Quick Start

Get Proxle running in 5 minutes. Cache LLM responses, track costs, and debug production issues.

1. Create an Account

Sign up at proxle.dev/signup. You'll get a default project created automatically.

2. Get Your Proxle API Key

After signing up, go to your Dashboard and navigate to Settings > API Keys. Click Create API Key and copy the key. It starts with pk_live_.

Store this key securely. You won't be able to see it again after closing the dialog.

3. Install the SDK

Python

pip install proxle

JavaScript / TypeScript

npm install proxle

4. Make Your First Request

Python

from proxle import OpenAI

client = OpenAI(
    api_key="sk-your-openai-key",
    proxy_key="pk_live_your-proxle-key"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, world!"}],
    metadata={
        "feature": "quickstart",
        "user_id": "demo"
    }
)

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

JavaScript

import { OpenAI } from "proxle";

const client = new OpenAI({
  apiKey: "sk-your-openai-key",
  proxyKey: "pk_live_your-proxle-key",
});

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello, world!" }],
  metadata: {
    feature: "quickstart",
    userId: "demo",
  },
});

console.log(response.choices[0].message.content);

5. View It in the Dashboard

Go to Dashboard > Requests to see your request logged with:

  • Provider & model used
  • Full request/response payloads
  • Cost estimate in USD
  • Metadata (feature and user attribution)
  • Latency in milliseconds

6. Next Steps

Python SDK