Providers · Beta

Put Google Gemini behind the same workload controls as the rest of your AI stack.

Gemini API keys through Google's OpenAI-compatible HTTPS endpoint.

Start in a test environment Read current API behavior

How the connection works

Provider access stays separate from application control.

Use Google's documented compatibility layer

Existing OpenAI-library clients can call the gateway's conventional endpoint while the provider adapter uses Google's published OpenAI-compatible base. The selected Gemini model still has to support the exact request being sent.

Give each application its own boundary

Issue a separate workload key for each environment or service, then attach its route, budget, request rate, token rate, and concurrency limit. The Google API key remains outside application configuration and source control.

Verify access before spending tokens

The connection test reads the current model catalog rather than generating a response. Administrators can review the credential state and eligible route targets before a client is allowed to send paid inference traffic.

Current shared controls

Status determines what can be configured.

Write-only, encrypted BYOK for implemented provider connections Stable model aliases and protocol-eligible route targets Organization and key budgets, RPM, TPM, and concurrency hard limits Observe, Shadow, Enforce, reason codes, and metadata-only evidence

Beta connections require customer validation against the exact model, payload, streaming mode, region, and provider account before production use.

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 while an administrator changes eligible provider accounts and models.

Implemented boundary

Only documented protocols become eligible.

Choose Google Gemini, enter the API key once in the write-only credential form, verify the current model catalog without generating tokens, and validate the exact chat or embedding model before production use.

POST /v1/chat/completions POST /v1/embeddings GET /v1/models connection test

Compatibility is bounded to the provider's current published interface. Review the provider documentation before approving a production model.