Announcing Google Vertex AI Support

Managing multiple AI provider credentials is a hassle. Different API keys, separate billing accounts, varying compliance requirements—it adds up quickly. Today, we're excited to announce full support for Google Vertex AI in Bastio, enabling you to access four AI providers through a single GCP credential.

One Credential, Four Vendors

Google Vertex AI's Model Garden brings together the best AI models from multiple providers under one unified platform:

• Google Gemini: Native Gemini 2.5 Flash, Pro, and the latest 3.0 preview models
• Anthropic Claude: Claude 4.5 Sonnet, Claude 3 Opus, Haiku, and more
• Mistral AI: Mistral Large, Small, Nemo, and Codestral
• Meta Llama: Llama 4 Maverick, Scout, and vision-capable models

One GCP service account. One invoice. Four world-class AI providers.

Why Vertex AI?

For teams already invested in Google Cloud, Vertex AI offers compelling advantages:

• Unified Billing: Consolidate all AI spend in your existing GCP bill
• Compliance: Leverage GCP's certifications (SOC 2, HIPAA, ISO 27001, FedRAMP)
• Network Security: VPC Service Controls, private endpoints, CMEK encryption
• Regional Control: Deploy in specific regions for data residency requirements

With Bastio's integration, you get all these benefits plus our comprehensive security layer.

Enterprise Security Meets GCP

When you route your Vertex AI traffic through Bastio, you get the best of both worlds:

Real-Time Threat Detection

Detect and block prompt injection, jailbreaks, and malicious usage before it reaches your models—regardless of which provider you're using.

PII Protection

Automatically detect and redact sensitive data across all four providers, ensuring consistent compliance with GDPR, HIPAA, and CCPA.

Unified Observability

One dashboard to monitor usage across Google, Anthropic, Mistral, and Meta models. Track costs, analyze threats, and maintain audit logs in a single place.

Getting Started

Setting up Vertex AI with Bastio takes just a few minutes:

1. Create a Service Account: In your GCP project, create a service account with roles/aiplatform.user
2. Enable Partner Models: In Model Garden, enable the models you want to use (Claude, Mistral, Llama)
3. Create a Bastio Proxy: Add your service account JSON and start making requests

from openai import OpenAI

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

# Switch between providers by changing the model name
response = client.chat.completions.create(
    model="gemini-2.5-flash",  # or claude-sonnet-4-5, mistral-large, llama-4-maverick
    messages=[{"role": "user", "content": "Hello from Vertex AI!"}]
)

Available Now

Google Vertex AI support is available today for all Bastio customers. To get started, visit your Dashboard and create a new proxy with the "Google Vertex AI" provider.

For detailed setup instructions including partner model enablement, check out our Vertex AI Documentation.