Building with extended thinking

ant messages create \
  --transform content --format yaml \
    --model claude-sonnet-4-6 \
    --max-tokens 16000 \
    --thinking '{type: enabled, budget_tokens: 10000}' \
    --message '{role: user, content: Are there an infinite number of prime numbers such that n mod 4 == 3?}'

import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    messages=[
        {
            "role": "user",
            "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?",
        }
    ],
)

# The response contains summarized thinking blocks and text blocks
for block in response.content:
    if block.type == "thinking":
        print(f"\nThinking summary: {block.thinking}")
    elif block.type == "text":
        print(f"\nResponse: {block.text}")

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic();

const response = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  messages: [
    {
      role: "user",
      content: "Are there an infinite number of prime numbers such that n mod 4 == 3?"
    }
  ]
});

// The response contains summarized thinking blocks and text blocks
for (const block of response.content) {
  if (block.type === "thinking") {
    console.log(`\nThinking summary: ${block.thinking}`);
  } else if (block.type === "text") {
    console.log(`\nResponse: ${block.text}`);
  }
}

using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

var parameters = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 16000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 10000),
    Messages = [
        new() {
            Role = Role.User,
            Content = "Are there an infinite number of prime numbers such that n mod 4 == 3?"
        }
    ]
};

var message = await client.Messages.Create(parameters);

foreach (var block in message.Content)
{
    if (block.TryPickThinking(out ThinkingBlock? thinking))
    {
        Console.WriteLine({{CONTENT}}quot;\nThinking summary: {thinking.Thinking}");
    }
    else if (block.TryPickText(out TextBlock? text))
    {
        Console.WriteLine({{CONTENT}}quot;\nResponse: {text.Text}");
    }
}

package main

import (
	"context"
	"fmt"
	"log"

	"github.com/anthropics/anthropic-sdk-go"
)

func main() {
	client := anthropic.NewClient()

	response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 16000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(10000),
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("Are there an infinite number of prime numbers such that n mod 4 == 3?")),
		},
	})
	if err != nil {
		log.Fatal(err)
	}

	for _, block := range response.Content {
		switch v := block.AsAny().(type) {
		case anthropic.ThinkingBlock:
			fmt.Printf("\nThinking summary: %s", v.Thinking)
		case anthropic.TextBlock:
			fmt.Printf("\nResponse: %s", v.Text)
		}
	}
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.Model;

void main() {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    MessageCreateParams params = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(16000L)
        .enabledThinking(10000L)
        .addUserMessage("Are there an infinite number of prime numbers such that n mod 4 == 3?")
        .build();

    Message response = client.messages().create(params);

    response.content().forEach(block -> {
        block.thinking().ifPresent(thinkingBlock ->
            IO.println("\nThinking summary: " + thinkingBlock.thinking())
        );
        block.text().ifPresent(textBlock ->
            IO.println("\nResponse: " + textBlock.text())
        );
    });
}

<?php

use Anthropic\Client;

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

$message = $client->messages->create(
    maxTokens: 16000,
    messages: [
        [
            'role' => 'user',
            'content' => 'Are there an infinite number of prime numbers such that n mod 4 == 3?'
        ]
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 10000],
);

foreach ($message->content as $block) {
    if ($block->type === 'thinking') {
        echo "\nThinking summary: " . $block->thinking;
    } elseif ($block->type === 'text') {
        echo "\nResponse: " . $block->text;
    }
}

require "anthropic"

client = Anthropic::Client.new

message = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  messages: [
    {
      role: "user",
      content: "Are there an infinite number of prime numbers such that n mod 4 == 3?"
    }
  ]
)

message.content.each do |block|
  case block.type
  when :thinking
    puts "\nThinking summary: #{block.thinking}"
  when :text
    puts "\nResponse: #{block.text}"
  end
end

ant messages create \
  --model claude-sonnet-4-6 \
  --max-tokens 16000 \
  --transform content --format yaml \
    --thinking '{type: enabled, budget_tokens: 10000, display: omitted}' \
    --message '{role: user, content: "What is 27 * 453?"}'

import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={
        "type": "enabled",
        "budget_tokens": 10000,
        "display": "omitted",
    },
    messages=[
        {"role": "user", "content": "What is 27 * 453?"},
    ],
)

for block in response.content:
    if block.type == "thinking":
        if block.thinking:
            print(f"Thinking: {block.thinking}")
        else:
            print("Thinking: [omitted]")
    elif block.type == "text":
        print(f"Response: {block.text}")

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic();

const response = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000,
    display: "omitted"
  },
  messages: [
    {
      role: "user",
      content: "What is 27 * 453?"
    }
  ]
});

for (const block of response.content) {
  if (block.type === "thinking") {
    if (block.thinking.length > 0) {
      console.log(`Thinking: ${block.thinking}`);
    } else {
      console.log("Thinking: [omitted]");
    }
  } else if (block.type === "text") {
    console.log(`Response: ${block.text}`);
  }
}

using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

var message = await client.Messages.Create(new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 16000,
    Thinking = new ThinkingConfigEnabled
    {
        BudgetTokens = 10000,
        Display = ThinkingConfigEnabledDisplay.Omitted
    },
    Messages =
    [
        new() { Role = Role.User, Content = "What is 27 * 453?" }
    ]
});

foreach (var block in message.Content)
{
    if (block.TryPickThinking(out ThinkingBlock? thinking))
    {
        Console.WriteLine(string.IsNullOrEmpty(thinking.Thinking)
            ? "Thinking: [omitted]"
            : {{CONTENT}}quot;Thinking: {thinking.Thinking}");
    }
    else if (block.TryPickText(out TextBlock? text))
    {
        Console.WriteLine({{CONTENT}}quot;Response: {text.Text}");
    }
}

package main

import (
	"cmp"
	"context"
	"fmt"
	"log"

	"github.com/anthropics/anthropic-sdk-go"
)

func main() {
	client := anthropic.NewClient()

	response, err := client.Messages.New(context.Background(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 16000,
		Thinking: anthropic.ThinkingConfigParamUnion{
			OfEnabled: &anthropic.ThinkingConfigEnabledParam{
				BudgetTokens: 10000,
				Display:      anthropic.ThinkingConfigEnabledDisplayOmitted,
			},
		},
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("What is 27 * 453?")),
		},
	})
	if err != nil {
		log.Fatal(err)
	}

	for _, block := range response.Content {
		switch v := block.AsAny().(type) {
		case anthropic.ThinkingBlock:
			fmt.Println("Thinking:", cmp.Or(v.Thinking, "[omitted]"))
		case anthropic.TextBlock:
			fmt.Println("Response:", v.Text)
		}
	}
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.Model;
import com.anthropic.models.messages.ThinkingConfigEnabled;

void main() {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    MessageCreateParams params = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(16000L)
        .thinking(ThinkingConfigEnabled.builder()
            .budgetTokens(10000L)
            .display(ThinkingConfigEnabled.Display.OMITTED)
            .build())
        .addUserMessage("What is 27 * 453?")
        .build();

    Message message = client.messages().create(params);

    message.content().forEach(block -> {
        block.thinking().ifPresent(thinkingBlock -> {
            if (thinkingBlock.thinking().isEmpty()) {
                IO.println("Thinking: [omitted]");
            } else {
                IO.println("Thinking: " + thinkingBlock.thinking());
            }
        });
        block.text().ifPresent(textBlock ->
            IO.println("Response: " + textBlock.text())
        );
    });
}

<?php

use Anthropic\Client;
use Anthropic\Messages\TextBlock;
use Anthropic\Messages\ThinkingBlock;
use Anthropic\Messages\ThinkingConfigEnabled;
use Anthropic\Messages\ThinkingConfigEnabled\Display;

