> ## Documentation Index > Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt > Use this file to discover all available pages before exploring further. # autogen.ModelClient
`ModelClient`



```python theme={null}
ModelClient(*args, **kwargs)
```

A client class must implement the following methods: 
- create must return a response object that implements the ModelClientResponseProtocol

* cost must return the cost of the response
* get\_usage must return a dict with the following keys: 
    - prompt\_tokens
  * completion\_tokens
  * total\_tokens
  * cost
  * model

This class is used to create a client that can be used by OpenAIWrapper.
The response returned from create must adhere to the ModelClientResponseProtocol but can be extended however needed.
The message\_retrieval method must be implemented to return a list of str or a list of messages from the response.

Parameters:

| Name       | Description |
| ---------- | ----------- |
| `*args`    |             |
| `**kwargs` |             |

### Class Attributes



#### ModelClientResponseProtocol




Base class for protocol classes.
Protocol classes are defined as:: 
    class Proto(Protocol): 
        def meth(self) -> int: 
            ...
Such classes are primarily used with static type checkers that recognize
structural subtyping (static duck-typing).
For example:: 
    class C: 
        def meth(self) -> int: 
            return 0

def func(x: Proto) -> int: 
        return x.meth()

func(C())  # Passes static type check

See PEP 544 for details. Protocol classes decorated with
@typing.runtime\_checkable act as simple-minded runtime protocols that check
only the presence of given attributes, ignoring their type signatures.
Protocol classes can be generic, they are defined as:: 
    class GenProto[T](Protocol): 
        def meth(self) -> T: 
            ...



#### RESPONSE\_USAGE\_KEYS







### Static Methods



#### get\_usage

```python theme={null}
get_usage(response: ModelClientResponseProtocol) -> dict
```

Return usage summary of the response using RESPONSE\_USAGE\_KEYS.

Parameters:

| Name       | Description                           |
| ---------- | ------------------------------------- |
| `response` | **Type:** ModelClientResponseProtocol |




### Instance Methods



#### cost

```python theme={null}
cost(self, response: ModelClientResponseProtocol) -> float
```

Parameters:

| Name       | Description                           |
| ---------- | ------------------------------------- |
| `response` | **Type:** ModelClientResponseProtocol |






#### create

```python theme={null}
create(self, params: dict[str, Any]) -> ModelClientResponseProtocol
```

Parameters:

| Name     | Description               |
| -------- | ------------------------- |
| `params` | **Type:** dict\[str, Any] |






#### message\_retrieval

```python theme={null}
message_retrieval(self, response: ModelClientResponseProtocol) -> Union[list[str], list[Message]]
```

Retrieve and return a list of strings or a list of Choice.Message from the response.
NOTE: if a list of Choice.Message is returned, it currently needs to contain the fields of OpenAI's ChatCompletion Message object,
since that is expected for function or tool calling in the rest of the codebase at the moment, unless a custom agent is being used.

Parameters:

| Name       | Description                           |
| ---------- | ------------------------------------- |
| `response` | **Type:** ModelClientResponseProtocol |