Home › Docs › Quickstart

Get started

Quickstart

Moving to apicuts is one line of code, and rolling back is the same line. Your endpoint and key are set up with you on a short onboarding call.

Before you start

  • A free 15-minute teardown, where we size your savings from a usage export.
  • Your apicuts endpoint and API key, set up with you on the onboarding call, together with your data region (EU or US).
  • Your existing code. Your prompts, tools and models stay the same.

1. Store your endpoint and key

Environment
export APICUTS_BASE_URL="YOUR_APICUTS_ENDPOINT"
export APICUTS_API_KEY="YOUR_APICUTS_KEY"

2. Point your client at apicuts

apicuts speaks the OpenAI API format, so the official SDKs work as they are. Only the base URL and key change.

Python
import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ["APICUTS_BASE_URL"],  # the only line you change
    api_key=os.environ["APICUTS_API_KEY"],
)

response = client.chat.completions.create(
    model="your-model",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: process.env.APICUTS_BASE_URL, // the only line you change
  apiKey: process.env.APICUTS_API_KEY,
});

const response = await client.chat.completions.create({
  model: "your-model",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);
cURL
curl "$APICUTS_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $APICUTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "your-model", "messages": [{"role": "user", "content": "Hello"}]}'

3. Check the first requests

Responses come back in the same format your code already expects. Within seconds, requests appear in your savings dashboard with model, provider, latency, tokens and cost.

Roll back anytime

Set the base URL back to your provider's. Traffic skips apicuts entirely. No migration, no lock-in, no long-term contract.

Next

Want us to find your 20%?

Book a free 15-minute API cost teardown. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.

Get a Free 15-Minute API Cost Teardown