> 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 full documentation content, see https://docs.nvidia.com/nemo/relay/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Module response

> Normalized LLM response types produced by response codecs.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi`.

Normalized LLM response types produced by response codecs.

This module defines [`AnnotatedLlmResponse`](/reference/api/rust-library-reference/nemo-relay/codec/response/struct-annotatedllmresponse) and its supporting types for structured, API-agnostic access to LLM response data.

## Structs

* [AnnotatedLlmResponse](/reference/api/rust-library-reference/nemo-relay/codec/response/struct-annotatedllmresponse): Structured view of an LLM response, produced by a response codec from raw JSON API output.
* [ResponseToolCall](/reference/api/rust-library-reference/nemo-relay/codec/response/struct-responsetoolcall): A tool call requested by the model in its response.
* [Usage](/reference/api/rust-library-reference/nemo-relay/codec/response/struct-usage): Token usage statistics from an LLM API response.

## Enums

* [ApiSpecificResponse](/reference/api/rust-library-reference/nemo-relay/codec/response/enum-apispecificresponse): API-specific response data that cannot be normalized across providers.
* [FinishReason](/reference/api/rust-library-reference/nemo-relay/codec/response/enum-finishreason): Normalized reason why the model stopped generating.