Quickstart

Connect your tools in 2 minutes

ScaleMax is OpenAI- and Anthropic-compatible. Point any client at the ScaleMax base URL, drop in your key, and send the same requests you already know. Pick your client below.

Full docs →

Which base URL?

OpenAI-compatible clients end in /v1. Native Anthropic clients use the origin only and append /v1/messages themselves. Token-pack keys add a /token segment.

Which model ID?

Always use an exact ID from your key's authenticated catalog. Fetch it with GET /v1/models. The samples below use safe defaults you can swap.

curl · OpenAI

OpenAI-compatible Chat Completions over plain HTTP.

API-credit keys use https://api.scalemax.pro/v1. OpenAI token-pack keys use https://api.scalemax.pro/token/v1.

chat.sh

curl "https://api.scalemax.pro/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_SCALEMAX_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "max_tokens": 16,
    "messages": [{"role": "user", "content": "Reply with exactly OK"}]
  }'

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

cURL reference →

curl · Anthropic

Native Anthropic Messages over plain HTTP.

Native Anthropic uses the origin only. API-credit keys use https://api.scalemax.pro; Claude token-pack keys use https://api.scalemax.pro/token. The client appends /v1/messages itself.

messages.sh

curl "https://api.scalemax.pro/v1/messages" \
  -H "Authorization: Bearer YOUR_SCALEMAX_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "max_tokens": 16,
    "messages": [{"role": "user", "content": "Reply with exactly OK"}]
  }'

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Anthropic Messages reference →

OpenAI SDK

Point the official OpenAI SDK at the ScaleMax base URL.

Set the base URL to https://api.scalemax.pro/v1 for API credit, or https://api.scalemax.pro/token/v1 for an OpenAI token pack.

Python

client.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_SCALEMAX_KEY",
    base_url="https://api.scalemax.pro/v1",
)

completion = client.chat.completions.create(
    model="claude-haiku-4-5-20251001",
    messages=[{"role": "user", "content": "Reply with exactly OK"}],
)

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

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Node

client.mjs

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_SCALEMAX_KEY",
  baseURL: "https://api.scalemax.pro/v1",
});

const completion = await client.chat.completions.create({
  model: "claude-haiku-4-5-20251001",
  messages: [{ role: "user", content: "Reply with exactly OK" }],
});

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

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

OpenAI SDK reference →

Anthropic SDK

Point the official Anthropic SDK at the ScaleMax origin.

Set the base URL to https://api.scalemax.pro for API credit, or https://api.scalemax.pro/token for a Claude token pack. Do not append /v1 — the SDK builds /v1/messages itself.

Python

client.py

from anthropic import Anthropic

client = Anthropic(
    api_key="YOUR_SCALEMAX_KEY",
    base_url="https://api.scalemax.pro",
)

message = client.messages.create(
    model="claude-haiku-4-5-20251001",
    max_tokens=16,
    messages=[{"role": "user", "content": "Reply with exactly OK"}],
)

print(message.content[0].text)

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Node

client.mjs

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "YOUR_SCALEMAX_KEY",
  baseURL: "https://api.scalemax.pro",
});

const message = await client.messages.create({
  model: "claude-haiku-4-5-20251001",
  max_tokens: 16,
  messages: [{ role: "user", content: "Reply with exactly OK" }],
});

console.log(message.content[0].text);

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Claude Code reference →

VS Code Continue

Continue talks to ScaleMax over OpenAI-compatible Chat Completions.

Continue uses the Chat Completions transport. Keep useResponsesApi: false — this route is not a Responses or tool-calling endpoint.

Store the key outside the config

~/.continue/.env

SCALEMAX_API_KEY=YOUR_SCALEMAX_KEY

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Add the model

~/.continue/config.yaml

models:
  - name: ScaleMax Claude Haiku 4.5
    provider: openai
    model: claude-haiku-4-5-20251001
    apiBase: https://api.scalemax.pro/v1
    apiKey: ${{ secrets.SCALEMAX_API_KEY }}
    useResponsesApi: false
    roles:
      - chat
      - edit

Continue reference →

Cursor

Add a custom OpenAI-compatible model in Cursor's model settings.

