> ## 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.

# Supported models

> Call 200+ LLMs with a single OpenAI compatible format

## Choose a model

After you integrate the LLM proxy, you can choose a model from the [Models page](https://platform.keywordsai.co/platform/models). In this page, you can see each model's description, pricing, and other metrics, which helps you choose the best model for your use case.

<Frame>
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/llm-proxy/models.png" />
</Frame>

### Model family

You can also click an exact model to see it's model family, which is a group of models that hosted by the different LLM providers.

<Frame>
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/llm-proxy/model-details.png" />
</Frame>

### Integration code

If you have already integrated the LLM proxy, you can click the `Code` button to copy the integration code with the language you are using.

<Frame>
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/llm-proxy/model-code.png" />
</Frame>

## Call models in different frameworks

<Tabs>
  <Tab title="OpenAI Python SDK">
    ```python {9} 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="claude-3-5-haiku-20241022",
        messages=[
            {"role": "user", "content": "Tell me a long story"}
        ]
    )
    ```
  </Tab>

  <Tab title="OpenAI TypeScript SDK">
    Here is an example of how to disable logging in the OpenAI TypeScript SDK. In OpenAI TypeScript SDK, you should add a `// @ts-expect-error` before the disable\_log field.

    ```typescript {11} 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: "claude-3-5-sonnet-20241022"
      })
      .asResponse();

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

  <Tab title="Standard API">
    ```python {3} theme={"system"}
    import requests
    def demo_call(input, 
                  model="groq/llama-3.3-70b-specdec",
                  token="YOUR_KEYWORDS_AI_API_KEY",
                  ):
        headers = {
            'Content-Type': 'application/json',
            'Authorization': f'Bearer {token}',
        }

        data = {
            'model': model,
            'messages': [{'role': 'user', 'content': input}],
        }

        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())
    ```
  </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>