# ProviderConfig

> **Class** in `deepagents_cli`

📖 [View in docs](https://reference.langchain.com/python/deepagents-cli/model_config/ProviderConfig)

Configuration for a model provider.

The optional `class_path` field allows bypassing `init_chat_model` entirely
and instantiating an arbitrary `BaseChatModel` subclass via importlib.

!!! warning

    Setting `class_path` executes arbitrary Python code from the user's
    config file. This has the same trust model as `pyproject.toml` build
    scripts — the user controls their own machine.

## Signature

```python
ProviderConfig()
```

## Extends

- `TypedDict`

## Constructors

```python
__init__(
    enabled: bool,
    models: list[str],
    api_key_env: str,
    base_url: str,
    class_path: str,
    params: dict[str, Any],
    profile: dict[str, Any],
)
```

| Name | Type |
|------|------|
| `enabled` | `bool` |
| `models` | `list[str]` |
| `api_key_env` | `str` |
| `base_url` | `str` |
| `class_path` | `str` |
| `params` | `dict[str, Any]` |
| `profile` | `dict[str, Any]` |


## Properties

- `enabled`
- `models`
- `api_key_env`
- `base_url`
- `class_path`
- `params`
- `profile`

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/a9e6e4f7ad7fe161dd9affc3d74bb19784aca70b/libs/cli/deepagents_cli/model_config.py#L164)