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

$response = $client->messages->create(
    model: 'claude-sonnet-4-6',
    maxTokens: 16000,
    thinking: ThinkingConfigEnabled::with(
        budgetTokens: 10000,
        display: Display::OMITTED,
    ),
    messages: [
        ['role' => 'user', 'content' => 'What is 27 * 453?'],
    ],
);

foreach ($response->content as $block) {
    echo match (true) {
        $block instanceof ThinkingBlock && $block->thinking === '' => "Thinking: [omitted]\n",
        $block instanceof ThinkingBlock => "Thinking: {$block->thinking}\n",
        $block instanceof TextBlock => "Response: {$block->text}\n",
        default => '',
    };
}

require "anthropic"

client = Anthropic::Client.new

response = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: :enabled,
    budget_tokens: 10000,
    # The Ruby SDK uses `display_` (trailing underscore) to avoid
    # shadowing Kernel#display; the wire field is still `display`.
    display_: :omitted
  },
  messages: [{role: "user", content: "What is 27 * 453?"}]
)

response.content.each do |block|
  case block.type
  when :thinking
    puts block.thinking.empty? ? "Thinking: [omitted]" : "Thinking: #{block.thinking}"
  when :text
    puts "Response: #{block.text}"
  end
end

ant messages create --stream --format jsonl \
  --model claude-sonnet-4-6 \
  --max-tokens 16000 \
  --thinking '{type: enabled, budget_tokens: 10000}' \
  --message '{role: user, content: What is the greatest common divisor of 1071 and 462?}'

import anthropic

client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    messages=[
        {
            "role": "user",
            "content": "What is the greatest common divisor of 1071 and 462?",
        }
    ],
) as stream:
    thinking_started = False
    response_started = False

    for event in stream:
        if event.type == "content_block_start":
            print(f"\nStarting {event.content_block.type} block...")
            # Reset flags for each new block
            thinking_started = False
            response_started = False
        elif event.type == "content_block_delta":
            if event.delta.type == "thinking_delta":
                if not thinking_started:
                    print("Thinking: ", end="", flush=True)
                    thinking_started = True
                print(event.delta.thinking, end="", flush=True)
            elif event.delta.type == "text_delta":
                if not response_started:
                    print("Response: ", end="", flush=True)
                    response_started = True
                print(event.delta.text, end="", flush=True)
        elif event.type == "content_block_stop":
            print("\nBlock complete.")

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic();

const stream = await client.messages.stream({
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  messages: [
    {
      role: "user",
      content: "What is the greatest common divisor of 1071 and 462?"
    }
  ]
});

let thinkingStarted = false;
let responseStarted = false;

for await (const event of stream) {
  if (event.type === "content_block_start") {
    console.log(`\nStarting ${event.content_block.type} block...`);
    // Reset flags for each new block
    thinkingStarted = false;
    responseStarted = false;
  } else if (event.type === "content_block_delta") {
    if (event.delta.type === "thinking_delta") {
      if (!thinkingStarted) {
        process.stdout.write("Thinking: ");
        thinkingStarted = true;
      }
      process.stdout.write(event.delta.thinking);
    } else if (event.delta.type === "text_delta") {
      if (!responseStarted) {
        process.stdout.write("Response: ");
        responseStarted = true;
      }
      process.stdout.write(event.delta.text);
    }
  } else if (event.type === "content_block_stop") {
    console.log("\nBlock complete.");
  }
}

using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

var parameters = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 16000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 10000),
    Messages = [new() { Role = Role.User, Content = "What is the greatest common divisor of 1071 and 462?" }]
};

bool thinkingStarted = false;
bool responseStarted = false;

await foreach (var streamEvent in client.Messages.CreateStreaming(parameters))
{
    if (streamEvent.TryPickContentBlockStart(out var blockStart))
    {
        Console.WriteLine({{CONTENT}}quot;\nStarting {blockStart.ContentBlock.Type} block...");
        thinkingStarted = false;
        responseStarted = false;
    }
    else if (streamEvent.TryPickContentBlockDelta(out var blockDelta))
    {
        if (blockDelta.Delta.TryPickThinking(out var thinkingDelta))
        {
            if (!thinkingStarted)
            {
                Console.Write("Thinking: ");
                thinkingStarted = true;
            }
            Console.Write(thinkingDelta.Thinking);
        }
        else if (blockDelta.Delta.TryPickText(out var textDelta))
        {
            if (!responseStarted)
            {
                Console.Write("Response: ");
                responseStarted = true;
            }
            Console.Write(textDelta.Text);
        }
    }
    else if (streamEvent.TryPickContentBlockStop(out _))
    {
        Console.WriteLine("\nBlock complete.");
    }
}

package main

import (
	"context"
	"fmt"
	"log"

	"github.com/anthropics/anthropic-sdk-go"
)

func main() {
	client := anthropic.NewClient()

	stream := client.Messages.NewStreaming(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 16000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(10000),
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("What is the greatest common divisor of 1071 and 462?")),
		},
	})

	thinkingStarted := false
	responseStarted := false

	for stream.Next() {
		event := stream.Current()
		switch eventVariant := event.AsAny().(type) {
		case anthropic.ContentBlockStartEvent:
			fmt.Printf("\nStarting %s block...\n", eventVariant.ContentBlock.Type)
			thinkingStarted = false
			responseStarted = false
		case anthropic.ContentBlockDeltaEvent:
			switch deltaVariant := eventVariant.Delta.AsAny().(type) {
			case anthropic.ThinkingDelta:
				if !thinkingStarted {
					fmt.Print("Thinking: ")
					thinkingStarted = true
				}
				fmt.Print(deltaVariant.Thinking)
			case anthropic.TextDelta:
				if !responseStarted {
					fmt.Print("Response: ")
					responseStarted = true
				}
				fmt.Print(deltaVariant.Text)
			}
		case anthropic.ContentBlockStopEvent:
			fmt.Println("\nBlock complete.")
		}
	}

	if err := stream.Err(); err != nil {
		log.Fatal(err)
	}
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Model;

void main() {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    MessageCreateParams params = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(16000L)
        .enabledThinking(10000L)
        .addUserMessage("What is the greatest common divisor of 1071 and 462?")
        .build();

    try (var streamResponse = client.messages().createStreaming(params)) {
        streamResponse.stream().forEach(event -> {
            event.contentBlockStart().ifPresent(startEvent ->
                IO.println("\nStarting block...")
            );
            event.contentBlockDelta().ifPresent(deltaEvent -> {
                deltaEvent.delta().thinking().ifPresent(td ->
                    IO.print(td.thinking())
                );
                deltaEvent.delta().text().ifPresent(td ->
                    IO.print(td.text())
                );
            });
            event.contentBlockStop().ifPresent(stopEvent ->
                IO.println("\nBlock complete.")
            );
        });
    }
}

<?php

use Anthropic\Client;

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

$thinkingStarted = false;
$responseStarted = false;

$stream = $client->messages->createStream(
    maxTokens: 16000,
    messages: [
        ['role' => 'user', 'content' => 'What is the greatest common divisor of 1071 and 462?']
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 10000],
);

foreach ($stream as $event) {
    if ($event->type === 'content_block_start') {
        echo "\nStarting {$event->contentBlock->type} block...\n";
        $thinkingStarted = false;
        $responseStarted = false;
    } elseif ($event->type === 'content_block_delta') {
        if ($event->delta->type === 'thinking_delta') {
            if (!$thinkingStarted) {
                echo "Thinking: ";
                $thinkingStarted = true;
            }
            echo $event->delta->thinking;
        } elseif ($event->delta->type === 'text_delta') {
            if (!$responseStarted) {
                echo "Response: ";
                $responseStarted = true;
            }
            echo $event->delta->text;
        }
    } elseif ($event->type === 'content_block_stop') {
        echo "\nBlock complete.\n";
    }
}

require "anthropic"

client = Anthropic::Client.new

thinking_started = false
response_started = false

stream = client.messages.stream(
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  messages: [
    { role: "user", content: "What is the greatest common divisor of 1071 and 462?" }
  ]
)

stream.each do |event|
  case event.type
  when :content_block_start
    puts "\nStarting #{event.content_block.type} block..."
    thinking_started = false
    response_started = false
  when :content_block_delta
    if event.delta.type == :thinking_delta
      unless thinking_started
        print "Thinking: "
        thinking_started = true
      end
      print event.delta.thinking
    elsif event.delta.type == :text_delta
      unless response_started
        print "Response: "
        response_started = true
      end
      print event.delta.text
    end
  when :content_block_stop
    puts "\nBlock complete."
  end
end

import anthropic

client = anthropic.Anthropic()

weather_tool = {
    "name": "get_weather",
    "description": "Get current weather for a location",
    "input_schema": {
        "type": "object",
        "properties": {"location": {"type": "string"}},
        "required": ["location"],
    },
}

