---
title: Google Gemini provider setup
description: Configure Google AI Studio Gemini API keys, native wire protocol, and multimodal routing.
---

Zorveus supports Google Gemini models via native Google GenAI wire protocols (`POST /v1beta/models/*`, `POST /vertex_ai/live`) as well as standard OpenAI-compatible `/v1/chat/completions`.

<KeyInserter type="api" label="API Key Tester" placeholder="zrv_your_api_key" />

---

## Configuration

- **Provider ID**: `gemini`
- **Secret kind**: `api_key`
- **Default model policy**: `gemini/*`

Open **Provider Credentials** in the dashboard, select Google Gemini, and enter your Google AI Studio API key.

Manage provider credentials in the Zorveus dashboard under **Provider Credentials**. Application code does not call a provider-credential API. Use a Zorveus API key for inference, not the upstream provider secret.

---

## Inference usage

You can call Gemini models directly using the standard OpenAI client format or through Zorveus SDKs:

<CodeGroup titles={["Python (zorveus)", "TypeScript (@zorveus/sdk)", "cURL"]}>

```python
from zorveus import Zorveus

client = Zorveus(api_key="zrv_your_api_key")

response = client.chat.completions.create(
    model="google/gemini-2.0-flash",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(response.choices[0].message.content)
```

```typescript
import { Zorveus } from "@zorveus/sdk";

const client = new Zorveus({
  apiKey: "zrv_your_api_key",
});

const response = await client.chat.completions.create({
  model: "google/gemini-2.0-flash",
  messages: [{ role: "user", content: "Explain quantum computing in one sentence." }],
});

console.log(response.choices[0].message.content);
```

```bash
curl https://api.zorveus.com/v1/chat/completions \
  -H "Authorization: Bearer zrv_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash",
    "messages": [{"role": "user", "content": "Explain quantum computing in one sentence."}]
  }'
```

</CodeGroup>

---

## Vertex AI integration

For enterprise Google Cloud Vertex AI deployments, use the separate `vertex_ai` provider contract. It takes `service_account_json` with required `project` and `location` configuration fields.