> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Google Vertex AI > Connect Google Vertex AI to Orq.ai for enterprise Gemini access. Configure service account auth, project billing, and data residency controls. Google Vertex AI provides enterprise-grade access to Gemini models with enhanced security, compliance, and control. By connecting Vertex AI to Orq.ai, you get enterprise Gemini capabilities with service account authentication, project-level billing, and data residency controls. ## Setup Your API Key To use Vertex AI with Orq.ai, you need to create a service account with appropriate permissions: 1. Go to [Google Cloud Console](https://console.cloud.google.com) 2. Navigate to **IAM & Admin** > **Service Accounts** 3. Click **Create Service Account** 4. Enter a name (e.g., "orq-vertex-ai") 5. Grant the following roles: * **Service Account Token Creator** * **Vertex AI User** 6. Click **Create and Continue** 7. Click **Done** 1. Find your service account in the list 2. Click the **Actions** menu (three dots) 3. Select **Manage Keys** 4. Click **Add Key** > **Create New Key** 5. Select **JSON** format 6. Click **Create** to download the key file 1. Navigate to **AI Router** > Providers 2. Find **Google Vertex AI** in the list 3. Click the **Configure** button 4. Select **Setup your own API Key** 5. Enter configuration name (e.g., "Vertex AI Production") 6. Paste your service account JSON in the **Deployment JSON** field (see format below) 7. Click **Save** to complete the setup Vertex AI configuration modal ### Deployment JSON Format Your deployment JSON should include the service account credentials, project ID, and region: ```json theme={"theme":{"light":"github-light","dark":"github-dark"}} { "projectId": "my-project-123456", "location": "us-central1", "serviceAccount": { "type": "service_account", "project_id": "my-project-123456", "private_key_id": "afd17083ecd5184b5ca880e70eb84c2e4c382f14", "private_key": "-----BEGIN PRIVATE KEY-----\n...=\n-----END PRIVATE KEY-----\n", "client_email": "vertex-ai@my-project-123456.iam.gserviceaccount.com", "client_id": "000000000000000000000", "auth_uri": "https://accounts.google.com/o/oauth2/auth", "token_uri": "https://oauth2.googleapis.com/token", "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs", "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/vertex-ai%40my-project-123456.iam.gserviceaccount.com", "universe_domain": "googleapis.com" } } ``` **Project ID**: Find your Google Cloud Project ID at the top of the Google Cloud Console. **Location**: Common regions include `us-central1`, `europe-west1`, `asia-northeast1`. Choose based on your data residency requirements. ## Available Models The **AI Router** supports all current Vertex AI Gemini models. Here are the most commonly used: ### Recommended Models | Model | Context | Best For | | ----------------------------- | ------- | ----------------------------- | | `google/gemini-3-pro-preview` | 1M | Latest preview, most advanced | | `google/gemini-2.5-pro` | 1M | Latest stable, most capable | | `google/gemini-2.5-flash` | 1M | Fast, balanced performance | | `google/gemini-2.0-flash-001` | 1M | Stable, reliable | For a complete and up-to-date list of all available Vertex AI models, see [Supported Models](/docs/proxy/supported-models#chat-models). Use `google/gemini-2.5-pro` for the latest stable model, or `google/gemini-2.5-flash` for the best balance of performance and cost. ## Quick Start Access Vertex AI Gemini models through the **AI Router**. ```typescript Typescript theme={"theme":{"light":"github-light","dark":"github-dark"}} import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.ORQ_API_KEY, baseURL: "https://api.orq.ai/v3/router", }); const response = await client.chat.completions.create({ model: "google/gemini-2.5-pro", messages: [ { role: "user", content: "Explain quantum computing in simple terms", }, ], }); console.log(response.choices[0].message.content); ``` ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}} from openai import OpenAI import os client = OpenAI( api_key=os.environ.get("ORQ_API_KEY"), base_url="https://api.orq.ai/v3/router", ) response = client.chat.completions.create( model="google/gemini-2.5-pro", messages=[ { "role": "user", "content": "Explain quantum computing in simple terms", } ], ) print(response.choices[0].message.content) ``` ## Using the AI Router Access Vertex AI Gemini models through the **AI Router** with enterprise-grade security, advanced chat completions, streaming, and intelligent model routing. All Vertex AI models are available with consistent formatting and automatic request logging. Vertex AI models use the provider slug format: `google/model-name`. For example: `google/gemini-2.5-pro` ### Prerequisites Before making requests to the **AI Router**, you need to configure your environment and install the SDKs if you choose to use them. **Endpoint** ``` POST https://api.orq.ai/v3/router/chat/completions ``` **Required Headers** Include the following headers in all requests: ``` Authorization: Bearer $ORQ_API_KEY Content-Type: application/json ``` **Getting your API Key:** 1. Go to [API Keys](/docs/router/api-keys) 2. Click **Create API Key** and copy it 3. Store it in your environment as `ORQ_API_KEY` **SDK Installation** Install the OpenAI SDK for your language (compatible with Vertex AI models): ```bash Node.js/TypeScript theme={"theme":{"light":"github-light","dark":"github-dark"}} npm