> ## 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.oai.gemini.GeminiClient

<h2 id="autogen.oai.gemini.GeminiClient" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">GeminiClient</span>
</h2>

```python theme={null}
GeminiClient(**kwargs)
```

Client for Google's Gemini API.<br />Uses either either api\_key for authentication from the LLM config
(specifying the GOOGLE\_GEMINI\_API\_KEY environment variable also works),
or follows the Google authentication mechanism for VertexAI in Google Cloud if no api\_key is specified,
where project\_id and location can also be passed as parameters. Previously created credentials object can be provided,
or a Service account key file can also be used. If neither a service account key file, nor the api\_key are passed,
then the default credentials will be used, which could be a personal account if the user is already authenticated in,
like in Google Cloud Shell.<br />

<b>Parameters:</b>

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

### Class Attributes

<code class="doc-symbol doc-symbol-heading doc-symbol-attribute" />

#### PARAMS\_MAPPING

<br />

<br />

### Instance Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### cost

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

<b>Parameters:</b>

| Name       | Description |
| ---------- | ----------- |
| `response` |             |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### create

```python theme={null}
create(self, params: dict) -> ChatCompletionExtended
```

<b>Parameters:</b>

| Name     | Description    |
| -------- | -------------- |
| `params` | **Type:** dict |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### get\_usage

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

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

<b>Parameters:</b>

| Name       | Description |
| ---------- | ----------- |
| `response` |             |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### message\_retrieval

```python theme={null}
message_retrieval(self, response) -> list
```

Retrieve and return a list of strings or a list of Choice.Message from the response.<br />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.

<b>Parameters:</b>

| Name       | Description |
| ---------- | ----------- |
| `response` |             |

<br />