AI & Models · Integration
Google Vertex AI
Add Google Vertex AI to your product for your customers, and give your AI agents governed access to it.
Embed a Google Vertex AI integration so your customers can run generation and prediction against their own project rather than a key you own, which is what enterprise buyers ask for as soon as their data is involved. fastn handles per-customer credentials, retries, and API upkeep, so model and endpoint choices are configuration per tenant instead of code.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let customers run generation or prediction requests against their own Vertex AI project from inside your product.
Call a customer's deployed endpoint when they have tuned or hosted their own model.
List the models a project has available so users choose inside your product rather than a cloud console.
Keep inference usage and cost per tenant so one customer's volume never lands on another's bill.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent calls a customer's own model endpoint within governed permissions.
An agent inspects which models a project has available before choosing one.
Every inference call is logged per tenant, so model usage is attributable.
Example prompt
List the model endpoints this project has deployed, then run a test prediction against the newest one.
Set up Google Vertex AI in 4 steps
- 01Open the Google Vertex AI connector from your fastn dashboard.
- 02Have each customer authenticate their own Google Cloud project with least-privilege access.
- 03Map the models and endpoints your product may call, then enable actions.
- 04Call them from your product, or expose them to an agent through the MCP server.
Why teams use the Google Vertex AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Google Vertex AI integration without building it. Your customers connect their own Google Vertex AI account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Google Vertex AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed Google Vertex AI connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
Anthropic Claude
Google GeminiWorks well with
Often used alongside
Tools the same teams tend to run next to Google Vertex AI, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeGoogle Vertex AI integration FAQ
How do I add a Google Vertex AI integration to my product?
Enable the Google Vertex AI connector in your fastn dashboard, then let each customer authenticate their own Google Vertex AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Google Vertex AI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Google Vertex AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Google Vertex AI account and only ever sees their own models, requests and outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Google Vertex AI integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent calls a customer's own model endpoint within governed permissions.
Who maintains the Google Vertex AI integration?
fastn does. When Google Vertex AI changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose Google Vertex AI API key and quota does each call use?
Each customer authorises their own Google Vertex AI account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the Google Vertex AI integration?
A common starting point: run generation or prediction requests against their own Vertex AI project from inside your product. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Google Vertex AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Google Vertex AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add Google Vertex AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.