> This page is for NeMo Relay, version dev.
> For other versions, use one of these documentation indexes:
> - Latest (v0.11.1) (default): https://docs.nvidia.com/nemo/relay/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/relay/dev/llms.txt
> - v0.11.1: https://docs.nvidia.com/nemo/relay/v0.11.1/llms.txt
> - v0.10.4: https://docs.nvidia.com/nemo/relay/v0.10.4/llms.txt
> - v0.9.4: https://docs.nvidia.com/nemo/relay/v0.9.4/llms.txt
> - v0.8.4: https://docs.nvidia.com/nemo/relay/v0.8.4/llms.txt
> - v0.7.3: https://docs.nvidia.com/nemo/relay/v0.7.3/llms.txt

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

# Struct LlmOptimization Summary

> Host-computed optimization accounting at completed LLM scope closure.

Generated from `cargo doc --no-deps -p nemo-relay-builtins -p nemo-relay-diagnostics -p nemo-relay-logging -p nemo-relay-plugin-host -p nemo-relay-codecs -p nemo-relay -p nemo-relay-runtime -p nemo-relay-model-pricing -p nemo-relay-resource-metrics -p nemo-relay-observability -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`.

<pre />

Host-computed optimization accounting at completed LLM scope closure.

## Fields

### `schema_version: String`

Versions of the optimization report/calculation, not the worker protocol.

### `calculation_version: String`

Arithmetic implementation version.

### `status: i32`

Whether all accounting inputs were available.

### `limitations: Vec<String>`

Machine-readable reasons for partial accounting.

### `baseline_model: Option<LlmOptimizationModel>`

Counterfactual model used for baseline pricing.

### `effective_model: Option<LlmOptimizationModel>`

Model that actually served the terminal response.

### `effective_usage: Option<Usage>`

Usage observed on the effective response.

### `baseline_usage: Option<Usage>`

Counterfactual usage derived from observed usage plus explicit savings.

### `tokens_saved: Option<LlmOptimizationTokens>`

Explicit aggregate token reductions, retained independently from pricing.

### `baseline_cost: Option<CostEstimate>`

Estimated cost for baseline model/usage.

### `actual_cost: Option<CostEstimate>`

Provider-reported or Relay-estimated actual cost.

### `estimated_cost_saved: Option<f64>`

Baseline cost minus actual cost when both share a currency.

### `currency: Option<String>`

Currency for `estimated_cost_saved`.

### `contributions: Vec<LlmOptimizationContribution>`

Ordered, bounded source evidence used by the calculation.

## Implementations

### `impl LlmOptimizationSummary`

<pre />

#### `status`

<pre />

Returns the enum value of `status`, or the default if the field is set to an invalid enum value.

#### `set_status`

<pre />

Sets `status` to the provided enum value.

#### `estimated_cost_saved`

<pre />

Returns the value of `estimated_cost_saved`, or the default value if `estimated_cost_saved` is unset.

#### `currency`

<pre />

Returns the value of `currency`, or the default value if `currency` is unset.

## Trait Implementations

### `impl Clone for LlmOptimizationSummary`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for LlmOptimizationSummary`

<pre />

#### `fmt`

<pre />

### `impl Default for LlmOptimizationSummary`

<pre />

#### `default`

<pre />

### `impl Message for LlmOptimizationSummary`

<pre />

#### `encoded_len`

<pre />

#### `clear`

<pre />

#### `encode`

<pre />

#### `encode_to_vec`

<pre />

#### `encode_length_delimited`

<pre />

#### `encode_length_delimited_to_vec`

<pre />

#### `decode`

<pre />

#### `decode_length_delimited`

<pre />

#### `merge`

<pre />

#### `merge_length_delimited`

<pre />

### `impl Name for LlmOptimizationSummary`

<pre />

#### `NAME`

<pre />

#### `PACKAGE`

<pre />

#### `full_name`

<pre />

#### `type_url`

<pre />

### `impl PartialEq for LlmOptimizationSummary`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl WireValue<LlmOptimizationSummary> for LlmOptimizationSummary`

<pre />

#### `to_wire`

<pre />

#### `from_wire`

<pre />

### `impl StructuralPartialEq for LlmOptimizationSummary`

<pre />