> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/v0.10.0/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Module capability

> Capability registry tracking per-backend and per-model-family supported features.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker`.

Capability registry tracking per-backend and per-model-family supported features.

The registry provides feature discovery so the policy engine knows which optimization intents can be expressed on which backend/model combinations.

## Two-Level Feature Lookup

[`BackendCapabilities`](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-backendcapabilities) stores backend-level defaults plus per-model-family overrides via [`ModelFamilyCapabilities`](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-modelfamilycapabilities). Feature lookups check the model family first, falling back to backend-level if the family is not registered.

## Built-in Defaults

[`CapabilityRegistry::with_defaults()`](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-capabilityregistry) returns a registry pre-populated with known Anthropic and OpenAI capabilities.

## Structs

* [BackendCapabilities](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-backendcapabilities): Capabilities of a specific backend provider.
* [CacheEconomics](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-cacheeconomics): Provider/model-specific cache economics used by the internal planner.
* [CapabilityRegistry](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-capabilityregistry): Registry holding capabilities for all known backends.
* [ModelFamilyCapabilities](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-modelfamilycapabilities): Per-model-family capability overrides within a backend.

## Enums

* [ProviderFeature](/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/enum-providerfeature): Feature that a backend or model family may support.

> Capability registry tracking per-backend and per-model-family supported features.

## Docs

- [Struct Backend Capabilities](https://docs.nvidia.com/nemo/relay/v0.10.0/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-backendcapabilities.md): Capabilities of a specific backend provider.
- [Struct Cache Economics](https://docs.nvidia.com/nemo/relay/v0.10.0/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-cacheeconomics.md): Provider/model-specific cache economics used by the internal planner.
- [Struct Capability Registry](https://docs.nvidia.com/nemo/relay/v0.10.0/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-capabilityregistry.md): Registry holding capabilities for all known backends.
- [Struct Model Family Capabilities](https://docs.nvidia.com/nemo/relay/v0.10.0/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/struct-modelfamilycapabilities.md): Per-model-family capability overrides within a backend.
- [Enum Provider Feature](https://docs.nvidia.com/nemo/relay/v0.10.0/reference/api/rust-library-reference/nemo-relay-adaptive/acg/capability/enum-providerfeature.md): Feature that a backend or model family may support.