> ## Documentation Index
> Fetch the complete documentation index at: https://docs.definable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Examples

> Examples for invoking LLMs across providers.

## 01 — Basic Invocation

The simplest way to call an LLM. Sends a message and prints the response.

```python theme={null}
from definable.model.openai import OpenAIChat
from definable.model.message import Message

model = OpenAIChat(id="gpt-4o-mini")

messages = [
    Message(role="system", content="You are a helpful assistant."),
    Message(role="user", content="What is the capital of France?"),
]

response = model.invoke(
    messages=messages,
    assistant_message=Message(role="assistant", content=""),
)

print(response.content)
print(f"Tokens: {response.response_usage.total_tokens}")
```

```bash theme={null}
python definable/examples/models/01_basic_invoke.py
```

## 02 — Async Invocation

Same as above, but using `asyncio` for non-blocking execution.

```python theme={null}
import asyncio
from definable.model.openai import OpenAIChat
from definable.model.message import Message

async def main():
    model = OpenAIChat(id="gpt-4o-mini")
    messages = [Message(role="user", content="Hello!")]
    response = await model.ainvoke(
        messages=messages,
        assistant_message=Message(role="assistant", content=""),
    )
    print(response.content)

asyncio.run(main())
```

```bash theme={null}
python definable/examples/models/02_async_invoke.py
```

## 03 — Streaming

Stream tokens as they are generated for real-time output.

```python theme={null}
from definable.model.openai import OpenAIChat
from definable.model.message import Message

model = OpenAIChat(id="gpt-4o-mini")
messages = [Message(role="user", content="Tell me a short story.")]

for chunk in model.invoke_stream(
    messages=messages,
    assistant_message=Message(role="assistant", content=""),
):
    if chunk.content:
        print(chunk.content, end="", flush=True)
```

```bash theme={null}
python definable/examples/models/03_streaming.py
```

## 04 — Structured Output

Return Pydantic models instead of free text.

```python theme={null}
import json
from pydantic import BaseModel
from definable.model.openai import OpenAIChat
from definable.model.message import Message

class Movie(BaseModel):
    title: str
    year: int
    genre: str

model = OpenAIChat(id="gpt-4o-mini")
response = model.invoke(
    messages=[Message(role="user", content="Recommend a sci-fi movie.")],
    assistant_message=Message(role="assistant", content=""),
    response_format=Movie,
)
movie = Movie(**json.loads(response.content))
print(movie)  # Movie(title=..., year=..., genre=...)
```

```bash theme={null}
python definable/examples/models/04_structured_output.py
```

## 05 — Multi-Provider

Use the same message format across OpenAI, DeepSeek, Moonshot, and xAI.

```python theme={null}
from definable.model.openai import OpenAIChat
from definable.model.deepseek import DeepSeekChat
from definable.model.moonshot import MoonshotChat
from definable.model.xai import xAI

providers = [
    OpenAIChat(id="gpt-4o-mini"),
    DeepSeekChat(id="deepseek-chat"),
    MoonshotChat(id="kimi-k2-turbo-preview"),
    xAI(id="grok-3"),
]

from definable.model.message import Message

messages = [Message(role="user", content="What is 2 + 2?")]
assistant = Message(role="assistant", content="")

for model in providers:
    response = model.invoke(messages=messages, assistant_message=assistant)
    print(f"{model.provider}: {response.content[:100]}")
```

```bash theme={null}
python definable/examples/models/05_multi_provider.py
```

<Note>
  Requires API keys for each provider: `OPENAI_API_KEY`, `DEEPSEEK_API_KEY`, `MOONSHOT_API_KEY`, `XAI_API_KEY`.
</Note>

## 06 — Vision & Audio

Send images and audio to multimodal models.

```python theme={null}
from definable.model.openai import OpenAIChat
from definable.model.message import Message
from definable.media import Image

model = OpenAIChat(id="gpt-4o")
response = model.invoke(
    messages=[Message(role="user", content="Describe this image.", images=[Image(url="https://example.com/photo.jpg")])],
    assistant_message=Message(role="assistant", content=""),
)
print(response.content)
```

```bash theme={null}
python definable/examples/models/06_vision_and_audio.py
```