Version not recorded
Customer safe
Gravitee Cost and Catalog
Per-model cost and token usage are visible without instrumenting the caller
AIAMLLM proxy
Per-model cost and token usage are visible without instrumenting the caller
A per-user token budget can be enforced as a custom policy the gateway loads
A desktop LLM client can be pointed through the gateway without touching the client
A graph governance layer can enrich an LLM prompt with banking context at call time
An agent hitting a live Databricks backend stays inside policy controls
One control plane behaves identically across SaaS, hybrid and self-managed
Multiple AI gateways federate behind one reusable agent
Nothing matches that.