Hormouz AIHormouzSign in

NVIDIA: Switchyard: AI model

Switchyard is an open-source router that switches between models to cut cost from NVIDIA with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
1,000,000 tokens
Pricing:
Variable pricing
Type:
text
  • Streaming
  • Long context

Switchyard is NVIDIA's open-source model router. Instead of answering every request with one model, it sends each one to either a low-cost or a high-capability model, using one of its routing algorithms to decide which the request really needs. By default it picks a popular cheap model and a popular strong one; you can name your own two choices in the models parameter.

It accepts text input and returns text, and supports streaming. Switchyard is commonly used for lowering the cost of mixed workloads, sending simple requests to cheap models, and keeping strong models for the hard ones. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Each request is billed at the price of the model the router chooses for it, shown per request in your usage log. There is no fixed monthly fee. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/switchyard",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorNVIDIA
TypeText
Context window1,000,000 tokens
PricingVariable pricing
APIChat Completions
CapabilitiesStreaming

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/switchyard",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="nvidia/switchyard",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "nvidia/switchyard",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the NVIDIA: Switchyard API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches NVIDIA: Switchyard and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Switchyard cost?
Each request is billed at the price of the model the router chooses for it, shown per request in your usage log. There is no fixed monthly fee.
How do I access Switchyard from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Switchyard compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Switchyard have?
It has a 1M-token context window, accepts text input, and supports streaming.
What is Switchyard good for?
Typical uses are lowering the cost of mixed workloads, sending simple requests to cheap models, and keeping strong models for the hard ones.

Updated 2026-10-13