> ## 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.

# Set budget for users

<Note>Only Keywords AI users who are using the **LLM proxy** can set budget for their users. See how to [set up LLM proxy](/get-started/quickstart/gateway) for more information.</Note>

<Tabs>
  <Tab title="OpenAI Python SDK">
    Here is an example of how to send a user's data with the parameter `customer_params` to Keywords AI in the OpenAI Python SDK.

    ```python {16-18} theme={"system"}
    from openai import OpenAI

    client = OpenAI(
        base_url="https://api.keywordsai.co/api/",
        api_key="YOUR_KEYWORDSAI_API_KEY",
    )

    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {"role": "user", "content": "Tell me a long story"}
        ],
        extra_body={
            "customer_params": {
                "customer_identifier": "customer_1",
                "budget_duration": "yearly",
                "period_budget": 1000,
                "total_budget": 10000 
            }
        }
    )
    ```
  </Tab>

  <Tab title="OpenAI TypeScript SDK">
    Here is an example of how to send a user's data with the parameter `customer_params` to Keywords AI in the OpenAI TypeScript SDK. In OpenAI TypeScript SDK, you should add a `// @ts-expect-error` before the metadata field.

    ```typescript {15-17} theme={"system"}
    import { OpenAI } from "openai";

    const client = new OpenAI({
      baseURL: "https://api.keywordsai.co/api",
      apiKey: "YOUR_KEYWORDSAI_API_KEY",
    });

    const response = await client.chat.completions
      .create({
        messages: [{ role: "user", content: "Say this is a test" }],
        model: "gpt-4o-mini",
        // @ts-expect-error
        customer_params: {
            "customer_identifier": "customer_1",
            "budget_duration": "yearly",
            "period_budget": 1000,
            "total_budget": 10000 
        }
      })
      .asResponse();

    console.log(await response.json());
    ```
  </Tab>

  <Tab title="Standard API">
    <CodeGroup>
      ```python LLM proxy {16-18} theme={"system"}
      import requests
      def demo_call(input, 
                    model="gpt-4o-mini",
                    token="YOUR_KEYWORDS_AI_API_KEY",
                    ):
          headers = {
              'Content-Type': 'application/json',
              'Authorization': f'Bearer {token}',
          }

          data = {
              'model': model,
              'messages': [{'role': 'user', 'content': input}],
              'customer_params': {
                  "customer_identifier": "customer_1",
                  "budget_duration": "yearly",
                  "period_budget": 1000,
                  "total_budget": 10000 
              }
          }

          response = requests.post('https://api.keywordsai.co/api/chat/completions', headers=headers, json=data)
          return response

      messages = "Say 'Hello World'"
      print(demo_call(messages).json())
      ```

      ```python Async logging {18-20} theme={"system"}
      import requests

      url = "https://api.keywordsai.co/api/request-logs/create/"
      payload = {
          "model": "gpt-4o-mini",
          "prompt_messages": [
              {
                  "role": "user",
                  "content": "Hi"
              },
          ],
          "completion_message": {
              "role": "assistant",
              "content": "Hi, how can I assist you today?"
          },
          "customer_params": {
              "customer_identifier": "customer_1",
              "budget_duration": "yearly",
              "period_budget": 1000,
              "total_budget": 10000 
          }
          # other parameters
      }
      headers = {
          "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
          "Content-Type": "application/json"
      }

      response = requests.request("POST", url, headers=headers, json=payload)
      ```
    </CodeGroup>
  </Tab>

  <Tab title="Other SDKs">
    We also support adding credentials in other SDKs or languages, please check out our [integration section](/documentation/admin/llm_provider_keys) for more information.
  </Tab>
</Tabs>

<Tip>
  You can also use `period_start` and `period_end` to set the budget period. In this case, you don't need to set the `budget_duration`.
</Tip>

## Parameters

<ParamField path="period_start" type="string">
  The start date of the period. It should be in the format `YYYY-MM-DD`.
</ParamField>

<ParamField path="period_end" type="string">
  The start date of the period. It should be in the format `YYYY-MM-DD`.
</ParamField>

<ParamField path="budget_duration" type="string">
  Choices are `yearly`, `monthly`, `weekly`, and `daily`
</ParamField>

<ParamField path="period_budget" type="float">
  The budget for the period. It should be a float.
</ParamField>

<ParamField path="markup_percentage" type="float">
  The markup percentage for the period. Usage report of your customers through this key will be increased by this percentge.
</ParamField>

<ParamField path="total_budget" type="float">
  The total budget for a user.
</ParamField>

## Other ways to set budget

You can also set the budget to a specific user by calling the [User Update endpoint](/api-endpoints/observe/users/update) or the [User Creation endpoint](/api-endpoints/observe/users/create) for the new users.