# OpenAI (/en/ai/models/llm/openai)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

OpenAI provides frontier models ranging from lightweight to high-capability.

### Sample configuration [#sample-configuration]

The following examples show how to configure OpenAI LLM when starting a conversational AI agent.

<Tabs defaultValue="python" groupId="ai-sdk-language">
  <TabsList>
    <TabsTrigger value="python">
      Python SDK
    </TabsTrigger>

    <TabsTrigger value="typescript">
      TypeScript SDK
    </TabsTrigger>

    <TabsTrigger value="go">
      Go SDK
    </TabsTrigger>

    <TabsTrigger value="rest-api">
      REST API
    </TabsTrigger>
  </TabsList>

  <TabsContent value="python">
    ```python
    from agora_agent import Agent, OpenAI

    # client is your configured Agora client
    agent = (
        Agent(client)
        .with_stt(...)  # configure your STT vendor
        .with_llm(OpenAI(
            api_key='your-openai-key',  # omit api_key and base_url to use Agora-managed mode
            base_url='https://api.openai.com/v1/chat/completions',
            model='gpt-4o-mini',
            system_messages=[{'role': 'system', 'content': 'You are a helpful chatbot.'}],
            greeting_message='Hello, how can I assist you?',
            failure_message='Please hold on a second.',
            max_history=32,
        ))
        .with_tts(...)  # configure your TTS vendor
    )
    ```
  </TabsContent>

  <TabsContent value="typescript">
    ```typescript
    import { Agent, OpenAI } from 'agora-agents';

    // client is your configured Agora client
    const agent = new Agent({ client })
      .withStt(/* configure your STT vendor */)
      .withLlm(new OpenAI({
        apiKey: 'your-openai-key',  // omit apiKey and url to use Agora-managed mode
        url: 'https://api.openai.com/v1/chat/completions',
        model: 'gpt-4o-mini',
        systemMessages: [{ role: 'system', content: 'You are a helpful chatbot.' }],
        greetingMessage: 'Hello, how can I assist you?',
        failureMessage: 'Please hold on a second.',
        maxHistory: 32,
      }))
      .withTts(/* configure your TTS vendor */);
    ```
  </TabsContent>

  <TabsContent value="go">
    ```go
    import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"

    // client is your configured Agora client
    agent := agentkit.NewAgent(client).WithStt(/* configure your STT vendor */).
      WithLlm(
        vendors.NewOpenAI(vendors.OpenAIOptions{
            APIKey:  "your-openai-key",  // omit APIKey and BaseURL to use Agora-managed mode
            BaseURL: "https://api.openai.com/v1/chat/completions",
            Model:   "gpt-4o-mini",
            SystemMessages: []map[string]interface{}{
                {"role": "system", "content": "You are a helpful chatbot."},
            },
            GreetingMessage: "Hello, how can I assist you?",
            FailureMessage:  "Please hold on a second.",
            MaxHistory:      agora.Int(32),
        }),
    ).WithTts(/* configure your TTS vendor */)
    ```
  </TabsContent>

  <TabsContent value="rest-api">
    * **Managed mode**

      To use an OpenAI LLM with Agora-managed credentials, set `credential_mode` to `"managed"` in the `llm` block. When using managed mode, `api_key` is not required. You can still use the `llm` field to configure additional settings such as `system_messages` and `greeting_message`. For more information, see [Use managed mode](/en/ai/build/custom-model-integration/managed-mode).

      ```json
      "llm": {
        "credential_mode": "managed",
        "vendor": "openai",
        "style": "openai",
        "url": "https://api.openai.com/v1/chat/completions",
        "params": {
          "model": "gpt-4.1-mini"
        },
        "system_messages": [
          {
            "role": "system",
            "content": "You are a helpful chatbot."
          }
        ],
        "max_history": 32,
        "greeting_message": "Hello, how can I assist you?",
        "failure_message": "Please hold on a second."
      }
      ```

    * **BYOK**

      ```json
      "llm": {
          "url": "https://api.openai.com/v1/chat/completions",
          "api_key": "<your_llm_key>",
          "system_messages": [
            {
              "role": "system",
              "content": "You are a helpful chatbot."
            }
          ],
          "max_history": 32,
          "greeting_message": "Hello, how can I assist you?",
          "failure_message": "Please hold on a second.",
          "params": {
            "model": "gpt-4o-mini"
          }
        }
      ```
  </TabsContent>
</Tabs>

### Key parameters [#key-parameters]

The following parameters are required when using your own API key (BYOK). When using managed mode, `api_key` is not required. For more information, see [Use managed mode](/en/ai/build/custom-model-integration/managed-mode).

<ParameterList title="llm">
  <Parameter name="api_key" type="string">
    Create or manage your API key from [OpenAI organization settings](https://platform.openai.com/settings/organization/api-keys). Required when using your own API key (BYOK).
  </Parameter>

  <Parameter name="url" type="string">
    Use the completions endpoint.
  </Parameter>

  <Parameter name="params" type="object">
    <Parameter name="model" type="string">
      Refer to [OpenAI models](https://platform.openai.com/docs/models) for available models.
    </Parameter>
  </Parameter>
</ParameterList>

For complete `llm` configuration options, see [LLM parameters](/en/api-reference/api-ref/conversational-ai/join#properties-llm). For OpenAI-specific options and model capabilities, see the [OpenAI API documentation](https://platform.openai.com/docs/api-reference/chat).