Cursor Settings → Models → add a custom OpenAI-compatible model. Use the custom form for Claude models too, not the built-in Anthropic login.

Custom model fields

text

Base URL:  https://api.scalemax.pro/v1
API key:   YOUR_SCALEMAX_KEY
Model:     gpt-5.6-terra   (or another exact catalog ID, e.g. fable-5)

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Equivalent settings entry

settings.json

{
  "openai.baseURL": "https://api.scalemax.pro/v1",
  "openai.apiKey": "YOUR_SCALEMAX_KEY"
}

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Cursor reference →

Claude Code

Route Claude Code through the native Anthropic Messages gateway.

Use the origin only in ANTHROPIC_BASE_URL — https://api.scalemax.pro for API credit, https://api.scalemax.pro/token for a Claude token pack. Never append /v1.

Try it in this terminal

terminal

export ANTHROPIC_BASE_URL="https://api.scalemax.pro"
export ANTHROPIC_AUTH_TOKEN="YOUR_SCALEMAX_KEY"
export ANTHROPIC_MODEL="claude-opus-5"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="claude-haiku-4-5-20251001"
claude

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Keep it for every new terminal

~/.zshrc

# macOS (zsh). On Linux with bash, use ~/.bashrc instead of ~/.zshrc.
cat >> ~/.zshrc <<'EOF'
export ANTHROPIC_BASE_URL="https://api.scalemax.pro"
export ANTHROPIC_AUTH_TOKEN="YOUR_SCALEMAX_KEY"
export ANTHROPIC_MODEL="claude-opus-5"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="claude-haiku-4-5-20251001"
EOF
# Open a new terminal, then run: claude

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Claude Code reference →

Codex CLI

Codex connects through the OpenAI-compatible Responses provider.

wire_api = "responses" is required. API-credit keys use https://api.scalemax.pro/v1; OpenAI token-pack keys use https://api.scalemax.pro/token/v1.

Provider config

~/.codex/config.toml

model = "gpt-5.6-terra"
model_provider = "scalemax"

[model_providers.scalemax]
name = "ScaleMax"
base_url = "https://api.scalemax.pro/v1"
wire_api = "responses"
requires_openai_auth = true

printf "%s" "YOUR_SCALEMAX_KEY" | codex login --with-api-key

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Codex reference →

Roo Code

Add ScaleMax as an OpenAI Compatible profile in Roo Code for VS Code.

Choose the OpenAI Compatible provider, never OpenAI Codex or its login. API-credit keys use https://api.scalemax.pro/v1; token-pack keys use https://api.scalemax.pro/token/v1.

In VS Code, open Roo Code → Settings → API Provider and create a new profile.
Choose OpenAI Compatible and fill in the fields below, then save.
Run tasks in Code or Debug mode. Ask and Architect modes cannot run terminal commands, so Roo says terminal tools are not available there. Switch modes; nothing is wrong with your key.

Profile fields

text

API provider:  OpenAI Compatible
Base URL:      https://api.scalemax.pro/v1
API key:       YOUR_SCALEMAX_KEY
Model ID:      gpt-5.6-terra   (or another exact catalog ID, e.g. claude-opus-5)
Streaming:     on

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Roo Code reference →

Cline

Point the Cline VS Code extension’s OpenAI Compatible provider at ScaleMax.

API-credit keys use https://api.scalemax.pro/v1; token-pack keys use https://api.scalemax.pro/token/v1. Paste only the raw key: no "Bearer " prefix and no custom Authorization header.

