> ## Documentation Index
> Fetch the complete documentation index at: https://docs.helicone.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Prompt Body

> Retrieve the full prompt body (messages, tools, etc.) for a specific prompt version

Retrieves the complete prompt body content for a specific prompt version, including messages, model configuration, tools, and other parameters. The prompt body is stored in S3 and contains the actual template content.

### Path Parameters

<ParamField path="promptVersionId" type="string" required>
  The unique identifier (UUID) of the prompt version to retrieve
</ParamField>

### Response

<ResponseField name="model" type="string">
  The model specified in the prompt (e.g., "gpt-4o-mini", "claude-3-opus")
</ResponseField>

<ResponseField name="messages" type="array">
  Array of message objects that make up the prompt template

  <Expandable title="Message Object">
    <ResponseField name="role" type="string">
      The role of the message (e.g., "system", "user", "assistant")
    </ResponseField>

    <ResponseField name="content" type="string">
      The content of the message, may include template variables like `{{ hc:variableName:type }}`
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="temperature" type="number" optional>
  The temperature setting for the model (if configured)
</ResponseField>

<ResponseField name="max_tokens" type="number" optional>
  The maximum number of tokens to generate (if configured)
</ResponseField>

<ResponseField name="tools" type="array" optional>
  Array of tool/function definitions (if configured)
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X GET "https://api.helicone.ai/v1/prompt-2025/6739b412-5fbb-498e-ab99-68ef21eb7df8/prompt-body" \
    -H "Authorization: Bearer $HELICONE_API_KEY"
  ```

  ```typescript TypeScript theme={null}
  const response = await fetch('https://api.helicone.ai/v1/prompt-2025/6739b412-5fbb-498e-ab99-68ef21eb7df8/prompt-body', {
    method: 'GET',
    headers: {
      'Authorization': `Bearer ${HELICONE_API_KEY}`,
    },
  });

  const promptBody = await response.json();
  ```

  ```python Python theme={null}
  import requests

  response = requests.get(
      'https://api.helicone.ai/v1/prompt-2025/6739b412-5fbb-498e-ab99-68ef21eb7df8/prompt-body',
      headers={
          'Authorization': f'Bearer {HELICONE_API_KEY}',
      }
  )

  prompt_body = response.json()
  ```
</RequestExample>

<ResponseExample>
  ```json Response theme={null}
  {
    "data": {
      "model": "gpt-4o-mini",
      "messages": [
        {
          "role": "system",
          "content": "You are a helpful AI assistant.\n\nYou are speaking to {{ hc:name:string }}"
        }
      ],
      "temperature": 0.7,
      "max_tokens": 1000
    },
    "error": null
  }
  ```
</ResponseExample>

### Notes

* This endpoint returns the full prompt body content, unlike other endpoints that only return metadata
* The `promptVersionId` must be a UUID, not the 6-character prompt ID
* Template variables in the format `{{ hc:variableName:type }}` can be used for dynamic content
* Use the `/v1/prompt-2025/query/versions` endpoint to get the version UUID from a prompt ID