Providers · Beta

Keep each Groq workload inside its own limits.

Connect one Groq project. Give each workload an approved model, an immediate spending limit, rate ceilings, and a fallback.

Create a free workspace Try the no-card Test Lab

How the connection works

How Groq works with the gateway

Check access without inference

The connection test reads Groq's documented model catalog with the encrypted project key. It does not send a prompt or generate tokens merely to prove the key can reach the project.

Stop each workload at its limit

Each app receives a scoped gateway key, dollar budget, request rate, token rate, and concurrency limit. The gateway checks its limits before forwarding a request; Groq's organization and project limits remain the upstream ceiling.

Match the route to the exact API

Groq publishes Chat Completions and a Responses API, but the supported parameters differ. The gateway removes only documented unsupported transport hints and rejects incompatible protocol boundaries instead of treating every request as interchangeable.

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 Groq model, API shape, streaming behavior, rate-limit response, and unsupported Responses parameters before production approval.

Client boundary

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

Each Groq-backed application uses the gateway URL, its scoped workload key, and a stable model alias. Administrators can change an eligible Groq model or API key centrally without distributing the Groq credential to every app.

Implemented boundary

Supported protocols

Select Groq and enter a project-specific API key. The connection test reads the model catalog and does not generate tokens. Then map an eligible model to a stable alias.

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

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

Need the complete client-to-provider path? Follow the tested Codex CLI, AI Gateway HQ, and Groq setup