Providers · Beta

Control OpenAI usage, cost, and access in one place.

OpenAI-compatible Responses, chat-completions, embeddings, streaming, BYOK, and credential pools.

Start in a test environment Read current API behavior

How the connection works

Provider access stays separate from application control.

Keep the client contract stable

Applications call the gateway's OpenAI-compatible endpoint with a workload key and approved alias. Administrators can change an eligible OpenAI model or account behind that alias without distributing the provider credential to every application.

Put a ceiling on each workload

Apply dollar budgets, request and token rates, concurrency limits, and fallback rules to the workload before it sends production traffic. A provider response never overrides a gateway hard stop.

Retain decision evidence, not prompt bodies

The default receipt records the principal, route decision, provider, model, usage, cost, policy result, and failure reason. The hosted gateway does not persist prompt or response bodies; transient content inspection is a separate, explicit organization control.

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 OpenAI, enter the API key once in the write-only credential form, verify account access without generating tokens, and route applications through a company-owned model alias.

POST /v1/responses 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.