AI Gateway HQ

AI Gateway HQ sits between applications, coding agents and automations and the model providers behind them, routing each request to an approved model and moving to a compatible backup when one is slow, unavailable or over budget.

The distinguishing feature is that budgets are enforcement rather than reporting. Every eligible request reserves its ceiling before a provider can charge, organisation and workload limits sit next to their hard-stop behaviour, and new provider attempts stop at the cap with automatic reload off until separately authorised.

Providers covered include OpenAI, Anthropic, Bedrock and Gemini. Bring-your-own-key usage is billed at the customer own provider rates with no inference markup; the gateway fee is charged separately.

A no-card Test Lab runs policy logic without connecting a provider. Paid tiers run from $0.10 per 1,000 successful requests on prepaid Flex, through Company at $499/month for 2M requests with OIDC, SAML and SCIM, to a Portfolio tier at $1,500/month aimed at private-equity sponsors reporting across portfolio companies.