> 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.

# Type Alias LlmRequest Intercept Fn

> Rewrite or annotate an LLM request before execution.

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`.

<pre />

Rewrite or annotate an LLM request before execution.

Request intercepts can transform the wire request, attach or replace a normalized [`AnnotatedLlmRequest`](/reference/api/rust-library-reference/nemo-relay/codec/request/struct-annotatedllmrequest), or both.

## Parameters

* First argument: Logical provider or model family name.
* Second argument: LLM request to transform.
* Third argument: Optional normalized request annotation to carry forward.

## Returns

A [`Result`](/reference/api/rust-library-reference/nemo-relay/error/type-result) containing the canonical request-intercept outcome. Without a request codec, the returned request is authoritative. With a request codec, its headers remain writable while its content must remain unchanged; provider-body edits must be returned through the required annotation.

## Errors

The callback can return any [`FlowError`](/reference/api/rust-library-reference/nemo-relay/error/enum-flowerror) to abort the request-intercept chain.

## Aliased Type

```rust
pub struct LlmRequestInterceptFn { /* private fields */ }
```