# First request - Claude responds with thinking and tool request
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What's the weather in Paris?"}],
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic();

const weatherTool: Anthropic.Tool = {
  name: "get_weather",
  description: "Get current weather for a location",
  input_schema: {
    type: "object",
    properties: {
      location: { type: "string" }
    },
    required: ["location"]
  }
};

// First request - Claude responds with thinking and tool request
const response = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  tools: [weatherTool],
  messages: [{ role: "user", content: "What's the weather in Paris?" }]
});

using System.Text.Json;
using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

var weatherTool = new ToolUnion(new Tool()
{
    Name = "get_weather",
    Description = "Get current weather for a location",
    InputSchema = new InputSchema()
    {
        Properties = new Dictionary<string, JsonElement>
        {
            ["location"] = JsonSerializer.SerializeToElement(new { type = "string" }),
        },
        Required = ["location"],
    },
});

var parameters = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 16000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 10000),
    Tools = [weatherTool],
    Messages = [new() { Role = Role.User, Content = "What's the weather in Paris?" }]
};

var message = await client.Messages.Create(parameters);
Console.WriteLine(message);

package main

import (
	"context"
	"fmt"
	"log"

	"github.com/anthropics/anthropic-sdk-go"
)

func main() {
	client := anthropic.NewClient()

	weatherTool := anthropic.ToolUnionParam{
		OfTool: &anthropic.ToolParam{
			Name:        "get_weather",
			Description: anthropic.String("Get current weather for a location"),
			InputSchema: anthropic.ToolInputSchemaParam{
				Properties: map[string]any{
					"location": map[string]any{
						"type": "string",
					},
				},
				Required: []string{"location"},
			},
		},
	}

	response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 16000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(10000),
		Tools:     []anthropic.ToolUnionParam{weatherTool},
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("What's the weather in Paris?")),
		},
	})
	if err != nil {
		log.Fatal(err)
	}
	fmt.Println(response)
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.Model;
import com.anthropic.models.messages.Tool;
import com.anthropic.core.JsonValue;
import java.util.List;
import java.util.Map;

void main() {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    MessageCreateParams params = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(16000L)
        .enabledThinking(10000L)
        .addTool(Tool.builder()
            .name("get_weather")
            .description("Get current weather for a location")
            .inputSchema(Tool.InputSchema.builder()
                .properties(JsonValue.from(Map.of(
                    "location", Map.of("type", "string")
                )))
                .required(List.of("location"))
                .build())
            .build())
        .addUserMessage("What's the weather in Paris?")
        .build();

    Message response = client.messages().create(params);
    IO.println(response);
}

<?php

use Anthropic\Client;

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

$weatherTool = [
    'name' => 'get_weather',
    'description' => 'Get current weather for a location',
    'input_schema' => [
        'type' => 'object',
        'properties' => [
            'location' => ['type' => 'string']
        ],
        'required' => ['location']
    ]
];

$message = $client->messages->create(
    maxTokens: 16000,
    messages: [
        ['role' => 'user', 'content' => "What's the weather in Paris?"]
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 10000],
    tools: [$weatherTool],
);
echo $message;

require "anthropic"

client = Anthropic::Client.new

weather_tool = {
  name: "get_weather",
  description: "Get current weather for a location",
  input_schema: {
    type: "object",
    properties: {
      location: { type: "string" }
    },
    required: ["location"]
  }
}

message = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  tools: [weather_tool],
  messages: [
    { role: "user", content: "What's the weather in Paris?" }
  ]
)
puts message

import anthropic

client = anthropic.Anthropic()
weather_tool = {
    "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"}
        },
        "required": ["location"],
    },
}
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What's the weather in Paris?"}],
)
# Extract thinking block and tool use block
thinking_block = next(
    (block for block in response.content if block.type == "thinking"), None
)
tool_use_block = next(
    (block for block in response.content if block.type == "tool_use"), None
)

# Call your actual weather API, here is where your actual API call would go
# Let's pretend this is what we get back
weather_data = {"temperature": 88}

# Second request - Include thinking block and tool result
# No new thinking blocks are generated in the response
continuation = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    tools=[weather_tool],
    messages=[
        {"role": "user", "content": "What's the weather in Paris?"},
        # notice that the thinking_block is passed in as well as the tool_use_block
        # if this is not passed in, an error is raised
        {"role": "assistant", "content": [thinking_block, tool_use_block]},
        {
            "role": "user",
            "content": [
                {
                    "type": "tool_result",
                    "tool_use_id": tool_use_block.id,
                    "content": f"Current temperature: {weather_data['temperature']}°F",
                }
            ],
        },
    ],
)
print(continuation)

// Extract thinking block and tool use block
const thinkingBlock = response.content.find(
  (block): block is Anthropic.ThinkingBlock => block.type === "thinking"
);
const toolUseBlock = response.content.find(
  (block): block is Anthropic.ToolUseBlock => block.type === "tool_use"
);

// Call your actual weather API, here is where your actual API call would go
// Let's pretend this is what we get back
const weatherData = { temperature: 88 };

if (thinkingBlock && toolUseBlock) {
  // Second request - Include thinking block and tool result
  // No new thinking blocks are generated in the response
  const continuation = await client.messages.create({
    model: "claude-sonnet-4-6",
    max_tokens: 16000,
    thinking: {
      type: "enabled",
      budget_tokens: 10000
    },
    tools: [weatherTool],
    messages: [
      { role: "user", content: "What's the weather in Paris?" },
      // notice that the thinkingBlock is passed in as well as the toolUseBlock
      // if this is not passed in, an error is raised
      { role: "assistant", content: [thinkingBlock, toolUseBlock] },
      {
        role: "user",
        content: [
          {
            type: "tool_result" as const,
            tool_use_id: toolUseBlock.id,
            content: `Current temperature: ${weatherData.temperature}°F`
          }
        ]
      }
    ]
  });
  console.log(continuation);
}

using System.Text.Json;
using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

var weatherTool = new ToolUnion(new Tool()
{
    Name = "get_weather",
    Description = "Get current weather for a location",
    InputSchema = new InputSchema()
    {
        Properties = new Dictionary<string, JsonElement>
        {
            ["location"] = JsonSerializer.SerializeToElement(new { type = "string", description = "City name" }),
        },
        Required = ["location"],
    },
});

var parameters = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 16000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 10000),
    Tools = [weatherTool],
    Messages = [
        new() { Role = Role.User, Content = "What is the weather in Paris?" }
    ]
};

var response = await client.Messages.Create(parameters);

// Extract the tool_use block to get its ID for the tool result
ToolUseBlock? toolUseBlock = null;
foreach (var block in response.Content)
{
    if (block.TryPickToolUse(out var toolUse))
    {
        toolUseBlock = toolUse;
    }
}

var weatherData = new { temperature = 88 };

// Build continuation with tool result
var continuationParams = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 16000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 10000),
    Tools = [weatherTool],
    Messages = [
        new() { Role = Role.User, Content = "What is the weather in Paris?" },
        // response.Content includes the thinking blocks; passing them back is required
        new() { Role = Role.Assistant, Content = response.Content.Select(block => new ContentBlockParam(block.Json)).ToList() },
        new() { Role = Role.User, Content = new MessageParamContent(new List<ContentBlockParam>
        {
            new ContentBlockParam(new ToolResultBlockParam()
            {
                ToolUseID = toolUseBlock?.ID ?? "",
                Content = {{CONTENT}}quot;Current temperature: {weatherData.temperature}°F"
            })
        })}
    ]
};

var continuation = await client.Messages.Create(continuationParams);
Console.WriteLine(continuation);

package main

import (
	"context"
	"fmt"
	"log"

