Providers · Beta

Use Groq speed without giving up workload controls.

First-class Groq BYOK with the official OpenAI-compatible base, model-catalog verification, Chat Completions, and Responses routing.

Start in a test environment Read current API behavior

How the connection works

Provider access stays separate from application control.

Match the route to the exact API

Groq documents both Chat Completions and a Responses API, but capability support can differ by model and parameter. The gateway admits only a target that matches the workload's request boundary instead of assuming every catalog entry is interchangeable.

Absorb bursts within a declared ceiling

Per-workload request, token, and concurrency controls prevent one fast client from consuming the shared provider allowance unchecked. Retries and fallback remain bounded so a rate limit cannot turn into an uncontrolled request multiplier.

Keep provider access write-only

The Groq API key stays in the encrypted provider credential boundary. Applications receive scoped AI Gateway HQ keys, while administrators can rotate the upstream key and review route decisions without placing it in source control or shell history.

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 Groq, enter the write-only API key, verify the model catalog, and select a model that supports the route's exact API.

POST /v1/chat/completions POST /v1/responses GET /openai/v1/models connection test

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

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