POST
/
v1
/
experimental
/
generate_prompt
curl -X POST https://api.anthropic.com/v1/experimental/generate_prompt \
     --header "x-api-key: $ANTHROPIC_API_KEY" \
     --header "anthropic-version: 2023-06-01" \
     --header "anthropic-beta: prompt-tools-2025-04-02" \
     --header "content-type: application/json" \
     --data \
'{
    "task": "a chef for a meal prep planning service",
    "target_model": "claude-3-7-sonnet-20250219"
}'
{
  "messages": [
    {
      "content": [
        {
          "text": "<generated prompt>",
          "type": "text"
        }
      ],
      "role": "user"
    }
  ],
  "system": "",
  "usage": [
    {
      "input_tokens": 490,
      "output_tokens": 661
    }
  ]
}

提示词工具 API 正在封闭研究预览中。申请加入封闭研究预览。

​
开始之前

提示词工具是一组用于生成和改进提示词的 API。与我们的其他 API 不同，这是一个实验性 API：您需要申请访问权限，并且它不具有与其他 API 相同级别的长期支持承诺。

这些 API 类似于 Anthropic Workbench 中可用的功能，旨在供其他提示词工程平台和游乐场使用。

​
开始使用提示词生成器

要使用提示词生成 API，您需要：

  1. 已加入提示词工具 API 的封闭研究预览
  2. 直接使用 API，而不是 SDK
  3. 添加 beta 标头 prompt-tools-2025-04-02

此 API 在 SDK 中不可用

​
生成提示词

Headers

​
anthropic-beta
string[]

Optional header to specify the beta version(s) you want to use.

To use multiple betas, use a comma separated list like beta1,beta2 or specify the header multiple times for each beta.

​
x-api-key
string
required

Your unique API key for authentication.

This key is required in the header of all API requests, to authenticate your account and access Anthropic's services. Get your API key through the Console. Each key is scoped to a Workspace.

Body

application/json
​
task
string
required

Description of the prompt's purpose.

The task parameter tells Claude what the prompt should do or what kind of role or functionality you want to create. This helps guide the prompt generation process toward your intended use case.

Example:

{"task": "a chef for a meal prep planning service"}
Examples:

"a chef for a meal prep planning service"

​
target_model
string | null
default:

The model this prompt will be used for. This optional parameter helps us understand which models our prompt tools are being used with, but it doesn't currently affect functionality.

Example:

"claude-3-7-sonnet-20250219"
Required string length: 1 - 256
Examples:

"claude-3-7-sonnet-20250219"

Response

200
application/json
Successful Response
​
messages
object[]
required

The response contains a list of message objects in the same format used by the Messages API. Typically includes a user message with the complete generated prompt text, and may include an assistant message with a prefill to guide the model's initial response.

These messages can be used directly in a Messages API request to start a conversation with the generated prompt.

Example:

{
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "You are a chef for a meal prep planning service..."
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "<recipe_planning>"
        }
      ]
    }
  ]
}
Examples:
[
  {
    "content": [
      {
        "text": "<generated prompt>",
        "type": "text"
      }
    ],
    "role": "user"
  }
]
​
system
string
default:
required

Currently, the system field is always returned as an empty string (""). In future iterations, this field may contain generated system prompts.

Directions similar to what would normally be included in a system prompt are included in messages when generating a prompt.

Examples:

""

​
usage
object
required

Usage information