	"github.com/anthropics/anthropic-sdk-go"
)

func main() {
	client := anthropic.NewClient()

	weatherTool := anthropic.ToolUnionParam{
		OfTool: &anthropic.ToolParam{
			Name:        "get_weather",
			Description: anthropic.String("Get current weather for a location"),
			InputSchema: anthropic.ToolInputSchemaParam{
				Properties: map[string]any{
					"location": map[string]any{
						"type":        "string",
						"description": "City name",
					},
				},
				Required: []string{"location"},
			},
		},
	}

	response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 16000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(10000),
		Tools:     []anthropic.ToolUnionParam{weatherTool},
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("What is the weather in Paris?")),
		},
	})
	if err != nil {
		log.Fatal(err)
	}

	var toolUseBlock anthropic.ToolUseBlock
	for _, block := range response.Content {
		switch v := block.AsAny().(type) {
		case anthropic.ToolUseBlock:
			toolUseBlock = v
		}
	}

	weatherData := map[string]int{"temperature": 88}

	continuation, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 16000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(10000),
		Tools:     []anthropic.ToolUnionParam{weatherTool},
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("What is the weather in Paris?")),
			response.ToParam(),
			anthropic.NewUserMessage(
				anthropic.NewToolResultBlock(toolUseBlock.ID, fmt.Sprintf("Current temperature: %d°F", weatherData["temperature"]), false),
			),
		},
	})
	if err != nil {
		log.Fatal(err)
	}

	fmt.Println(continuation)
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.ContentBlockParam;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.Model;
import com.anthropic.models.messages.Tool;
import com.anthropic.models.messages.ToolResultBlockParam;
import com.anthropic.models.messages.ToolUseBlock;
import com.anthropic.models.messages.ToolUseBlockParam;
import com.anthropic.models.messages.ThinkingBlock;
import com.anthropic.models.messages.ThinkingBlockParam;
import com.anthropic.core.JsonValue;
import java.util.List;
import java.util.Map;

void main() {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    Tool weatherTool = Tool.builder()
        .name("get_weather")
        .description("Get current weather for a location")
        .inputSchema(Tool.InputSchema.builder()
            .properties(JsonValue.from(Map.of(
                "location", Map.of("type", "string", "description", "City name")
            )))
            .required(List.of("location"))
            .build())
        .build();

    MessageCreateParams initialParams = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(16000L)
        .enabledThinking(10000L)
        .addTool(weatherTool)
        .addUserMessage("What is the weather in Paris?")
        .build();

    Message response = client.messages().create(initialParams);

    ThinkingBlock thinkingBlock = null;
    ToolUseBlock toolUseBlock = null;
    for (var block : response.content()) {
        if (block.thinking().isPresent()) {
            thinkingBlock = block.thinking().get();
        }
        if (block.toolUse().isPresent()) {
            toolUseBlock = block.toolUse().get();
        }
    }

    int temperature = 88;

    // Second request: pass back thinking block and tool result
    MessageCreateParams continuationParams = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(16000L)
        .enabledThinking(10000L)
        .addTool(weatherTool)
        .addUserMessage("What is the weather in Paris?")
        .addAssistantMessageOfBlockParams(List.of(
            ContentBlockParam.ofThinking(ThinkingBlockParam.builder()
                .thinking(thinkingBlock.thinking())
                .signature(thinkingBlock.signature())
                .build()),
            ContentBlockParam.ofToolUse(ToolUseBlockParam.builder()
                .id(toolUseBlock.id())
                .name(toolUseBlock.name())
                .input(toolUseBlock._input())
                .build())
        ))
        .addUserMessageOfBlockParams(List.of(
            ContentBlockParam.ofToolResult(
                ToolResultBlockParam.builder()
                    .toolUseId(toolUseBlock.id())
                    .content("Current temperature: " + temperature + "°F")
                    .build()
            )
        ))
        .build();

    Message continuation = client.messages().create(continuationParams);
    IO.println(continuation);
}

<?php

use Anthropic\Client;

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

$weatherTool = [
    'name' => 'get_weather',
    'description' => 'Get current weather for a location',
    'input_schema' => [
        'type' => 'object',
        'properties' => [
            'location' => [
                'type' => 'string',
                'description' => 'City name'
            ]
        ],
        'required' => ['location']
    ]
];

$response = $client->messages->create(
    maxTokens: 16000,
    messages: [
        ['role' => 'user', 'content' => 'What is the weather in Paris?']
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 10000],
    tools: [$weatherTool],
);

$thinkingBlock = null;
$toolUseBlock = null;
foreach ($response->content as $block) {
    if ($block->type === 'thinking') {
        $thinkingBlock = $block;
    }
    if ($block->type === 'tool_use') {
        $toolUseBlock = $block;
    }
}

$weatherData = ['temperature' => 88];

$continuation = $client->messages->create(
    maxTokens: 16000,
    messages: [
        ['role' => 'user', 'content' => 'What is the weather in Paris?'],
        ['role' => 'assistant', 'content' => [$thinkingBlock, $toolUseBlock]],
        ['role' => 'user', 'content' => [
            [
                'type' => 'tool_result',
                'tool_use_id' => $toolUseBlock->id,
                'content' => "Current temperature: {$weatherData['temperature']}°F"
            ]
        ]]
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 10000],
    tools: [$weatherTool],
);

echo $continuation;

require "anthropic"

client = Anthropic::Client.new

weather_tool = {
  name: "get_weather",
  description: "Get current weather for a location",
  input_schema: {
    type: "object",
    properties: {
      location: { type: "string", description: "City name" }
    },
    required: ["location"]
  }
}

response = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  tools: [weather_tool],
  messages: [
    { role: "user", content: "What is the weather in Paris?" }
  ]
)

thinking_block = response.content.find { |block| block.type == :thinking }
tool_use_block = response.content.find { |block| block.type == :tool_use }

raise "No tool_use block found" unless tool_use_block

weather_data = { temperature: 88 }

continuation = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000
  },
  tools: [weather_tool],
  messages: [
    { role: "user", content: "What is the weather in Paris?" },
    { role: "assistant", content: [thinking_block, tool_use_block] },
    { role: "user", content: [
      {
        type: "tool_result",
        tool_use_id: tool_use_block.id,
        content: "Current temperature: #{weather_data[:temperature]}°F"
      }
    ] }
  ]
)

puts continuation

from anthropic import Anthropic
import requests
from bs4 import BeautifulSoup

client = Anthropic()


def fetch_article_content(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.content, "html.parser")

    # Remove script and style elements
    for script in soup(["script", "style"]):
        script.decompose()

    # Get text
    text = soup.get_text()

    # Break into lines and remove leading and trailing space on each
    lines = (line.strip() for line in text.splitlines())
    # Break multi-headlines into a line each
    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
    # Drop blank lines
    text = "\n".join(chunk for chunk in chunks if chunk)

    return text


# Fetch the content of the article
book_url = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt"
book_content = fetch_article_content(book_url)
# Use just enough text for caching (first few chapters)
LARGE_TEXT = book_content[:10000]

SYSTEM_PROMPT = [
    {
        "type": "text",
        "text": "You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully.",
    },
    {"type": "text", "text": LARGE_TEXT, "cache_control": {"type": "ephemeral"}},
]

MESSAGES = [{"role": "user", "content": "Analyze the tone of this passage."}]

# First request - establish cache
print("First request - establishing cache")
response1 = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=20000,
    thinking={"type": "enabled", "budget_tokens": 4000},
    system=SYSTEM_PROMPT,
    messages=MESSAGES,
)

print(f"First response usage: {response1.usage}")

