open-interpreter/docs/language-models/hosted-models/vertex-ai.mdx

---
title: Google (Vertex AI)
---

## Pre-requisites
* `pip install google-cloud-aiplatform`
* Authentication: 
    * run `gcloud auth application-default login` See [Google Cloud Docs](https://cloud.google.com/docs/authentication/external/set-up-adc)
    * Alternatively you can set `application_default_credentials.json`

To use Open Interpreter with Google's Vertex AI API, set the `model` flag:

<CodeGroup>

```bash Terminal
interpreter --model gemini-pro
interpreter --model gemini-pro-vision
```

```python Python
from interpreter import interpreter

interpreter.llm.model = "gemini-pro"
interpreter.llm.model = "gemini-pro-vision"
interpreter.chat()
```

</CodeGroup>

# Required Environment Variables

Set the following environment variables [(click here to learn how)](https://chat.openai.com/share/1062cdd8-62a1-4aa8-8ec9-eca45645971a) to use these models.

Environment Variable  | Description  | Where to Find  |
--------------------- | ------------ | -------------- |
`VERTEXAI_PROJECT`       | The Google Cloud project ID. | [Google Cloud Console](https://console.cloud.google.com/vertex-ai) |
`VERTEXAI_LOCATION`      | The location of your Vertex AI resources. | [Google Cloud Console](https://console.cloud.google.com/vertex-ai) |

## Supported Models

- gemini-pro
- gemini-pro-vision
- chat-bison-32k
- chat-bison
- chat-bison@001
- codechat-bison
- codechat-bison-32k
- codechat-bison@001