it/build-with-claude/context-windows">
    Usa i conteggi dei token per mantenere i prompt entro la finestra di contesto di un modello.
  </Card>

  <Card title="Limiti di velocità" icon="gauge" href="https://platform.claude.com/docs/it/api/rate-limits">
    Controlla i conteggi dei token prima di inviare una richiesta per rimanere entro il tuo livello di utilizzo.
  </Card>

  <Card title="Cache dei prompt" icon="database" href="https://platform.claude.com/docs/it/build-with-claude/prompt-caching">
    Riduci costi e latenza sui prompt ripetuti memorizzando nella cache i prefissi dei prompt.
  </Card>
</CardGroup>