### Configure LlamaAPI client with openai-generic provider

Source: https://docs.proxyman.io

Use this BAML configuration to call Llama models via the OpenAI-compatible endpoint. The base_url must point to https://llama-api.meta.com/compat/v1, and the api_key is read from the LLAMA_API_KEY environment variable. The model is set to Llama-3.3-8B-Instruct.

```baml
client<llm> LlamaAPI {
  provider openai-generic
  retry_policy Exponential
  options {
    base_url "https://llama-api.meta.com/compat/v1"
    model "Llama-3.3-8B-Instruct"
    api_key env.LLAMA_API_KEY
    // see openai-generic docs for more options
  }
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.