---
title: P11 Streaming LLM API
emoji: ⚡
colorFrom: yellow
colorTo: green
sdk: gradio
sdk_version: 5.29.0
app_file: app.py
pinned: false
---

# P11 · Streaming LLM API + Real-time UX

Token-by-token streaming with TTFT tracking, cancellation, and rate limiting.
Part of the [Staff SRE · AI Engineer Portfolio](https://github.com/amarshiv86).

> Model runs locally — no external API calls.