Quick Start

Start with the CLI. It writes only ScaleMax-managed client configuration and always reads the live model list from the API.

Step 0: Get a key

Everything below needs a ScaleMax API key (it starts with sm_live_). Start a free trial with no card, or buy API credit or a token pack from ₹250. The key is shown once, so copy it somewhere safe.

Install

Requires Node.js 18.19 or later with npm and npx. Pick your system; the commands differ on Windows.

npm install -g scalemax
scalemax

npm.cmd install -g scalemax
scalemax.cmd

For a one-time run without keeping a global install:

npx scalemax@latest

npx.cmd scalemax@latest

Authenticate

Paste your ScaleMax API key when prompted. The installer validates its primary scope and authenticated effective model catalog, then hides client setup choices that cannot use any model returned for that key.

Enter your ScaleMax API key:

Use the web guided setup

If you prefer a browser checklist, open the ScaleMax guided setup wizard. Sign in once with your key and it shows the matching credit or token URL, provider scope, live key-scoped models, and links to Web Chat, Studio, and client-specific instructions. The web wizard never reveals the key and cannot edit local files; use scalemax setup in a terminal when you want automatic local configuration.

That sign-in is shared across scalemax.pro, docs.scalemax.pro, dashboard.scalemax.pro, web.scalemax.pro, and studio.scalemax.pro. Switching surfaces does not change the active billing identity.

Choose the manual base URL

The CLI detects this automatically. If you are configuring an SDK or client yourself, select the row that matches both the key you bought and that client's protocol.

The protocol decides whether the client field ends in /v1. OpenAI-compatible clients use a base URL ending in /v1. Native Anthropic clients use the origin only, without /v1, because they append /v1/messages themselves. A Claude token key therefore reaches /token/v1/messages when the native client builds its request.

Use the key's matching billing surface and only models returned by its authenticated catalog. A Claude token key and an OpenAI token key are provider-scoped; neither can be swapped onto the other's models.

Claude Desktop is a native Anthropic client with its own third-party inference settings. Follow the Claude Desktop guide; it does not read Claude Code's configuration.

If a key already exists, ScaleMax shows it masked and asks what to do:

✓ Existing ScaleMax configuration detected.

API key:
••••••••••••••••abcd

1. Keep existing key
2. Replace with a new key
3. Remove configuration
4. Exit

Configure Clients

The installer automatically detects these supported configuration targets and can configure one or all targets compatible with the key scope:

• Codex
• Cursor
• Roo Code
• Cline
• Continue
• TRAE SOLO
• Claude Code
• OpenCode
• OpenClaw
• Hermes
• Cherry Studio
• API Code

Claude Desktop on 3P uses a separate managed Gateway configuration. Follow the Claude Desktop guide; it does not read Claude Code settings.

Verify Installation

scalemax doctor

scalemax.cmd doctor

scalemax doctor verifies your API key, live model endpoint, streaming path, usage path, and local client configuration files. Its streaming check sends a small billable request, and a configured client verifier may send an additional small billable request.

scalemax models

scalemax.cmd models

scalemax models fetches the current live model list from the matching authenticated endpoint: /v1/models for API credit or /token/v1/models for an API-token key. Unsupported or disabled models disappear immediately.

Use browser apps

After your access is ready, you can use ScaleMax directly in the browser without configuring a local SDK.

• Web Chat — workspace-scoped browser conversations.
• Studio — prompt-to-website and prompt-to-app generation with previews.

First Chat Example

Select a model from scalemax models, then send a standard OpenAI-compatible request. API-credit users set the first base URL; API-token users set the second. A Claude token key must use a Claude model returned by its catalog.

export SCALEMAX_API_KEY="sm_live_..."
# API-credit key:
export SCALEMAX_BASE_URL="https://api.scalemax.pro/v1"
# API-token key used with an OpenAI-compatible client:
# export SCALEMAX_BASE_URL="https://api.scalemax.pro/token/v1"

curl "$SCALEMAX_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $SCALEMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_AUTHENTICATED_MODEL_ID",
    "max_tokens": 16,
    "messages": [{"role": "user", "content": "Reply with exactly OK"}]
  }'

$env:SCALEMAX_API_KEY = "sm_live_..."
# API-credit key:
$env:SCALEMAX_BASE_URL = "https://api.scalemax.pro/v1"
# API-token key used with an OpenAI-compatible client:
# $env:SCALEMAX_BASE_URL = "https://api.scalemax.pro/token/v1"

@'
{
  "model": "YOUR_AUTHENTICATED_MODEL_ID",
  "max_tokens": 16,
  "messages": [{"role": "user", "content": "Reply with exactly OK"}]
}
'@ | Set-Content -Path body.json

curl.exe "$env:SCALEMAX_BASE_URL/chat/completions" `
  -H "Authorization: Bearer $env:SCALEMAX_API_KEY" `
  -H "Content-Type: application/json" `
  --data-binary "@body.json"

OpenAI SDK Example

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SCALEMAX_API_KEY,
  baseURL: process.env.SCALEMAX_BASE_URL,
});

const response = await client.chat.completions.create({
  model: "YOUR_AUTHENTICATED_MODEL_ID",
  messages: [{ role: "user", content: "Reply with exactly OK" }],
  max_tokens: 16,
});

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

Next steps

• Copy a working request in cURL, Python, or JavaScript.
• Read the full ScaleMax API reference for every endpoint and parameter.
• Check rate limits and error codes before going to production.