Glossary
AI API dependency
A model reached over the network - a dependency whose payload you only partly control.
Definition
An AI API dependency is a hosted model service consumed over the network, where the request payload is composed at call time from system instructions, retrieved documents, prior conversation turns and tool output, and where routing to the underlying model, serving tier and region is decided inside the provider’s trust domain.
The problem
It is treated as a larger version of a conventional SaaS API dependency, and it is not. The payload is partly authored by a retrieval step rather than by the application, retries are a cost and quota control as well as a reliability one, and the provider’s status plane and serving plane fail independently.
Why it matters
Each of those differences changes a control. Data classification has to move upstream of the call; failure-domain isolation becomes a reliability requirement with a security benefit; and an availability figure for "the provider" is a measurement of one endpoint, not of the service.
Practical example
RELIASTRA’s public record for OpenAI observes https://status.openai.com from one region. That record is evidence about the status site. It is not evidence about the inference API, and the public page says so rather than letting the vendor name imply otherwise.
How RELIASTRA approaches it
RELIASTRA monitors the externally observable endpoints of AI providers from its own infrastructure, names each endpoint and region explicitly, and keeps the status plane and the serving plane as separate records rather than one vendor-level availability figure.
Know what you depend on. Prove what it did.
RELIASTRA observes the external services your product relies on, attributes their failures, and produces evidence you can act on. Every new organization starts on a 14-day Pro trial.