Introduction
One OpenAI-compatible endpoint that routes across every provider — and your own infrastructure — with governance and observability built in.
Nyuro is a governed routing gateway for LLMs. You point your existing OpenAI-compatible client at one endpoint, and Nyuro decides which model and provider should answer each request — OpenAI, Anthropic, open-weight models, or inference running on your own VPS or GPU node — then streams the answer back in the shape your SDK already understands.
Unlike a plain proxy, every request flows through budgets, policies, and full observability, so platform teams keep control of spend and data while developers keep a single, stable integration.
Why a gateway
One endpoint, every model
Drop-in OpenAI-compatible /v1/chat/completions. Swap a base URL and your
code reaches dozens of models — including local ones.
Routing, not rewrites
Pick by intent (strategy:cost, strategy:quality) or by industry, and
let the router choose. Add a fallback chain so one provider outage never
takes you down.
Governance built in
Per-key and org-wide budgets with graduated alerts and a hard cap. Spend stays inside the limits you set.
Run it on your perimeter
Bring your own provider keys, or route to Ollama / vLLM on your own boxes so sensitive data never leaves your network.
A request in one call
from openai import OpenAI
client = OpenAI(
base_url="https://api.nyuro.ai/v1",
api_key="neu_live_…", # your Nyuro key
)
resp = client.chat.completions.create(
model="auto", # let the router pick
messages=[{"role": "user", "content": "Explain TLS like I'm five."}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.nyuro.ai/v1",
apiKey: process.env.NYURO_API_KEY!, // neu_live_…
});
const resp = await client.chat.completions.create({
model: "auto",
messages: [{ role: "user", content: "Explain TLS like I'm five." }],
});
console.log(resp.choices[0].message.content);curl https://api.nyuro.ai/v1/chat/completions \
-H "Authorization: Bearer neu_live_…" \
-H "Content-Type: application/json" \
-d '{"model": "auto", "messages": [{"role": "user", "content": "Explain TLS like I am five."}]}'New here?
Start with the 5-minute Quickstart — key, first call, routing, streaming, and pointing the gateway at your own VPS.