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

# Coding Agents: How to select and configure models

> Select from Claude, Nova, and OpenAI models for different use cases.

# A guide for coding agents to select and configure models

**Models** are the large language models that **Agents** rely on to understand, reason, and make autonomous decisions.

> **Key Terms**: See the [definitions section of the main guide](https://autonomy.computer/docs/_for-coding-agents.md#definitions).

*Keywords: claude, model selection, claude-sonnet, nova, openai*

This guide covers available models and helps you select the right model for an agent.

## Supported Models

Autonomy Computer supports a wide range of models from different providers. When creating agents, you can specify which model to use with the `Model()` constructor.

For the complete list of supported models with pricing, see the [Models documentation](/docs/agents/models).

## Example of how to use a model

```python theme={null}
from autonomy import Agent, Model, Node

async def main(node):
    # Using Claude Sonnet 4.5 (recommended for most applications)
    await Agent.start(
        node=node,
        name="assistant",
        instructions="You are a helpful assistant",
        model=Model("claude-sonnet-4-5")
    )

    # Using a different model for a different use case
    await Agent.start(
        node=node,
        name="reasoning-agent",
        instructions="You are a reasoning specialist",
        model=Model("claude-opus-4-5")
    )

Node.start(main)
```

### Recommendations for selecting a model

* **For most applications**: `claude-sonnet-4-5` - Best balance of capability and cost
* **For complex reasoning**: `claude-opus-4-5` or `o1` - Maximum intelligence for difficult tasks
* **For fast, simple tasks**: `claude-haiku-4-5` or `gpt-4o-mini` - Quick responses at lower cost
* **For cost-effective solutions**: `nova-micro` or `nova-lite` - Extremely affordable
* **For high-volume production**: `gpt-4.1-nano` or `gpt-5-nano` - Best for scale
* **For embeddings**: `embed-english` or `embed-multilingual` - Recommended for semantic search

All models support the same interface, so you can easily switch between them by changing the model name in your `Model()` constructor.

## Related Guides

* [How to create and deploy a new Autonomy app](https://autonomy.computer/docs/_for-coding-agents/create-a-new-autonomy-app.md)
* [How to give agents tools](https://autonomy.computer/docs/_for-coding-agents/tools.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.