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

# Update custom model

Update a specific custom model. Only the provided fields will be updated - other fields remain unchanged.

<Note>
  **Restrictions**:

  * Only custom models can be updated (not global models)
  * The `model_name` field is read-only and cannot be changed
  * Only the owning organization can update their custom models
</Note>

## Path parameters

<ParamField path="model_name" type="string" required>
  The model's unique name to update.

  <Accordion title="Example">
    ```
    my-custom-gpt-4
    ```
  </Accordion>
</ParamField>

## Request body

All fields are optional. Only provide the fields you want to update.

<ParamField body="display_name" type="string">
  Human-readable display name for the model.

  <Accordion title="Example">
    ```json theme={"system"}
    "display_name": "My Updated Custom GPT-4"
    ```
  </Accordion>
</ParamField>

<ParamField body="custom_provider_id" type="integer | string">
  ID or `provider_id` of the custom provider to associate with this model.
</ParamField>

### Pricing

<ParamField body="input_cost" type="float">
  Cost per 1M input tokens in USD.

  <Accordion title="Example">
    ```json theme={"system"}
    "input_cost": 0.030
    ```
  </Accordion>
</ParamField>

<ParamField body="output_cost" type="float">
  Cost per 1M output tokens in USD.
</ParamField>

<ParamField body="cache_hit_input_cost" type="float">
  Cost per 1M cached input tokens in USD.
</ParamField>

<ParamField body="cache_creation_input_cost" type="float">
  Cost per 1M cache creation tokens in USD.
</ParamField>

### Capabilities

<ParamField body="max_context_window" type="integer">
  Maximum context window size for the model.
</ParamField>

<ParamField body="streaming_support" type="integer">
  Streaming support. `0` for no, `1` for yes.
</ParamField>

<ParamField body="function_call" type="integer">
  Function calling support. `0` for no, `1` for yes.
</ParamField>

<ParamField body="image_support" type="integer">
  Image/vision support. `0` for no, `1` for yes.
</ParamField>

<ParamField body="supported_params_override" type="object">
  Partial override of UI parameter support. New overrides are merged with existing ones.

  <Accordion title="Example">
    ```json theme={"system"}
    {
      "supported_params_override": {
        "temperature": {
          "name": "temperature",
          "type": "number",
          "default": 0.7,
          "min": 0,
          "max": 1.5
        }
      }
    }
    ```
  </Accordion>
</ParamField>

## Response

Returns the updated model object.

<ResponseExample>
  ```json 200 OK theme={"system"}
  {
    "id": "my-custom-gpt-4",
    "model_name": "my-custom-gpt-4",
    "display_name": "My Updated Custom GPT-4",
    "base_model_name": "gpt-4",
    "affiliation_category": "custom",
    "input_cost": 0.030,
    "output_cost": 0.075,
    "max_context_window": 8192,
    "streaming_support": 1,
    "function_call": 1,
    "image_support": 0,
    "source": "db",
    "provider": {
      "id": "my-custom-provider",
      "provider_id": "my-custom-provider",
      "provider_name": "My Custom Provider",
      "organization_id": 123
    }
  }
  ```

  ```json 403 Forbidden theme={"system"}
  {
    "detail": "Cannot modify hardcoded models. They are synced from code and will be overwritten on next deployment. Only database-only models can be modified."
  }
  ```

  ```json 404 Not Found theme={"system"}
  {
    "detail": "Not found."
  }
  ```

  ```json 401 Unauthorized theme={"system"}
  {
    "detail": "Authentication credentials were not provided."
  }
  ```
</ResponseExample>

<RequestExample>
  ```python Python theme={"system"}
  import requests

  model_name = "my-custom-gpt-4"
  url = f"https://api.keywordsai.co/api/models/{model_name}/"
  headers = {
      "Authorization": "Bearer YOUR_API_KEY",
      "Content-Type": "application/json"
  }
  payload = {
      "display_name": "My Updated Custom GPT-4",
      "input_cost": 0.030
  }

  response = requests.patch(url, headers=headers, json=payload)
  print(response.json())
  ```

  ```typescript TypeScript theme={"system"}
  const modelName = 'my-custom-gpt-4';
  const url = `https://api.keywordsai.co/api/models/${modelName}/`;
  const headers = {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json'
  };

  const payload = {
      display_name: 'My Updated Custom GPT-4',
      input_cost: 0.030
  };

  const response = await fetch(url, {
      method: 'PATCH',
      headers: headers,
      body: JSON.stringify(payload)
  });

  const data = await response.json();
  console.log(data);
  ```

  ```bash cURL theme={"system"}
  curl -X PATCH "https://api.keywordsai.co/api/models/my-custom-gpt-4/" \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "display_name": "My Updated Custom GPT-4",
      "input_cost": 0.030
    }'
  ```
</RequestExample>