This guide walks you through creating your first request to Runars.

Prerequisites

You'll need:

A Runars account and organization (sign up at the app)
An API key (generated in your dashboard)
Enough credit balance (top up if needed)

Step 1: Create an organization

If you don't have one already, log in and create a new organization. Each organization has its own API keys, usage tracking, and billing.

Step 2: Generate an API key

Go to Dashboard → API Keys
Click Create API Key
Give your key a descriptive name (e.g., "My App" or "Claude Code (laptop)")
Copy the key—it's shown only once and starts with sk-runars-

Store this key securely. You'll use it to authenticate every request.

Step 3: Top up your balance (if needed)

Runars uses a credit-based billing model. If your organization has no balance, you'll need to add credits:

Go to Dashboard → Payments
Click Add Funds
Choose an amount ($5–$500)
Complete the Helcim checkout

Your credits are now available. Check your current balance and spending in Dashboard → Usage.

Step 4: Make your first request

Using curl (Anthropic-compatible endpoint)

curl https://api.runars.ca/v1/messages \
  -H "x-api-key: $RUNARS_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "glm-5.2",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Hello, Runars! What is 2+2?"
      }
    ]
  }'

Replace $RUNARS_API_KEY with your actual key or set it as an environment variable.

Using the Anthropic SDK

npm install @anthropic-ai/sdk

import Anthropic from "@anthropic-ai/sdk"

const anthropic = new Anthropic({
  baseURL: "https://api.runars.ca",
  apiKey: process.env.RUNARS_API_KEY,
})

const message = await anthropic.messages.create({
  model: "glm-5.2",
  max_tokens: 1024,
  messages: [
    {
      role: "user",
      content: "Hello, Runars! What is 2+2?",
    },
  ],
})

console.log(message.content[0].type === "text" && message.content[0].text)

Using the OpenAI SDK

npm install openai

import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://api.runars.ca/v1",
  apiKey: process.env.RUNARS_API_KEY,
})

const completion = await openai.chat.completions.create({
  model: "glm-5.2",
  max_tokens: 1024,
  messages: [
    {
      role: "user",
      content: "Hello, Runars! What is 2+2?",
    },
  ],
})

console.log(completion.choices[0].message.content)

What's next?

Setting up Claude Code, Codex CLI, or another tool? Head to Install SDKs for environment variable setup.
Curious about endpoints? See the full API reference.
Questions about billing? Check out Pricing and Rate Limits.

Quickstart