SwitchPoint

SwitchPoint: Router

switchpoint/router

Access Router from SwitchPoint using Puter.js AI API.

Get Started 
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "switchpoint/router"
}).then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "switchpoint/router"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="switchpoint/router",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)

curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "switchpoint/router",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Switchpoint Router is an intelligent LLM routing system by Switchpoint AI that automatically analyzes each request and directs it to the optimal model from a continuously updated library of LLMs.

Rather than being a single model, it acts as a smart proxy — using a cascading approach that attempts lower-cost models first and escalates to more capable ones only when needed. The underlying pool includes models like DeepSeek, Claude, GPT, and Mixtral, selected based on a cost-performance balance.

It offers a 131,072-token context window and flat-rate pricing at $0.85 per million input tokens and $3.40 per million output tokens. As new models are released, the router incorporates them automatically, so your integration stays current without code changes.

Ideal for developers who want cost-efficient inference without manually selecting or switching between models.

Context Window 131K

tokens

Max Output N/A

tokens

Input Cost $0.85

per million tokens

Output Cost $3.4

per million tokens

Release Date Mar 1, 2025

 

Model Playground

Try Router instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat switchpoint/router
SwitchPoint
Chat with Router
Powered by Puter.js

Frequently Asked Questions

How do I use Router?

You can access Router by SwitchPoint through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Router free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Router to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Router?
Pricing for Router is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$0.85
Output$3.4
Who created Router?

Router was created by SwitchPoint and released on Mar 1, 2025.

What is the context window of Router?

Router supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Router API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Router to your app without worrying about API keys or setup.

Read the Docs View Tutorials