GATEWAY REGISTRYAPPNEURALAI & ModelsP2Reference
LLM Gateway
Multi-provider model routing with per-product budgets, response caching, fallbacks, and usage metering, taking over the role of the legacy AI Gateway.
CapabilityAI & Models
OwnerUnassigned
Delivery progressNot tracked yet
LifecycleReference
About this gateway
Purpose and scope
Multi-provider model routing with per-product budgets, response caching, fallbacks, and usage metering, taking over the role of the legacy AI Gateway.
- Runtime
- Not chosen
- Traffic boundary
- Product traffic to model providers
- Integration role
- Model routing, budgets, and fallbacks
- Catalog status
- Planned gateway type — no repository yet
AI brief
What it is, when to use it, how to start
Written by Claude from this gateway's record. Check the details before you rely on them.