Open Cline settings and choose the OpenAI Compatible API provider.
Fill in the fields below, leave custom headers empty, save, and reload VS Code.
Switch Cline to Act mode to let it edit files and run the task. Plan mode only reads and plans; nothing is wrong with your key.

Provider fields

text

API provider:  OpenAI Compatible
Base URL:      https://api.scalemax.pro/v1
API key:       YOUR_SCALEMAX_KEY
Model ID:      gpt-5.6-terra   (or another exact catalog ID)

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Cline reference →

OpenCode

API-credit keys use https://api.scalemax.pro/v1; token-pack keys use https://api.scalemax.pro/token/v1. The key lives in its own file, never in opencode.json.

Store the key outside the config

store-key.sh

umask 077
mkdir -p "$HOME/.config/opencode"
printf "%s\n" "YOUR_SCALEMAX_KEY" > "$HOME/.config/opencode/scalemax.key"

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Add the provider (merge into existing providers)

~/.config/opencode/opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "model": "scalemax/gpt-5.6-terra",
  "small_model": "scalemax/gpt-5.6-luna",
  "provider": {
    "scalemax": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "ScaleMax",
      "options": {
        "baseURL": "https://api.scalemax.pro/v1",
        "apiKey": "{file:~/.config/opencode/scalemax.key}"
      },
      "models": {
        "gpt-5.6-terra": { "name": "GPT 5.6 Terra" },
        "gpt-5.6-luna": { "name": "GPT 5.6 Luna" }
      }
    }
  }
}

OpenCode reference →

Cherry Studio

Add ScaleMax as an OpenAI-compatible custom provider.

Choose the OpenAI Compatible provider. API-credit keys use https://api.scalemax.pro/v1; token-pack keys use https://api.scalemax.pro/token/v1.

Provider fields

text

Provider:  OpenAI Compatible
API host:  https://api.scalemax.pro/v1
API key:   YOUR_SCALEMAX_KEY
Model:     fable-5   (or another exact ID from /v1/models)

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Cherry Studio reference →

n8n

Wire n8n's AI Agent to ScaleMax through the OpenAI Chat Model sub-node.

Set the credential Base URL to https://api.scalemax.pro/v1 for API credit, or https://api.scalemax.pro/token/v1 for an OpenAI token pack. Do not append /chat/completions — n8n adds the path itself.

Add an AI Agent node and attach "OpenAI Chat Model" as its Chat Model sub-node. Do not use the standalone OpenAI node (v2): a custom Base URL passes its credential test but 404s at runtime (n8n issue #21651); the AI Agent sub-node handles custom base URLs correctly.
On the sub-node, create a new OpenAI credential with the fields below.
If the model dropdown is empty — it usually is for custom providers — switch the Model field to "By ID" and type an exact catalog ID from the list below.
Claude needs no separate node: type a claude-* ID in the same OpenAI Chat Model node and ScaleMax translates the request.
For anything the chat node can't do, send the request yourself from an HTTP Request node — settings and body below.

Step 2 · OpenAI credential fields

text

API Key:   YOUR_SCALEMAX_KEY
Base URL:  https://api.scalemax.pro/v1

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

Step 3 · Model IDs to type

text

claude-haiku-4-5-20251001
gpt-5.6-sol
claude-opus-5
claude-sonnet-5
deepseek-v4-flash   (requires a DeepSeek-entitled key — other keys get a scope error)

Step 5 · Fallback: HTTP Request node

text

Method:          POST
URL:             https://api.scalemax.pro/v1/chat/completions
Authentication:  Generic Credential Type → Header Auth
Header name:     Authorization
Header value:    Bearer YOUR_SCALEMAX_KEY
Body:            JSON (body.json below)

Replace YOUR_SCALEMAX_KEY with your ScaleMax key.

body.json

{
  "model": "claude-haiku-4-5-20251001",
  "messages": [{ "role": "user", "content": "Reply with exactly OK" }]
}

Need account help or a key? Contact support.