# multillm-openai

OpenAI provider for [multillm](../multillm).

## Installation

```bash
pip install multillm-openai
```

## Usage

```python
import asyncio
import multillm

async def main():
    client = multillm.Client()

    # Simple query
    answer = await client.single("openai/gpt-4o", "Hello!")
    print(answer)

    # Chat completion
    response = await client.chat_complete("openai/gpt-4o", [
        {"role": "user", "content": "What is Python?"}
    ])
    print(response.text)

    # Streaming
    async for chunk in client.chat_complete_stream("openai/gpt-4o", messages):
        print(chunk, end="")

asyncio.run(main())
```

## Configuration

Choose one of the following methods (priority: direct config > env var > config file):

**Option 1: Config file** (recommended)

Create `~/.config/multillm/providers/openai.json`:

```json
{
  "api_key": "sk-...",
  "organization": "org-..."
}
```

Set permissions:
```bash
chmod 600 ~/.config/multillm/providers/openai.json
```

**Option 2: Environment variable**

```bash
export OPENAI_API_KEY=sk-...
```

**Option 3: Direct config**

```python
client = multillm.Client({
    "openai": {"api_key": "sk-...", "organization": "org-..."}
})
```

### Config File Fields

| Field | Required | Description |
|-------|----------|-------------|
| `api_key` | Yes | Your OpenAI API key |
| `organization` | No | Your organization ID (if applicable) |

## Models

Use OpenAI model names after the provider prefix:

- `openai/gpt-4o`
- `openai/gpt-4o-mini`
- `openai/gpt-4-turbo`
- `openai/o1-preview`