> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/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 optimization

> Re-exported plugin-neutral LLM optimization data types.

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`.

Re-exported plugin-neutral LLM optimization data types.

## Structs

* [LlmOptimizationContribution](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationcontribution): One optimizer's evidence for a change to an LLM call.
* [LlmOptimizationKind](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationkind): Open, forward-compatible optimization classification.
* [LlmOptimizationModel](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationmodel): Model identity used for counterfactual and effective pricing.
* [LlmOptimizationModelTransition](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationmodeltransition): A model change proposed or applied by an optimizer.
* [LlmOptimizationSummary](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationsummary): Close-time accounting attached to the normalized LLM response.
* [LlmOptimizationTokenImpact](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationtokenimpact): Shared token evidence that Relay can aggregate without understanding a plugin payload.
* [LlmOptimizationTokens](/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationtokens): Token quantities retained independently from pricing arithmetic.

## Enums

* [LlmOptimizationEvidenceQuality](/reference/api/rust-library-reference/nemo-relay/codec/optimization/enum-llmoptimizationevidencequality): Whether token evidence was observed directly or estimated.
* [LlmOptimizationSummaryStatus](/reference/api/rust-library-reference/nemo-relay/codec/optimization/enum-llmoptimizationsummarystatus): Completeness of close-time optimization accounting.

## Traits

* [LlmOptimizationPayload](/reference/api/rust-library-reference/nemo-relay/codec/optimization/trait-llmoptimizationpayload): Trait implemented by typed plugin payloads embedded in an optimization contribution.

> Re-exported plugin-neutral LLM optimization data types.

## Docs

- [Struct LlmOptimization Contribution](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationcontribution.md): One optimizer's evidence for a change to an LLM call.
- [Struct LlmOptimization Kind](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationkind.md): Open, forward-compatible optimization classification.
- [Struct LlmOptimization Model](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationmodel.md): Model identity used for counterfactual and effective pricing.
- [Struct LlmOptimization Model Transition](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationmodeltransition.md): A model change proposed or applied by an optimizer.
- [Struct LlmOptimization Summary](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationsummary.md): Close-time accounting attached to the normalized LLM response.
- [Struct LlmOptimization Token Impact](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationtokenimpact.md): Shared token evidence that Relay can aggregate without understanding a plugin payload.
- [Struct LlmOptimization Tokens](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/struct-llmoptimizationtokens.md): Token quantities retained independently from pricing arithmetic.
- [Enum LlmOptimization Evidence Quality](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/enum-llmoptimizationevidencequality.md): Whether token evidence was observed directly or estimated.
- [Enum LlmOptimization Summary Status](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/enum-llmoptimizationsummarystatus.md): Completeness of close-time optimization accounting.
- [Trait LlmOptimization Payload](https://docs.nvidia.com/nemo/relay/v0.8.4/reference/api/rust-library-reference/nemo-relay/codec/optimization/trait-llmoptimizationpayload.md): Trait implemented by typed plugin payloads embedded in an optimization contribution.