> 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.

# Function nemo_relay_llm_request_new

> Create a new LLM request object. Returns a heap-allocated `FfiLLMRequest` that must be freed with `nemo_relay_llm_request_free`. Returns null on invalid input.

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

<pre />

Create a new LLM request object. Returns a heap-allocated `FfiLLMRequest` that must be freed with `nemo_relay_llm_request_free`. Returns null on invalid input.

## Parameters

* `headers_json`: JSON object of headers/metadata, or null.
* `content_json`: JSON request content payload, or null.

## Safety

All string arguments must be valid null-terminated C strings or null.