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

# Specifying a Model Provider (Routing)

You can specify the upstream provider with a **model name prefix**. This is typically used when you want to pin a specific provider's AI models or have explicit requirements for consistent behavior.

## Default routing (no provider specified)

When you don't add a prefix, the system uses the **default route**: it automatically selects an available upstream.

```text theme={"theme":{"light":"min-light","dark":"min-dark"}}
gpt-4o
```

## Specify a provider (add a prefix to the model name)

Specify the provider using the `provider/<base_model>` format:

```text theme={"theme":{"light":"min-light","dark":"min-dark"}}
openai/gpt-4o
azure/gpt-5.2
anthropic/claude-sonnet-4-5-20250929
google/gemini-2.5-flash
```

## Note: specifying a provider may change the price

* Billing prices for the **default route** and a **specified provider** may differ
* Before using this in production, confirm the price and availability of the model at that provider before pinning it

## Further reading

<CardGroup cols={1}>
  <Card title="Model Naming (prefix / base model / :free)" icon="tag" href="/en/api-reference/introduction/model-naming">
    See the full model naming rules, the free-model :free suffix, and more examples.
  </Card>
</CardGroup>


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