MESSAGES.append({"role": "assistant", "content": response1.content})
MESSAGES.append({"role": "user", "content": "Analyze the characters in this passage."})
# Second request - same thinking parameters (cache hit expected)
print("\nSecond request - same thinking parameters (cache hit expected)")
response2 = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=20000,
    thinking={"type": "enabled", "budget_tokens": 4000},
    system=SYSTEM_PROMPT,
    messages=MESSAGES,
)

print(f"Second response usage: {response2.usage}")

# Third request - different thinking parameters (cache miss for messages)
print("\nThird request - different thinking parameters (cache miss for messages)")
response3 = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=20000,
    thinking={
        "type": "enabled",
        "budget_tokens": 8000,  # Changed thinking budget
    },
    system=SYSTEM_PROMPT,  # System prompt remains cached
    messages=MESSAGES,  # Messages cache is invalidated
)

print(f"Third response usage: {response3.usage}")

import Anthropic from "@anthropic-ai/sdk";
import axios from "axios";
import * as cheerio from "cheerio";

const client = new Anthropic();

async function fetchArticleContent(url: string): Promise<string> {
  const response = await axios.get(url);
  const $ = cheerio.load(response.data);
  $("script, style").remove();
  let text = $.text();
  const lines = text.split("\n").map((line) => line.trim());
  text = lines.filter((line) => line.length > 0).join("\n");
  return text;
}

const bookUrl = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt";
const bookContent = await fetchArticleContent(bookUrl);
const LARGE_TEXT = bookContent.slice(0, 10000);

const SYSTEM_PROMPT: Anthropic.TextBlockParam[] = [
  {
    type: "text",
    text: "You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully."
  },
  {
    type: "text",
    text: LARGE_TEXT,
    cache_control: { type: "ephemeral" }
  }
];

const messages: Anthropic.MessageParam[] = [
  { role: "user", content: "Analyze the tone of this passage." }
];

// First request - establish cache
console.log("First request - establishing cache");
const response1 = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: { type: "enabled", budget_tokens: 4000 },
  system: SYSTEM_PROMPT,
  messages
});

console.log(`First response usage: ${JSON.stringify(response1.usage)}`);

messages.push({
  role: "assistant",
  content: response1.content
});
messages.push({
  role: "user",
  content: "Analyze the characters in this passage."
});

// Second request - same thinking parameters (cache hit expected)
console.log("\nSecond request - same thinking parameters (cache hit expected)");
const response2 = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: { type: "enabled", budget_tokens: 4000 },
  system: SYSTEM_PROMPT,
  messages
});

console.log(`Second response usage: ${JSON.stringify(response2.usage)}`);

// Third request - different thinking parameters (cache miss for messages)
console.log("\nThird request - different thinking parameters (cache miss for messages)");
const response3 = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: { type: "enabled", budget_tokens: 8000 },
  system: SYSTEM_PROMPT,
  messages
});

console.log(`Third response usage: ${JSON.stringify(response3.usage)}`);

using System.Net.Http;
using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

// Fetch book content
using var httpClient = new HttpClient();
var bookContent = await httpClient.GetStringAsync("https://www.gutenberg.org/cache/epub/1342/pg1342.txt");
var largeText = bookContent.Substring(0, Math.Min(10000, bookContent.Length));

var systemPrompt = new MessageCreateParamsSystem(new List<TextBlockParam>
{
    new TextBlockParam()
    {
        Text = "You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully."
    },
    new TextBlockParam()
    {
        Text = largeText,
        CacheControl = new CacheControlEphemeral(),
    },
});

var messages = new List<MessageParam>
{
    new() { Role = Role.User, Content = "Analyze the tone of this passage." }
};

// First request - establish cache
Console.WriteLine("First request - establishing cache");
var parameters1 = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 20000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 4000),
    System = systemPrompt,
    Messages = messages
};

var response1 = await client.Messages.Create(parameters1);
Console.WriteLine({{CONTENT}}quot;First response usage: {response1.Usage}");

messages.Add(new() { Role = Role.Assistant, Content = response1.Content.Select(block => new ContentBlockParam(block.Json)).ToList() });
messages.Add(new() { Role = Role.User, Content = "Analyze the characters in this passage." });

// Second request - same thinking parameters (cache hit expected)
Console.WriteLine("\nSecond request - same thinking parameters (cache hit expected)");
var parameters2 = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 20000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 4000),
    System = systemPrompt,
    Messages = messages
};

var response2 = await client.Messages.Create(parameters2);
Console.WriteLine({{CONTENT}}quot;Second response usage: {response2.Usage}");

// Third request - different thinking parameters (cache miss for messages)
Console.WriteLine("\nThird request - different thinking parameters (cache miss for messages)");
var parameters3 = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 20000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 8000),
    System = systemPrompt,
    Messages = messages
};

var response3 = await client.Messages.Create(parameters3);
Console.WriteLine({{CONTENT}}quot;Third response usage: {response3.Usage}");

package main

import (
	"context"
	"fmt"
	"io"
	"log"
	"net/http"

	"github.com/anthropics/anthropic-sdk-go"
)

func main() {
	client := anthropic.NewClient()

	// Fetch book content
	resp, err := http.Get("https://www.gutenberg.org/cache/epub/1342/pg1342.txt")
	if err != nil {
		log.Fatal(err)
	}
	defer resp.Body.Close()

	body, err := io.ReadAll(resp.Body)
	if err != nil {
		log.Fatal(err)
	}

	largeText := string(body)
	if len(largeText) > 10000 {
		largeText = largeText[:10000]
	}

	systemPrompt := []anthropic.TextBlockParam{
		{Text: "You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully."},
		{
			Text:         largeText,
			CacheControl: anthropic.NewCacheControlEphemeralParam(),
		},
	}

	messages := []anthropic.MessageParam{
		anthropic.NewUserMessage(anthropic.NewTextBlock("Analyze the tone of this passage.")),
	}

	// First request - establish cache
	fmt.Println("First request - establishing cache")
	response1, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 20000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(4000),
		System:    systemPrompt,
		Messages:  messages,
	})
	if err != nil {
		log.Fatal(err)
	}

	fmt.Printf("First response usage: %s\n", response1.Usage.RawJSON())

	messages = append(messages, response1.ToParam())
	messages = append(messages, anthropic.NewUserMessage(anthropic.NewTextBlock("Analyze the characters in this passage.")))

	// Second request - same thinking parameters (cache hit expected)
	fmt.Println("\nSecond request - same thinking parameters (cache hit expected)")
	response2, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 20000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(4000),
		System:    systemPrompt,
		Messages:  messages,
	})
	if err != nil {
		log.Fatal(err)
	}

	fmt.Printf("Second response usage: %s\n", response2.Usage.RawJSON())

	// Third request - different thinking parameters (cache miss for messages)
	fmt.Println("\nThird request - different thinking parameters (cache miss for messages)")
	response3, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 20000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(8000),
		System:    systemPrompt,
		Messages:  messages,
	})
	if err != nil {
		log.Fatal(err)
	}

	fmt.Printf("Third response usage: %s\n", response3.Usage.RawJSON())
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.CacheControlEphemeral;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.Model;
import com.anthropic.models.messages.TextBlockParam;
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.util.List;

void main() throws Exception {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    // Fetch book content
    HttpClient httpClient = HttpClient.newHttpClient();
    HttpRequest request = HttpRequest.newBuilder()
        .uri(URI.create("https://www.gutenberg.org/cache/epub/1342/pg1342.txt"))
        .build();
    HttpResponse<String> response = httpClient.send(request, HttpResponse.BodyHandlers.ofString());
    String bookContent = response.body();
    String largeText = bookContent.substring(0, Math.min(10000, bookContent.length()));

    List<TextBlockParam> systemPrompt = List.of(
        TextBlockParam.builder()
            .text("You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully.")
            .build(),
        TextBlockParam.builder()
            .text(largeText)
            .cacheControl(CacheControlEphemeral.builder().build())
            .build()
    );

