Docs · Getting started

Quick start

Make your first request in three steps: get your endpoint and API key, install an SDK, call a model.

1. Get your endpoint and API key

Base URL

https://<your-endpoint>/v1

Visible in the console after sign-in

API Key

YOUR_API_KEY

Create one in the console

Your endpoint is only shown in the console. Every https://<your-endpoint> in these docs is a placeholder — replace it with the address from the console.

2. Install an SDK

pip install --upgrade openai

3. Set environment variables

The official OpenAI SDKs read OPENAI_BASE_URL and OPENAI_API_KEY automatically, so nothing is hard-coded.

# Find your endpoint and API key in the console
export OPENAI_BASE_URL="https://<your-endpoint>/v1"
export OPENAI_API_KEY="YOUR_API_KEY"

4. Send your first request

curl https://<your-endpoint>/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

The response has exactly the OpenAI shape. Next, read:

Chat completions: multi-turn conversations, parameters and the response format
Streaming: receive tokens as they are generated
Anthropic format: call Claude with the Anthropic SDK
Best practices: retries, timeouts, concurrency and cost control

Overview

Authentication