Complete guide to using Google Gemini with Bastio for Gemini 3, 2.5, and 1.5 models.

Google Gemini Integration

Use Google's Gemini models through Google AI Studio or Vertex AI while maintaining Bastio's security protection.

Overview

Bastio offers full support for Google Gemini models, allowing you to:

Access latest models - Gemini 3 Pro, 2.5 Pro/Flash, and 1.5 series
Flexible integration - Support for both AI Studio (API Key) and Vertex AI (OAuth)
Full security coverage - All Bastio security features work with Gemini
Unified API - Use OpenAI-compatible endpoints for Gemini models

Supported Models

Bastio supports the latest Gemini models:

Model	ID	Context	Input/Output Price
Gemini 3 Pro	gemini-3-pro	2M	$2.00/$12.00 per 1M tokens
Gemini 2.5 Pro	gemini-2.5-pro	2M	$1.25/$5.00 per 1M tokens
Gemini 2.5 Flash	gemini-2.5-flash	1M	$0.10/$0.40 per 1M tokens
Gemini 1.5 Pro	gemini-1.5-pro	2M	$1.25/$5.00 per 1M tokens
Gemini 1.5 Flash	gemini-1.5-flash	1M	$0.075/$0.30 per 1M tokens
Gemini 1.5 Flash-8B	gemini-1.5-flash-8b	1M	$0.0375/$0.15 per 1M tokens

Quick Start

Prerequisites

Google Cloud Project or AI Studio account
API Key (for AI Studio) or Service Account (for Vertex AI)
Enabled Vertex AI API (if using Vertex AI)

Step 1: Get Credentials

Option A: Google AI Studio (Recommended for Startups)

Go to Google AI Studio
Click Get API key
Create a key in a new or existing project

Option B: Vertex AI (Recommended for Enterprise)

Go to Google Cloud Console
Create a Service Account with Vertex AI User role
Generate a JSON key for the service account

Configuration

Via Dashboard

Go to Dashboard → Proxies → Create New Proxy
Select Google Gemini as provider
Choose your authentication method:
- API Key: Enter your AI Studio API key
- Vertex AI: Upload your Service Account JSON

Via API

# Create Gemini proxy
curl -X POST https://api.bastio.ai/proxy \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Production Gemini",
    "provider": "google",
    "llm_mode": "byok",
    "model_behavior": "passthrough"
  }'

# Add API Key
curl -X POST https://api.bastio.ai/keys/provider \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "google",
    "key_name": "AI Studio Key",
    "api_key": "your-google-api-key"
  }'

Making Requests

Bastio provides an OpenAI-compatible interface for Gemini, so you can use standard OpenAI SDKs.

Python Example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.bastio.ai/v1/guard/{PROXY_ID}/v1",
    api_key="your-bastio-api-key"
)

response = client.chat.completions.create(
    model="gemini-3-pro",
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ]
)

print(response.choices[0].message.content)

JavaScript Example

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.bastio.ai/v1/guard/{PROXY_ID}/v1',
  apiKey: process.env.BASTIO_API_KEY,
});

const response = await client.chat.completions.create({
  model: 'gemini-2.5-flash',
  messages: [
    { role: 'user', content: 'Hello from Gemini!' }
  ],
});

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

Streaming Example

stream = client.chat.completions.create(
    model="gemini-1.5-pro",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Features & Limitations

Supported Features

Text Generation: Full support for chat completions
Streaming: Real-time token streaming
Function Calling: Support for tools and function calling
Vision: Multimodal support (image input)
System Instructions: Supported via system role messages

Vision Example

response = client.chat.completions.create(
    model="gemini-1.5-flash",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg"
                    }
                }
            ]
        }
    ]
)

Troubleshooting

Invalid API Key

Error: 401 Unauthorized or Invalid API Key Solution: Check that your AI Studio key is active and has not been revoked.

Quota Exceeded

Error: 429 Too Many Requests Solution: Check your Google Cloud or AI Studio quota limits. Gemini models have different rate limits depending on your tier.

Model Not Found

Error: 404 Not Found Solution: Ensure the model ID is correct (e.g., gemini-1.5-pro not gemini-pro-1.5) and available in your region.