Adorbis AI Docs
One key. Every model. Auto-routed. Connect any AI tool to Adorbis in under 60 seconds.
⚡ Fastest setup — run this in your terminal
npx adorbis-init
Detects your tools (Cline, Cursor, Claude Code, Aider, Continue, Roo, OpenCode, Zed) and configures them all automatically.
Quick Start
Get your free API key at ai.adorbistech.com — no credit card required. Free plan includes 1,000 credits/month.
Test your key in 30 seconds
curl https://api.adorbistech.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "adorbis/quick",
"messages": [{"role": "user", "content": "Hello!"}]
}'
YOUR_KEY with your Adorbis API key from the dashboard.
Authentication
All requests require a Bearer token in the Authorization header:
Authorization: Bearer adorbis_your_key_here
API keys start with adorbis_ and are shown once at registration. Store them securely — they cannot be retrieved again, but you can create new keys from your dashboard.
Model Departments
Instead of specifying a model, you choose a department. Adorbis routes to the best available model for that task automatically.
| Department | Best for | Speed |
|---|---|---|
adorbis/quick | Fast responses, chat, Q&A | Fastest |
adorbis/coder | Code generation, debugging, review | Fast |
adorbis/auto | Smart routing — best model for your task | Varies |
adorbis/write | Long-form writing, documentation | Medium |
adorbis/reason | Math, logic, multi-step analysis | Slower |
npx adorbis-init
The fastest way to configure any AI coding tool. Works on Windows, Mac, and Linux.
npx adorbis-init
The interactive wizard will:
- Ask for your Adorbis API key and validate it live
- Show all supported tools — select one or multiple
- Ask which department to use (defaults to
adorbis/coder) - Write the correct config file for each selected tool
Supported tools: Cline, Cursor, Continue, Claude Code, Aider, Roo Code, OpenCode, Zed
VS Code Extension
Install from the VS Code Marketplace for a visual setup wizard and live credit balance in your status bar.
- Open VS Code → Extensions (
Ctrl+Shift+X) - Search Adorbis AI
- Click Install
- Open Command Palette (
Ctrl+Shift+P) → Adorbis: Setup - Paste your API key and click Connect
- Click your AI tool to auto-configure it
ext install adorbis.adorbis-ai
The extension adds a live credit balance to your VS Code status bar and auto-configures Cline, Continue, Claude Code, Aider, Roo Code, and OpenCode.
Cline
Add to your VS Code settings.json (Ctrl+Shift+P → Open User Settings JSON):
{
"cline.apiProvider": "openai-native",
"cline.openAiApiKey": "YOUR_ADORBIS_KEY",
"cline.openAiBaseUrl": "https://api.adorbistech.com/v1",
"cline.openAiModelId": "adorbis/coder"
}
Cursor
In Cursor: Settings → Models → Add Model or use the API key settings:
Base URL: https://api.adorbistech.com/v1 API Key: YOUR_ADORBIS_KEY Model: adorbis/coder
Claude Code
Add to ~/.claude/settings.json:
{
"ANTHROPIC_BASE_URL": "https://api.adorbistech.com",
"ANTHROPIC_API_KEY": "YOUR_ADORBIS_KEY"
}
Or set environment variables:
export ANTHROPIC_BASE_URL=https://api.adorbistech.com export ANTHROPIC_API_KEY=YOUR_ADORBIS_KEY
Aider
Add to ~/.aider.conf.yml:
openai-api-key: YOUR_ADORBIS_KEY openai-api-base: https://api.adorbistech.com/v1 model: adorbis/coder
Or pass as flags:
aider --openai-api-key YOUR_ADORBIS_KEY \
--openai-api-base https://api.adorbistech.com/v1 \
--model adorbis/coder
Continue
Add to ~/.continue/config.json under models:
{
"models": [
{
"title": "Adorbis AI",
"provider": "openai",
"model": "adorbis/coder",
"apiKey": "YOUR_ADORBIS_KEY",
"apiBase": "https://api.adorbistech.com/v1"
}
]
}
MCP Servers
Adorbis AI is available as a Model Context Protocol (MCP) server — the standard used by Claude Code, Cursor, Cline, and every modern AI coding tool. Install once and your AI assistant gains access to 7 Adorbis tools automatically.
⚡ What you get after connecting
| Tool | What it does |
|---|---|
adorbis_chat | General AI chat — auto-routes to best model |
adorbis_code | Code generation, debugging, review |
adorbis_reason | Math, logic, multi-step analysis |
adorbis_write | Documentation, articles, emails |
adorbis_balance | Check credits and connection status |
adorbis_models | List all available departments |
adorbis_multi_turn | Multi-turn conversation with history |
Claude Code
Two installation methods depending on your OS:
Windows (recommended)
Clone the repo and point Claude Code to the local dist file:
git clone https://github.com/adorbistech/adorbis-mcp cd adorbis-mcp npm install && npm run build
Then add to ~/.claude.json:
{
"mcpServers": {
"adorbis": {
"command": "node",
"args": ["C:\\path\\to\\adorbis-mcp\\dist\\index.js"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
}
Mac / Linux
claude mcp add adorbis -e ADORBIS_API_KEY=your_key -- npx -y @adorbistech/mcp-server
Or manually in ~/.claude.json:
{
"mcpServers": {
"adorbis": {
"command": "npx",
"args": ["-y", "@adorbistech/mcp-server"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
}
npx -y may fail on Windows. Use the node dist/index.js method above instead.
