# API Reference

This API reference describes the RESTful, streaming, and real‑time APIs you can use to interact with the Freddy platform by Aitronos.

## Getting Started

### Option 1: Use the Python SDK (Recommended)

The official Python SDK provides a clean, type-safe interface to the Freddy API:


```bash
pip install freddy-ai
```


```python
from freddy import FreddyClient

with FreddyClient(api_key="your-api-key") as client:
    response = client.responses.create(
        model="gpt-4.1",
        inputs=[{"role": "user", "texts": [{"text": "Hello!"}]}]
    )
    print(response.output[0].content[0].text)
```

**Benefits:**

- ✅ Type hints and autocompletion
- ✅ Automatic error handling
- ✅ Sync and async support
- ✅ Production-ready patterns


[View complete Python SDK documentation →](/docs/documentation/libraries/python-sdk)

### Option 2: Direct HTTP Requests

The REST APIs are usable via HTTP in any environment that supports HTTP requests:


```bash
curl https://api.freddy.aitronos.com/v1/model/response \
  -H "Authorization: Bearer $FREDDY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "inputs": [{"role": "user", "texts": [{"text": "Hello!"}]}]
  }'
```

### Other Languages

Language-specific SDKs are available for JavaScript/TypeScript, .NET, and more. See the [Libraries & SDKs](/docs/documentation/libraries) page for the full list.