Providers · Beta

Keep Gemini API spend within hard limits.

Add a Gemini API key once. Give each app an approved model, a hard spending limit, and a compatible fallback.

Create a free workspace Try the no-card Test Lab

How the connection works

How Google Gemini works with the gateway

Keep the OpenAI-compatible request shape

Apps call the gateway's conventional endpoint with a workload key and model alias. The adapter uses Google's published OpenAI-compatible interface, but the selected Gemini model must still support the request and streaming mode.

Set a lower ceiling for each workload

Google applies rate limits by project, not by API key. Give every app or environment its own gateway key, budget, request and token rates, and concurrency limit instead of sharing one project-wide boundary.

Check access before inference

The connection test reads Google's current model catalog without generating a response. Administrators can confirm the API key and eligible route targets before an application sends inference traffic.

Current shared controls

What every supported connection includes

Encrypted BYOK credentials that remain hidden after setup Stable model aliases and compatible route targets Organization and key budgets, rate limits, and concurrency limits Observe, Shadow, and Enforce modes with metadata-only evidence

Test the exact Gemini model, request shape, streaming mode, and API project as part of the production review.

Client boundary

AIGHQ_BASE_URL=https://api.aigatewayhq.com/v1
AIGHQ_API_KEY=from-your-workspace
AIGHQ_MODEL=company-approved-fast

Applications keep a stable gateway URL and model alias for Google Gemini. Administrators can change eligible Gemini API projects and models centrally.

Implemented boundary

Supported protocols

Select Google Gemini and enter the API key once. The connection test reads the current model catalog and does not generate tokens. Finish by assigning each app an approved model alias.

POST /v1/chat/completions OpenAI-compatible streaming POST /v1/embeddings GET /v1/models connection test

Compatibility follows the provider's current published interface. Review the provider documentation before approving Google Gemini for production.