    // First request - establish cache
    IO.println("First request - establishing cache");
    MessageCreateParams params1 = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(20000L)
        .enabledThinking(4000L)
        .systemOfTextBlockParams(systemPrompt)
        .addUserMessage("Analyze the tone of this passage.")
        .build();

    Message response1 = client.messages().create(params1);
    IO.println("First response usage: " + response1.usage());

    // Second request - same thinking parameters (cache hit expected)
    IO.println("\nSecond request - same thinking parameters (cache hit expected)");
    MessageCreateParams params2 = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(20000L)
        .enabledThinking(4000L)
        .systemOfTextBlockParams(systemPrompt)
        .addUserMessage("Analyze the tone of this passage.")
        .addAssistantMessageOfBlockParams(response1.content().stream()
            .map(block -> block.toParam())
            .collect(java.util.stream.Collectors.toList()))
        .addUserMessage("Analyze the characters in this passage.")
        .build();

    Message response2 = client.messages().create(params2);
    IO.println("Second response usage: " + response2.usage());

    // Third request - different thinking parameters (cache miss for messages)
    IO.println("\nThird request - different thinking parameters (cache miss for messages)");
    MessageCreateParams params3 = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(20000L)
        .enabledThinking(8000L)
        .systemOfTextBlockParams(systemPrompt)
        .addUserMessage("Analyze the tone of this passage.")
        .addAssistantMessageOfBlockParams(response1.content().stream()
            .map(block -> block.toParam())
            .collect(java.util.stream.Collectors.toList()))
        .addUserMessage("Analyze the characters in this passage.")
        .build();

    Message response3 = client.messages().create(params3);
    IO.println("Third response usage: " + response3.usage());
}

<?php


use Anthropic\Client;

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

// Fetch book content
$bookContent = file_get_contents("https://www.gutenberg.org/cache/epub/1342/pg1342.txt");
$largeText = substr($bookContent, 0, 10000);

$systemPrompt = [
    [
        'type' => 'text',
        'text' => 'You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully.'
    ],
    [
        'type' => 'text',
        'text' => $largeText,
        'cache_control' => ['type' => 'ephemeral']
    ]
];

$messages = [
    ['role' => 'user', 'content' => 'Analyze the tone of this passage.']
];

// First request - establish cache
echo "First request - establishing cache\n";
$response1 = $client->messages->create(
    maxTokens: 20000,
    messages: $messages,
    model: 'claude-sonnet-4-6',
    system: $systemPrompt,
    thinking: ['type' => 'enabled', 'budget_tokens' => 4000],
);

echo "First response usage: " . json_encode($response1->usage) . "\n";

$messages[] = ['role' => 'assistant', 'content' => $response1->content];
$messages[] = ['role' => 'user', 'content' => 'Analyze the characters in this passage.'];

// Second request - same thinking parameters (cache hit expected)
echo "\nSecond request - same thinking parameters (cache hit expected)\n";
$response2 = $client->messages->create(
    maxTokens: 20000,
    messages: $messages,
    model: 'claude-sonnet-4-6',
    system: $systemPrompt,
    thinking: ['type' => 'enabled', 'budget_tokens' => 4000],
);

echo "Second response usage: " . json_encode($response2->usage) . "\n";

// Third request - different thinking parameters (cache miss for messages)
echo "\nThird request - different thinking parameters (cache miss for messages)\n";
$response3 = $client->messages->create(
    maxTokens: 20000,
    messages: $messages,
    model: 'claude-sonnet-4-6',
    system: $systemPrompt,
    thinking: ['type' => 'enabled', 'budget_tokens' => 8000],
);

echo "Third response usage: " . json_encode($response3->usage) . "\n";

require "anthropic"
require "net/http"
require "uri"

client = Anthropic::Client.new

# Fetch book content
uri = URI("https://www.gutenberg.org/cache/epub/1342/pg1342.txt")
response = Net::HTTP.get_response(uri)
book_content = response.body
large_text = book_content[0...10000]

system_prompt = [
  {
    type: "text",
    text: "You are an AI assistant that is tasked with literary analysis. Analyze the following text carefully."
  },
  {
    type: "text",
    text: large_text,
    cache_control: { type: "ephemeral" }
  }
]

messages = [
  { role: "user", content: "Analyze the tone of this passage." }
]

# First request - establish cache
puts "First request - establishing cache"
response1 = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: {
    type: "enabled",
    budget_tokens: 4000
  },
  system: system_prompt,
  messages: messages
)

puts "First response usage: #{response1.usage}"

messages << { role: "assistant", content: response1.content }
messages << { role: "user", content: "Analyze the characters in this passage." }

# Second request - same thinking parameters (cache hit expected)
puts "\nSecond request - same thinking parameters (cache hit expected)"
response2 = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: {
    type: "enabled",
    budget_tokens: 4000
  },
  system: system_prompt,
  messages: messages
)

puts "Second response usage: #{response2.usage}"

# Third request - different thinking parameters (cache miss for messages)
puts "\nThird request - different thinking parameters (cache miss for messages)"
response3 = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: {
    type: "enabled",
    budget_tokens: 8000
  },
  system: system_prompt,
  messages: messages
)

puts "Third response usage: #{response3.usage}"

from anthropic import Anthropic
import requests
from bs4 import BeautifulSoup

client = Anthropic()


def fetch_article_content(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.content, "html.parser")

    # Remove script and style elements
    for script in soup(["script", "style"]):
        script.decompose()

    # Get text
    text = soup.get_text()

    # Break into lines and remove leading and trailing space on each
    lines = (line.strip() for line in text.splitlines())
    # Break multi-headlines into a line each
    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
    # Drop blank lines
    text = "\n".join(chunk for chunk in chunks if chunk)

    return text


# Fetch the content of the article
book_url = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt"
book_content = fetch_article_content(book_url)
# Use just enough text for caching (first few chapters)
LARGE_TEXT = book_content[:10000]

# No system prompt - caching in messages instead
MESSAGES = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": LARGE_TEXT,
                "cache_control": {"type": "ephemeral"},
            },
            {"type": "text", "text": "Analyze the tone of this passage."},
        ],
    }
]

# First request - establish cache
print("First request - establishing cache")
response1 = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=20000,
    thinking={"type": "enabled", "budget_tokens": 4000},
    messages=MESSAGES,
)

print(f"First response usage: {response1.usage}")

MESSAGES.append({"role": "assistant", "content": response1.content})
MESSAGES.append({"role": "user", "content": "Analyze the characters in this passage."})
# Second request - same thinking parameters (cache hit expected)
print("\nSecond request - same thinking parameters (cache hit expected)")
response2 = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=20000,
    thinking={
        "type": "enabled",
        "budget_tokens": 4000,  # Same thinking budget
    },
    messages=MESSAGES,
)

print(f"Second response usage: {response2.usage}")

MESSAGES.append({"role": "assistant", "content": response2.content})
MESSAGES.append({"role": "user", "content": "Analyze the setting in this passage."})

# Third request - different thinking budget (cache miss expected)
print("\nThird request - different thinking budget (cache miss expected)")
response3 = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=20000,
    thinking={
        "type": "enabled",
        "budget_tokens": 8000,  # Different thinking budget breaks cache
    },
    messages=MESSAGES,
)

print(f"Third response usage: {response3.usage}")

import Anthropic from "@anthropic-ai/sdk";
import axios from "axios";
import * as cheerio from "cheerio";

const client = new Anthropic();

async function fetchArticleContent(url: string): Promise<string> {
  const response = await axios.get(url);
  const $ = cheerio.load(response.data);

  // Remove script and style elements
  $("script, style").remove();

  // Get text
  let text = $.text();

  // Clean up text (break into lines, remove whitespace)
  const lines = text.split("\n").map((line) => line.trim());
  const chunks = lines.flatMap((line) => line.split("  ").map((phrase) => phrase.trim()));
  text = chunks.filter((chunk) => chunk).join("\n");

  return text;
}

const bookUrl = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt";
const bookContent = await fetchArticleContent(bookUrl);
const LARGE_TEXT = bookContent.substring(0, 10000);

