List model catalog

Returns the catalog of supported models, optionally filtered by provider. When gateway_id and registry_id are supplied, the list is narrowed to the models that registry’s credentials can actually use: AWS Bedrock registries are checked against the AWS control plane (on-demand base models and system-defined inference profiles), and every other provider is checked against its authenticated models listing (so org-restricted API keys are respected). An Azure registry lists its resource’s deployments: the slug is the deployment name a request must send, and the call fails instead of offering catalog names that would answer DeploymentNotFound — 404 when the registry does not exist, 422 when it is not an Azure registry or Azure rejects its endpoint or credentials, 502 when Azure does not answer. A provider the catalog does not carry — a self-hosted openai_compatible endpoint — is listed live from the registry itself instead of returning nothing. For every other provider, malformed ids, providers without a listing, and unreachable provider endpoints are ignored and yield the full catalog.