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"adorbis": {
"command": "node",
"args": ["/path/to/adorbis-mcp/dist/index.js"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
}
Cline
In VS Code, open Cline settings → MCP Servers → Add:
{
"adorbis": {
"command": "node",
"args": ["/path/to/adorbis-mcp/dist/index.js"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
MCP Tool Reference
Once connected, these tools are available inside your AI assistant:
adorbis_chat
General purpose chat. Auto-routes to the best model for your task.
Parameters: message (required) — your message department (optional) — adorbis/quick, adorbis/coder, adorbis/auto, adorbis/write, adorbis/reason system_prompt (optional) — set context for the AI max_tokens (optional) — default 2048
adorbis_code
Code generation, debugging, and review. Routes to the best coding model automatically.
Parameters: task (required) — coding task description code (optional) — existing code to review or build on language (optional) — programming language max_tokens (optional) — default 4096
adorbis_reason
Multi-step reasoning, math, and analysis. Routes to frontier reasoning models.
Parameters: problem (required) — the problem to solve context (optional) — additional data or context max_tokens (optional) — default 4096
adorbis_write
Long-form writing — docs, articles, emails, reports.
Parameters: task (required) — writing task content (optional) — source material tone (optional) — professional, casual, technical, friendly max_tokens (optional) — default 4096
adorbis_balance
Check your API key connection status and credit balance.
No parameters required. Example: "Check my Adorbis balance"
adorbis_models
List all available departments and their use cases.
No parameters required. Example: "What Adorbis departments are available?"
adorbis_multi_turn
Multi-turn conversation with full message history.
Parameters:
messages (required) — array of {role, content} objects
department (optional) — default adorbis/auto
max_tokens (optional) — default 2048
WordPress Plugin
Add an AI chat assistant to any WordPress site with the [adorbis_chat] shortcode.
- Go to Plugins → Add New → Search for Adorbis AI
- Install and Activate
- Go to Settings → Adorbis AI
- Paste your API key and click Save
- Add
[adorbis_chat]to any page or post
Shortcode parameters
[adorbis_chat title="Ask our AI" placeholder="How can I help you?" height="500" department="adorbis/quick" system_prompt="You are a support agent for Acme Store." ]
| Parameter | Default | Description |
|---|---|---|
title | Ask AI | Chat header title |
placeholder | Ask me anything... | Input placeholder |
height | 480 | Chat box height in px |
department | adorbis/quick | AI model department |
system_prompt | (from settings) | Override system prompt |
Wix App
Install Adorbis AI from the Wix App Market to add AI chat to any Wix site.
- Go to Wix App Market and search Adorbis AI
- Click Add to Site
- In your Wix Dashboard → Adorbis AI
- Enter your API key and click Save
- A floating chat bubble appears on every page automatically
Squarespace
Inject the Adorbis widget using a Code Block or via Settings → Advanced → Code Injection.
<script>
window.ADORBIS_CONFIG = {
apiKey: "YOUR_ADORBIS_KEY",
department: "adorbis/quick",
title: "Ask AI",
color: "#1e9ad6",
greeting: "Hi! How can I help you today?",
system: "You are a helpful assistant for this website."
};
</script>
<script src="https://api.adorbistech.com/wix/widget.js"></script>
Paste this in Settings → Advanced → Code Injection → Footer.
Webflow
Add via Project Settings → Custom Code → Footer Code:
<script>
window.ADORBIS_CONFIG = {
apiKey: "YOUR_ADORBIS_KEY",
department: "adorbis/quick",
title: "Ask AI",
color: "#1e9ad6",
greeting: "Hi! How can I help you today?",
system: "You are a helpful assistant for this website."
};
</script>
<script src="https://api.adorbistech.com/wix/widget.js"></script>
Chat Completions
Fully OpenAI-compatible. Drop in as a replacement for any OpenAI SDK usage.
Request
POST https://api.adorbistech.com/v1/chat/completions
{
"model": "adorbis/quick",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is Adorbis AI?"}
],
"max_tokens": 1024
}
Python example
from openai import OpenAI
client = OpenAI(
api_key="YOUR_ADORBIS_KEY",
base_url="https://api.adorbistech.com/v1"
)
response = client.chat.completions.create(
model="adorbis/quick",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
Node.js example
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_ADORBIS_KEY",
baseURL: "https://api.adorbistech.com/v1",
});
const response = await client.chat.completions.create({
model: "adorbis/quick",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
All Endpoints
| Method | Endpoint | Auth | Description |
|---|---|---|---|
| POST | /v1/chat/completions | API Key | OpenAI-compatible chat |
| POST | /v1/messages | API Key | Anthropic-compatible chat |
| GET | /v1/auth/me | JWT | Profile, plan, credits |
| GET | /v1/user/keys | JWT | List active API keys |
| GET | /v1/user/usage | JWT | Request history |
| GET | /v1/pricing/plans | None | All subscription plans |
| POST | /v1/checkout/subscribe | API Key | Start Stripe checkout |
| GET | /health | None | API health check |
Error Codes
| Status | Meaning | Fix |
|---|---|---|
401 | Invalid or missing API key | Check Authorization header format |
402 | Insufficient credits | Top up at ai.adorbistech.com/dashboard |
429 | Rate limit exceeded | Slow down requests or upgrade plan |
500 | Server error | Retry — check status at ai.adorbistech.com |
503 | All models unavailable | Retry in 30 seconds |
Plans & Pricing
| Plan | Price | Credits | Notes |
|---|---|---|---|
| Free | $0 | 1,000 AC/mo | Local models only |
| Starter | $10/mo | 15,000 AC/mo | Full model bouquet |
| Pro | $30/mo | 50,000 AC/mo | Priority routing |
| Business | $100/mo | 200,000 AC/mo | Enterprise support |
1 AC = $0.001 of underlying compute. Upgrade your plan →