// No system prompt - caching in messages instead
const messages: Anthropic.MessageParam[] = [
  {
    role: "user",
    content: [
      {
        type: "text",
        text: LARGE_TEXT,
        cache_control: { type: "ephemeral" }
      },
      {
        type: "text",
        text: "Analyze the tone of this passage."
      }
    ]
  }
];

// First request - establish cache
console.log("First request - establishing cache");
const response1 = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: { type: "enabled", budget_tokens: 4000 },
  messages
});

console.log("First response usage: ", response1.usage);

messages.push(
  { role: "assistant", content: response1.content },
  { role: "user", content: "Analyze the characters in this passage." }
);

// Second request - same thinking parameters (cache hit expected)
console.log("\nSecond request - same thinking parameters (cache hit expected)");
const response2 = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: { type: "enabled", budget_tokens: 4000 },
  messages
});

console.log("Second response usage: ", response2.usage);

messages.push(
  { role: "assistant", content: response2.content },
  { role: "user", content: "Analyze the setting in this passage." }
);

// Third request - different thinking budget (cache miss expected)
console.log("\nThird request - different thinking budget (cache miss expected)");
const response3 = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: { type: "enabled", budget_tokens: 8000 },
  messages
});

console.log("Third response usage: ", response3.usage);

using System.Net.Http;
using Anthropic;
using Anthropic.Models.Messages;

AnthropicClient client = new();

string bookUrl = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt";
string bookContent = await FetchArticleContent(bookUrl);
string largeText = bookContent.Substring(0, Math.Min(10000, bookContent.Length));

Console.WriteLine("First request - establishing cache");
var parameters1 = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 20000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 4000),
    Messages =
    [
        new()
        {
            Role = Role.User,
            Content = new MessageParamContent(new List<ContentBlockParam>
            {
                new ContentBlockParam(new TextBlockParam()
                {
                    Text = largeText,
                    CacheControl = new CacheControlEphemeral(),
                }),
                new ContentBlockParam(new TextBlockParam()
                {
                    Text = "Analyze the tone of this passage."
                }),
            })
        }
    ]
};

var response1 = await client.Messages.Create(parameters1);
Console.WriteLine({{CONTENT}}quot;First response usage: {response1.Usage}");

Console.WriteLine("\nSecond request - same thinking parameters (cache hit expected)");
var parameters2 = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 20000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 4000),
    Messages =
    [
        new()
        {
            Role = Role.User,
            Content = new MessageParamContent(new List<ContentBlockParam>
            {
                new ContentBlockParam(new TextBlockParam()
                {
                    Text = largeText,
                    CacheControl = new CacheControlEphemeral(),
                }),
                new ContentBlockParam(new TextBlockParam()
                {
                    Text = "Analyze the tone of this passage."
                }),
            })
        },
        new()
        {
            Role = Role.Assistant,
            Content = response1.Content.Select(block => new ContentBlockParam(block.Json)).ToList()
        },
        new()
        {
            Role = Role.User,
            Content = "Analyze the characters in this passage."
        }
    ]
};

var response2 = await client.Messages.Create(parameters2);
Console.WriteLine({{CONTENT}}quot;Second response usage: {response2.Usage}");

Console.WriteLine("\nThird request - different thinking budget (cache miss expected)");
var parameters3 = new MessageCreateParams
{
    Model = Model.ClaudeSonnet4_6,
    MaxTokens = 20000,
    Thinking = new ThinkingConfigEnabled(budgetTokens: 8000),
    Messages =
    [
        new()
        {
            Role = Role.User,
            Content = new MessageParamContent(new List<ContentBlockParam>
            {
                new ContentBlockParam(new TextBlockParam()
                {
                    Text = largeText,
                    CacheControl = new CacheControlEphemeral(),
                }),
                new ContentBlockParam(new TextBlockParam()
                {
                    Text = "Analyze the tone of this passage."
                }),
            })
        },
        new()
        {
            Role = Role.Assistant,
            Content = response1.Content.Select(block => new ContentBlockParam(block.Json)).ToList()
        },
        new()
        {
            Role = Role.User,
            Content = "Analyze the characters in this passage."
        },
        new()
        {
            Role = Role.Assistant,
            Content = response2.Content.Select(block => new ContentBlockParam(block.Json)).ToList()
        },
        new()
        {
            Role = Role.User,
            Content = "Analyze the setting in this passage."
        }
    ]
};

var response3 = await client.Messages.Create(parameters3);
Console.WriteLine({{CONTENT}}quot;Third response usage: {response3.Usage}");

static async Task<string> FetchArticleContent(string url)
{
    using HttpClient httpClient = new();
    string content = await httpClient.GetStringAsync(url);
    return content;
}

package main

import (
	"context"
	"fmt"
	"io"
	"log"
	"net/http"
	"strings"

	"github.com/anthropics/anthropic-sdk-go"
)

func fetchArticleContent(url string) (string, error) {
	resp, err := http.Get(url)
	if err != nil {
		return "", err
	}
	defer resp.Body.Close()

	body, err := io.ReadAll(resp.Body)
	if err != nil {
		return "", err
	}

	text := string(body)
	lines := strings.Split(text, "\n")
	var cleanedLines []string
	for _, line := range lines {
		trimmed := strings.TrimSpace(line)
		if trimmed != "" {
			cleanedLines = append(cleanedLines, trimmed)
		}
	}

	return strings.Join(cleanedLines, "\n"), nil
}

func main() {
	client := anthropic.NewClient()

	bookURL := "https://www.gutenberg.org/cache/epub/1342/pg1342.txt"
	bookContent, err := fetchArticleContent(bookURL)
	if err != nil {
		log.Fatal(err)
	}

	largeText := bookContent
	if len(largeText) > 10000 {
		largeText = largeText[:10000]
	}

	// No system prompt - caching in messages instead
	messages := []anthropic.MessageParam{
		anthropic.NewUserMessage(
			anthropic.ContentBlockParamUnion{OfText: &anthropic.TextBlockParam{
				Text:         largeText,
				CacheControl: anthropic.NewCacheControlEphemeralParam(),
			}},
			anthropic.NewTextBlock("Analyze the tone of this passage."),
		),
	}

	// First request - establish cache
	fmt.Println("First request - establishing cache")
	response1, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 20000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(4000),
		Messages:  messages,
	})
	if err != nil {
		log.Fatal(err)
	}
	fmt.Printf("First response usage: %s\n", response1.Usage.RawJSON())

	messages = append(messages, response1.ToParam())
	messages = append(messages, anthropic.NewUserMessage(anthropic.NewTextBlock("Analyze the characters in this passage.")))

	// Second request - same thinking parameters (cache hit expected)
	fmt.Println("\nSecond request - same thinking parameters (cache hit expected)")
	response2, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 20000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(4000),
		Messages:  messages,
	})
	if err != nil {
		log.Fatal(err)
	}
	fmt.Printf("Second response usage: %s\n", response2.Usage.RawJSON())

	messages = append(messages, response2.ToParam())
	messages = append(messages, anthropic.NewUserMessage(anthropic.NewTextBlock("Analyze the setting in this passage.")))

