working-with-messages

build-with-claude/working-with-messages First recorded · 1056 lines, first recorded

## Basic request and response ## Multiple conversational turns ### System role in messages ## Prefilling Claude's response ## Vision ## Next steps

The first capture of this source. The page was already there, and this is what it said.

---
title: Using the Messages API
url: https://platform.claude.com/docs/en/build-with-claude/working-with-messages
description: Practical patterns and examples for using the Messages API effectively
---

Anthropic offers two ways to build with Claude, each suited to different use cases:

|                | Messages API                                | Claude Managed Agents                                                     |
| -------------- | ------------------------------------------- | ------------------------------------------------------------------------- |
| **What it is** | Direct model prompting access               | Pre-built, configurable agent harness that runs in managed infrastructure |
| **Best for**   | Custom agent loops and fine-grained control | Long-running tasks and asynchronous work                                  |

This guide covers common patterns for working with the Messages API, including basic requests, multi-turn conversations, prefill techniques, and vision capabilities. For complete API specifications, see the [Messages API reference](https://platform.claude.com/docs/en/api/messages/create). For the managed agent harness instead, see the [Claude Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview).

<Note>
  For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
</Note>

## Basic request and response

<Note>
  The `temperature`, `top_p`, and `top_k` sampling parameters are not supported on Claude 4.7 and later models and Claude Mythos Preview. Setting them to a non-default value returns a 400 error. Omit them from request payloads and use prompting to guide the model's behavior instead. See the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide#migrating-from-claude-opus-47).
</Note>

<CodeGroup>
  ```bash cURL
  #!/bin/sh
  curl https://api.anthropic.com/v1/messages \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "content-type: application/json" \
    -d '{
      "model": "claude-opus-5",
      "max_tokens": 1024,
      "messages": [
        {"role": "user", "content": "Hello, Claude"}
      ]
    }'
  ```

  ```bash CLI
  ant messages create \
    --model claude-opus-5 \
    --max-tokens 1024 \
    --message '{role: user, content: "Hello, Claude"}'
  ```

  ```python Python
  message = anthropic.Anthropic().messages.create(
      model="claude-opus-5",
      max_tokens=1024,
      messages=[{"role": "user", "content": "Hello, Claude"}],
  )
  print(message)
  ```

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

  const message = await anthropic.messages.create({
    model: "claude-opus-5",
    max_tokens: 1024,
    messages: [{ role: "user", content: "Hello, Claude" }]
  });
  console.log(message);
  ```

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

  var parameters = new MessageCreateParams
  {
      Model = Model.ClaudeOpus5,
      MaxTokens = 1024,
      Messages = [new() { Role = Role.User, Content = "Hello, Claude" }]
  };
  var message = await client.Messages.Create(parameters);
  Console.WriteLine(message);
  ```

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

  response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
  	Model:     anthropic.ModelClaudeOpus5,
  	MaxTokens: 1024,
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Hello, Claude")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }
  fmt.Println(response)
  ```

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

  MessageCreateParams params = MessageCreateParams.builder()
      .model(Model.CLAUDE_OPUS_5)
      .maxTokens(1024L)
      .addUserMessage("Hello, Claude")
      .build();

  Message response = client.messages().create(params);
  System.out.println(response);
  ```

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

  $message = $client->messages->create(
      maxTokens: 1024,
      messages: [['role' => 'user', 'content' => 'Hello, Claude']],
      model: 'claude-opus-5',
  );
  echo json_encode($message, JSON_PRETTY_PRINT), PHP_EOL;
  ```

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

  message = client.messages.create(
    model: "claude-opus-5",
    max_tokens: 1024,
    messages: [
      { role: "user", content: "Hello, Claude" }
    ]
  )
  puts message
  ```
</CodeGroup>

```json Output
{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello!"
    }
  ],
  "model": "claude-opus-5",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 12,
    "output_tokens": 6
  }
}
```

Refusal responses (`stop_reason: "refusal"`) also include a `stop_details` object identifying the policy category that triggered the refusal, on every model. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the field reference and example handling code.

