> 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.

# Function nemo_relay_llm_request_intercepts

> Run the registered LLM request intercept chain on the given request.

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 />

Run the registered LLM request intercept chain on the given request.

This helper applies only the request-intercept middleware and does not emit lifecycle events or execute the provider callback.

This legacy helper blocks its caller. If called from a Tokio runtime, middleware must not depend on work driven exclusively by that caller thread.

## Parameters

* `name`: Optional provider name as a null-terminated C string. Pass null to use an empty logical name.
* `native_json`: The request payload as a JSON C string representing an `LlmRequest` (`{"headers": {...}, "content": {...}}`).
* `out`: On success, receives the transformed JSON string (caller must free with `nemo_relay_string_free`). The output is a serialized `LlmRequest`.

## Returns

Returns [`NemoRelayStatus::Ok`](/reference/api/rust-library-reference/nemo-relay-ffi/error/enum-nemorelaystatus) on success and writes the transformed serialized request to `out`.

## Safety

All pointers must be valid. `out` must be non-null.