> 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.

# Trait LlmResponse Codec

> Decode-only codec for LLM API responses.

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

<pre />

Decode-only codec for LLM API responses.

Unlike [`LlmCodec`](/reference/api/rust-library-reference/nemo-relay/codec/traits/trait-llmcodec) (which is bidirectional for requests), response codecs are introspection-only: they parse a raw response into structured form but never need to encode back. This matches the pipeline design where responses are observed, not modified.

## Design

* **Synchronous**: `decode_response` is a pure data transform (JSON parsing), not an I/O operation.
* **`Send + Sync`**: Required for storage in `Arc` behind `RwLock`.
* **Trait object**: Codecs are registered at runtime, stored as `Arc<dyn LlmResponseCodec>`.
* **Fallible**: Returns `Result`; managed call sites may omit annotations on decode failure, while manual lifecycle bindings may surface the error.

## Two-Phase Decode

Implementations should use a two-phase decode pattern:

1. Deserialize raw JSON into API-specific intermediate structs
2. Map intermediate structs into the normalized `AnnotatedLlmResponse`

## Required Methods

#### `decode_response`

<pre />

Parse a raw JSON response into normalized structured form.

Implementations should return `Err` only for genuinely unparseable input.

## Implementors

### `impl LlmResponseCodec for AnthropicMessagesCodec`

<pre />

### `impl LlmResponseCodec for OpenAIChatCodec`

<pre />

### `impl LlmResponseCodec for OpenAIResponsesCodec`

<pre />