## Multiple conversational turns

The Messages API is stateless, which means that you always send the full conversational history to the API. You can use this pattern to build up a conversation over time. Earlier conversational turns don't necessarily need to actually originate from Claude. You can use synthetic `assistant` messages.

<CodeGroup>
  ```bash cURL
  #!/bin/sh
  curl https://api.anthropic.com/v1/messages \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "content-type: application/json" \
    -d '{
      "model": "claude-opus-5",
      "max_tokens": 1024,
      "messages": [
        {"role": "user", "content": "Hello, Claude"},
        {"role": "assistant", "content": "Hello!"},
        {"role": "user", "content": "Can you describe LLMs to me?"}

      ]
    }'
  ```

  ```bash CLI
  ant messages create \
    --model claude-opus-5 \
    --max-tokens 1024 \
    --message '{role: user, content: "Hello, Claude"}' \
    --message '{role: assistant, content: "Hello!"}' \
    --message '{role: user, content: "Can you describe LLMs to me?"}'
  ```

  ```python Python
  message = anthropic.Anthropic().messages.create(
      model="claude-opus-5",
      max_tokens=1024,
      messages=[
          {"role": "user", "content": "Hello, Claude"},
          {"role": "assistant", "content": "Hello!"},
          {"role": "user", "content": "Can you describe LLMs to me?"},
      ],
  )
  print(message)
  ```

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

  const message = await anthropic.messages.create({
    model: "claude-opus-5",
    max_tokens: 1024,
    messages: [
      { role: "user", content: "Hello, Claude" },
      { role: "assistant", content: "Hello!" },
      { role: "user", content: "Can you describe LLMs to me?" }
    ]
  });
  console.log(message);
  ```

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

  var parameters = new MessageCreateParams
  {
      Model = Model.ClaudeOpus5,
      MaxTokens = 1024,
      Messages =
      [
          new() { Role = Role.User, Content = "Hello, Claude" },
          new() { Role = Role.Assistant, Content = "Hello!" },
          new() { Role = Role.User, Content = "Can you describe LLMs to me?" }
      ]
  };

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

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

  response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
  	Model:     anthropic.ModelClaudeOpus5,
  	MaxTokens: 1024,
  	Messages: []anthropic.MessageParam{
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Hello, Claude")),
  		anthropic.NewAssistantMessage(anthropic.NewTextBlock("Hello!")),
  		anthropic.NewUserMessage(anthropic.NewTextBlock("Can you describe LLMs to me?")),
  	},
  })
  if err != nil {
  	log.Fatal(err)
  }
  fmt.Println(response)
  ```

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

  MessageCreateParams params = MessageCreateParams.builder()
      .model(Model.CLAUDE_OPUS_5)
      .maxTokens(1024L)
      .addUserMessage("Hello, Claude")
      .addAssistantMessage("Hello!")
      .addUserMessage("Can you describe LLMs to me?")
      .build();

  Message response = client.messages().create(params);
  System.out.println(response);
  ```

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

  $message = $client->messages->create(
      maxTokens: 1024,
      messages: [
          ['role' => 'user', 'content' => 'Hello, Claude'],
          ['role' => 'assistant', 'content' => 'Hello!'],
          ['role' => 'user', 'content' => 'Can you describe LLMs to me?'],
      ],
      model: 'claude-opus-5',
  );

  echo json_encode($message, JSON_PRETTY_PRINT), PHP_EOL;
  ```

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

  message = client.messages.create(
    model: "claude-opus-5",
    max_tokens: 1024,
    messages: [
      { role: "user", content: "Hello, Claude" },
      { role: "assistant", content: "Hello!" },
      { role: "user", content: "Can you describe LLMs to me?" }
    ]
  )
  puts message
  ```

Cut at 300 lines.