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

# Update Prompt

> Create a new version of an existing prompt

Creates a new version of an existing prompt. You can create either a minor version (incremental updates) or a major version (breaking changes).

## Request Body

<ParamField body="promptId" type="string" required>
  The unique identifier of the prompt to update
</ParamField>

<ParamField body="promptVersionId" type="string" required>
  The version ID to base the new version on
</ParamField>

<ParamField body="newMajorVersion" type="boolean" required>
  Whether to create a new major version (true) or minor version (false)
</ParamField>

<ParamField body="commitMessage" type="string" required>
  Description of the changes in this version
</ParamField>

<ParamField body="environment" type="string">
  Optional environment to associate with this version (e.g., "production", "staging")
</ParamField>

<ParamField body="promptBody" type="object" required>
  The updated prompt content in OpenAI chat format

  <Expandable title="Prompt Body">
    <ParamField body="model" type="string">
      The model to use
    </ParamField>

    <ParamField body="messages" type="array">
      Array of message objects with role and content
    </ParamField>

    <ParamField body="temperature" type="number">
      Sampling temperature (0-2)
    </ParamField>

    <ParamField body="top_p" type="number">
      Nucleus sampling parameter
    </ParamField>

    <ParamField body="max_tokens" type="number">
      Maximum tokens to generate
    </ParamField>

    <ParamField body="tools" type="array">
      Array of tool/function definitions
    </ParamField>

    <ParamField body="tool_choice" type="string | object">
      Controls which tool to call
    </ParamField>
  </Expandable>
</ParamField>

## Response

<ResponseField name="data" type="object">
  <ResponseField name="id" type="string">
    The unique identifier for the new version
  </ResponseField>
</ResponseField>

<ResponseField name="error" type="string | null">
  Error message if the request failed, null otherwise
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST https://api.helicone.ai/v1/prompt-2025/update \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "promptId": "prompt_abc123xyz",
      "promptVersionId": "version_def456uvw",
      "newMajorVersion": false,
      "commitMessage": "Updated temperature and added max_tokens",
      "environment": "production",
      "promptBody": {
        "model": "gpt-4o",
        "messages": [
          {
            "role": "system",
            "content": "You are a helpful customer support agent. Be polite and professional."
          },
          {
            "role": "user",
            "content": "{{user_question}}"
          }
        ],
        "temperature": 0.5,
        "max_tokens": 750
      }
    }'
  ```

  ```typescript TypeScript theme={null}
  const response = await fetch('https://api.helicone.ai/v1/prompt-2025/update', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      promptId: 'prompt_abc123xyz',
      promptVersionId: 'version_def456uvw',
      newMajorVersion: false,
      commitMessage: 'Updated temperature and added max_tokens',
      environment: 'production',
      promptBody: {
        model: 'gpt-4o',
        messages: [
          {
            role: 'system',
            content: 'You are a helpful customer support agent. Be polite and professional.',
          },
          {
            role: 'user',
            content: '{{user_question}}',
          },
        ],
        temperature: 0.5,
        max_tokens: 750,
      },
    }),
  });

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

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

  response = requests.post(
      'https://api.helicone.ai/v1/prompt-2025/update',
      headers={
          'Authorization': 'Bearer YOUR_API_KEY',
          'Content-Type': 'application/json',
      },
      json={
          'promptId': 'prompt_abc123xyz',
          'promptVersionId': 'version_def456uvw',
          'newMajorVersion': False,
          'commitMessage': 'Updated temperature and added max_tokens',
          'environment': 'production',
          'promptBody': {
              'model': 'gpt-4o',
              'messages': [
                  {
                      'role': 'system',
                      'content': 'You are a helpful customer support agent. Be polite and professional.',
                  },
                  {
                      'role': 'user',
                      'content': '{{user_question}}',
                  },
              ],
              'temperature': 0.5,
              'max_tokens': 750,
          },
      },
  )

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

<ResponseExample>
  ```json 200 Success theme={null}
  {
    "data": {
      "id": "version_ghi789rst"
    },
    "error": null
  }
  ```

  ```json 500 Error theme={null}
  {
    "data": null,
    "error": "Failed to create new version"
  }
  ```
</ResponseExample>

## Version Management

### Minor Versions

Set `newMajorVersion: false` for incremental updates:

* Bug fixes
* Small improvements
* Configuration tweaks

Example: 1.0 → 1.1 → 1.2

### Major Versions

Set `newMajorVersion: true` for breaking changes:

* Complete rewrites
* Structural changes
* Different model or approach

Example: 1.5 → 2.0 → 3.0