# default_effort_for_model

> **Function** in `deepagents_code`

📖 [View in docs](https://reference.langchain.com/python/deepagents-code/reasoning_effort/default_effort_for_model)

Return the documented default reasoning effort when known.

Returns a plain `str` rather than `EffortLabel`: like
`supported_efforts_for_model`, this is the public boundary where the label
vocabulary is intentionally dropped, since every caller treats the value as
display text.

## Signature

```python
default_effort_for_model(
    model_spec: str | None,
) -> str | None
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `model_spec` | `str \| None` | Yes | `provider:model` spec for the active model. |

## Returns

`str | None`

The provider default effort label, or `None` when the default is unknown.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/e14e0adcbe78565ed3650e7f24b2a775d5437d25/libs/code/deepagents_code/reasoning_effort.py#L507)