install openai # or yarn add openai ``` ```bash Python theme={"theme":{"light":"github-light","dark":"github-dark"}} pip install openai ``` If your OpenAI code is already functionning, you only need to change the `base_url` and `api_key` to the router endpoint and `ORQ_API_KEY`. ### Chat Completions Send messages to Vertex AI Gemini models and get intelligent responses: ```typescript Typescript theme={"theme":{"light":"github-light","dark":"github-dark"}} import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.ORQ_API_KEY, baseURL: "https://api.orq.ai/v3/router", }); const response = await client.chat.completions.create({ model: "google/gemini-2.5-pro", messages: [ { role: "system", content: "You are a helpful assistant that explains complex concepts simply.", }, { role: "user", content: "Explain machine learning", }, ], temperature: 0.7, max_tokens: 500, }); console.log(response.choices[0].message.content); ``` ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}} from openai import OpenAI import os client = OpenAI( api_key=os.environ.get("ORQ_API_KEY"), base_url="https://api.orq.ai/v3/router", ) response = client.chat.completions.create( model="google/gemini-2.5-pro", messages=[ { "role": "system", "content": "You are a helpful assistant that explains complex concepts simply.", }, { "role": "user", "content": "Explain machine learning", }, ], temperature=0.7, max_tokens=500, ) print(response.choices[0].message.content) ``` ```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://api.orq.ai/v3/router/chat/completions \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "google/gemini-2.5-pro", "messages": [ { "role": "system", "content": "You are a helpful assistant that explains complex concepts simply." }, { "role": "user", "content": "Explain machine learning" } ], "temperature": 0.7, "max_tokens": 500 }' ``` ### Streaming Stream responses for real-time output and improved user experience: ```typescript Typescript theme={"theme":{"light":"github-light","dark":"github-dark"}} import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.ORQ_API_KEY, baseURL: "https://api.orq.ai/v3/router", }); const stream = await client.chat.completions.create({ model: "google/gemini-2.5-pro", messages: [ { role: "user", content: "Write a short poem about the ocean", }, ], stream: true, }); for await (const chunk of stream) { const content = chunk.choices[0]?.delta?.content || ""; process.stdout.write(content); } console.log("\n"); ``` ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}} from openai import OpenAI import os client = OpenAI( api_key=os.environ.get("ORQ_API_KEY"), base_url="https://api.orq.ai/v3/router", ) stream = client.chat.completions.create( model="google/gemini-2.5-pro", messages=[ { "role": "user", "content": "Write a short poem about the ocean", } ], stream=True, ) for chunk in stream: print(chunk.choices[0].delta.content or "", end="", flush=True) print() ``` ```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://api.orq.ai/v3/router/chat/completions \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "google/gemini-2.5-pro", "messages": [ { "role": "user", "content": "Write a short poem about the ocean" } ], "stream": true }' ``` ### Function Calling Vertex AI Gemini models support function calling for structured interactions: ```typescript Typescript theme={"theme":{"light":"github-light","dark":"github-dark"}} const response = await client.chat.completions.create({ model: "google/gemini-2.5-pro", messages: [ { role: "user", content: "What's the weather in San Francisco?", }, ], tools: [ { type: "function", function: { name: "get_weather", description: "Get the current weather in a location", parameters: { type: "object", properties: { location: { type: "string", description: "The city and state, e.g. San Francisco, CA", }, unit: { type: "string", enum: ["celsius", "fahrenheit"], }, }, required: ["location"], }, }, }, ], }); const toolCall = response.choices[0].message.tool_calls?.[0]; if (toolCall?.type === "function") { console.log(`Calling function: ${toolCall.function.name}`); console.log(`Arguments: ${toolCall.function.arguments}`); } ``` ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}} response = client.chat.completions.create( model="google/gemini-2.5-pro", messages=[ { "role": "user", "content": "What's the weather in San Francisco?", } ], tools=[ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather in a location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"], }, }, "required": ["location"], }, }, } ], ) tool_call = response.choices[0].message.tool_calls[0] print(f"Calling function: {tool_call.function.name}") print(f"Arguments: {tool_call.function.arguments}") ``` ## Automatic Request Logging All requests made through the **AI Router** are automatically logged to your dashboard. You can view: * **Request details**: Model used, tokens, latency * **Cost tracking**: Per-request and aggregate costs * **Error monitoring**: Failed requests with error messages * **Performance metrics**: Response times and throughput No additional configuration is needed—logging happens automatically. ## Reference * [Vertex AI Documentation](https://cloud.google.com/vertex-ai/docs) * [Gemini API Reference](https://ai.google.dev/api/generate-content) * [Service Account Setup](https://cloud.google.com/iam/docs/service-accounts-create) * [Vertex AI Pricing](https://cloud.google.com/vertex-ai/pricing)