	// Third request - different thinking budget (cache miss expected)
	fmt.Println("\nThird request - different thinking budget (cache miss expected)")
	response3, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
		Model:     anthropic.ModelClaudeSonnet4_6,
		MaxTokens: 20000,
		Thinking:  anthropic.ThinkingConfigParamOfEnabled(8000),
		Messages:  messages,
	})
	if err != nil {
		log.Fatal(err)
	}
	fmt.Printf("Third response usage: %s\n", response3.Usage.RawJSON())
}

import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.CacheControlEphemeral;
import com.anthropic.models.messages.ContentBlockParam;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.Model;
import com.anthropic.models.messages.TextBlockParam;
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.util.List;

void main() throws Exception {
    AnthropicClient client = AnthropicOkHttpClient.fromEnv();

    String bookUrl = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt";
    String bookContent = fetchArticleContent(bookUrl);
    String largeText = bookContent.substring(0, Math.min(10000, bookContent.length()));

    // First request - establishing cache
    IO.println("First request - establishing cache");
    MessageCreateParams params1 = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(20000L)
        .enabledThinking(4000L)
        .addUserMessageOfBlockParams(List.of(
            ContentBlockParam.ofText(TextBlockParam.builder()
                .text(largeText)
                .cacheControl(CacheControlEphemeral.builder().build())
                .build()),
            ContentBlockParam.ofText(TextBlockParam.builder()
                .text("Analyze the tone of this passage.")
                .build())
        ))
        .build();

    Message response1 = client.messages().create(params1);
    IO.println("First response usage: " + response1.usage());

    // Second request - same thinking parameters (cache hit expected)
    IO.println("\nSecond request - same thinking parameters (cache hit expected)");
    MessageCreateParams params2 = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(20000L)
        .enabledThinking(4000L)
        .addUserMessageOfBlockParams(List.of(
            ContentBlockParam.ofText(TextBlockParam.builder()
                .text(largeText)
                .cacheControl(CacheControlEphemeral.builder().build())
                .build()),
            ContentBlockParam.ofText(TextBlockParam.builder()
                .text("Analyze the tone of this passage.")
                .build())
        ))
        .addAssistantMessageOfBlockParams(response1.content().stream()
            .map(block -> block.toParam())
            .collect(java.util.stream.Collectors.toList()))
        .addUserMessage("Analyze the characters in this passage.")
        .build();

    Message response2 = client.messages().create(params2);
    IO.println("Second response usage: " + response2.usage());

    // Third request - different thinking budget (cache miss expected)
    IO.println("\nThird request - different thinking budget (cache miss expected)");
    MessageCreateParams params3 = MessageCreateParams.builder()
        .model(Model.CLAUDE_SONNET_4_6)
        .maxTokens(20000L)
        .enabledThinking(8000L)
        .addUserMessageOfBlockParams(List.of(
            ContentBlockParam.ofText(TextBlockParam.builder()
                .text(largeText)
                .cacheControl(CacheControlEphemeral.builder().build())
                .build()),
            ContentBlockParam.ofText(TextBlockParam.builder()
                .text("Analyze the tone of this passage.")
                .build())
        ))
        .addAssistantMessageOfBlockParams(response1.content().stream()
            .map(block -> block.toParam())
            .collect(java.util.stream.Collectors.toList()))
        .addUserMessage("Analyze the characters in this passage.")
        .addAssistantMessageOfBlockParams(response2.content().stream()
            .map(block -> block.toParam())
            .collect(java.util.stream.Collectors.toList()))
        .addUserMessage("Analyze the setting in this passage.")
        .build();

    Message response3 = client.messages().create(params3);
    IO.println("Third response usage: " + response3.usage());
}

String fetchArticleContent(String url) throws Exception {
    HttpClient client = HttpClient.newHttpClient();
    HttpRequest request = HttpRequest.newBuilder()
        .uri(URI.create(url))
        .build();
    HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
    return response.body();
}

<?php


use Anthropic\Client;


function fetchArticleContent($url) {
    $content = file_get_contents($url);
    $lines = explode("\n", $content);
    $cleanedLines = array_filter(array_map('trim', $lines));
    return implode("\n", $cleanedLines);
}

$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));

$bookUrl = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt";
$bookContent = fetchArticleContent($bookUrl);
$largeText = substr($bookContent, 0, 10000);

echo "First request - establishing cache\n";
$response1 = $client->messages->create(
    maxTokens: 20000,
    messages: [[
        'role' => 'user',
        'content' => [
            [
                'type' => 'text',
                'text' => $largeText,
                'cache_control' => ['type' => 'ephemeral']
            ],
            [
                'type' => 'text',
                'text' => 'Analyze the tone of this passage.'
            ]
        ]
    ]],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 4000],
);

echo "First response usage: " . json_encode($response1->usage) . "\n";

echo "\nSecond request - same thinking parameters (cache hit expected)\n";
$response2 = $client->messages->create(
    maxTokens: 20000,
    messages: [
        [
            'role' => 'user',
            'content' => [
                [
                    'type' => 'text',
                    'text' => $largeText,
                    'cache_control' => ['type' => 'ephemeral']
                ],
                [
                    'type' => 'text',
                    'text' => 'Analyze the tone of this passage.'
                ]
            ]
        ],
        [
            'role' => 'assistant',
            'content' => $response1->content
        ],
        [
            'role' => 'user',
            'content' => 'Analyze the characters in this passage.'
        ]
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 4000],
);

echo "Second response usage: " . json_encode($response2->usage) . "\n";

echo "\nThird request - different thinking budget (cache miss expected)\n";
$response3 = $client->messages->create(
    maxTokens: 20000,
    messages: [
        [
            'role' => 'user',
            'content' => [
                [
                    'type' => 'text',
                    'text' => $largeText,
                    'cache_control' => ['type' => 'ephemeral']
                ],
                [
                    'type' => 'text',
                    'text' => 'Analyze the tone of this passage.'
                ]
            ]
        ],
        [
            'role' => 'assistant',
            'content' => $response1->content
        ],
        [
            'role' => 'user',
            'content' => 'Analyze the characters in this passage.'
        ],
        [
            'role' => 'assistant',
            'content' => $response2->content
        ],
        [
            'role' => 'user',
            'content' => 'Analyze the setting in this passage.'
        ]
    ],
    model: 'claude-sonnet-4-6',
    thinking: ['type' => 'enabled', 'budget_tokens' => 8000],
);

echo "Third response usage: " . json_encode($response3->usage) . "\n";

require "anthropic"
require "net/http"
require "uri"

def fetch_article_content(url)
  uri = URI.parse(url)
  response = Net::HTTP.get_response(uri)
  text = response.body

  lines = text.split("\n").map(&:strip)
  lines.reject(&:empty?).join("\n")
end

client = Anthropic::Client.new

book_url = "https://www.gutenberg.org/cache/epub/1342/pg1342.txt"
book_content = fetch_article_content(book_url)
large_text = book_content[0...10000]

puts "First request - establishing cache"
response1 = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: {
    type: "enabled",
    budget_tokens: 4000
  },
  messages: [{
    role: "user",
    content: [
      {
        type: "text",
        text: large_text,
        cache_control: { type: "ephemeral" }
      },
      {
        type: "text",
        text: "Analyze the tone of this passage."
      }
    ]
  }]
)

puts "First response usage: #{response1.usage}"

puts "\nSecond request - same thinking parameters (cache hit expected)"
response2 = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: {
    type: "enabled",
    budget_tokens: 4000
  },
  messages: [
    {
      role: "user",
      content: [
        {
          type: "text",
          text: large_text,
          cache_control: { type: "ephemeral" }
        },
        {
          type: "text",
          text: "Analyze the tone of this passage."
        }
      ]
    },
    {
      role: "assistant",
      content: response1.content
    },
    {
      role: "user",
      content: "Analyze the characters in this passage."
    }
  ]
)

puts "Second response usage: #{response2.usage}"

puts "\nThird request - different thinking budget (cache miss expected)"
response3 = client.messages.create(
  model: "claude-sonnet-4-6",
  max_tokens: 20000,
  thinking: {
    type: "enabled",
    budget_tokens: 8000
  },
  messages: [
    {
      role: "user",
      content: [
        {
          type: "text",
          text: large_text,
          cache_control: { type: "ephemeral" }
        },
        {
          type: "text",
          text: "Analyze the tone of this passage."
        }
      ]
    },
    {
      role: "assistant",
      content: response1.content
    },
    {
      role: "user",
      content: "Analyze the characters in this passage."
    },
    {
      role: "assistant",
      content: response2.content
    },
    {
      role: "user",
      content: "Analyze the setting in this passage."
    }
  ]
)

puts "Third response usage: #{response3.usage}"