AI Model API Documentation

One API Key for Claude, GPT, Gemini, MiniMax and all major AI models

Quickstart

1. Complete a purchase on the landing page to get your API Key (shown once – save it immediately).
2. Copy the Base URL and API Key.
3. Follow the client-specific guide below, or verify with curl first.

Verify your API Key

Replace `YOUR_API_KEY` with your real key; you should receive a list of available models:

curl -s "https://api.aibottoken.com/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

Send a test chat request:

curl -s "https://api.aibottoken.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-3-5-sonnet",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 64
  }'

Supported Models

These are our featured models. Run GET /v1/models to see all models available to your Key.

Client Setup

⚠️ Important: Model selection works differently in each client. Most agent-style tools (Claude Code, OpenClaw) do not have a UI model picker — you specify the model via environment variables or config. Only GUI clients (Cherry Studio, Continue) let you pick models from a dropdown.

Claude Code

Claude Code uses the Anthropic subscription by default. To route requests through your own API Key, set these environment variables before launching:

export ANTHROPIC_API_KEY="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.aibottoken.com"
# Then launch Claude Code
claude

Claude Code has no graphical model selector. To switch models, use one of these methods:

1. Method 1 (recommended): Type /model in the Claude Code chat, then enter the Model ID, e.g. anthropic/claude-3-5-sonnet.
2. Method 2: Set a default model via env var before launch: export ANTHROPIC_MODEL="anthropic/claude-3-5-sonnet" (supported in some versions).
3. Method 3: Specify the model field directly in your code or SDK calls.

After launching, send a message in Claude Code, then check the "Usage Logs" in your dashboard to confirm requests are arriving. If they appear, integration is successful.

OpenClaw

Add the following to your OpenClaw Gateway config (~/.openclaw/.env):

ANTHROPIC_API_KEY=YOUR_API_KEY
ANTHROPIC_BASE_URL=https://api.aibottoken.com

OpenClaw selects the model via config — no UI picker needed. Set in ~/.openclaw/.env:

ANTHROPIC_MODEL=anthropic/claude-3-5-sonnet

To use GPT or other models via OpenAI-compatible config:

OPENAI_MODEL=openai/gpt-4o

Cherry Studio / Continue

In the client's "Provider" settings, select "OpenAI Compatible" and fill in:

Base URL: https://api.aibottoken.com/v1
API Key:  YOUR_API_KEY

Cherry Studio and Continue support in-app model selection. Steps:

Cherry Studio:

1. Open Settings → Providers → Create or edit a Provider
2. Set Type to OpenAI Compatible
3. Enter the Base URL and API Key (see below)
4. Click "Fetch Models" or manually enter a Model ID, e.g. anthropic/claude-3-5-sonnet
5. Switch models from the dropdown at the top of the chat view

Continue (~/.continue/config.json):

1. Edit ~/.continue/config.json
2. Add an entry to the models array with the model field set to the Model ID
3. Add multiple entries to switch between them in the UI

{
  "models": [
    {
      "title": "Claude 3.5 Sonnet",
      "provider": "openai",
      "model": "anthropic/claude-3-5-sonnet",
      "apiBase": "https://api.aibottoken.com/v1",
      "apiKey": "YOUR_API_KEY"
    },
    {
      "title": "GPT-4o",
      "provider": "openai",
      "model": "openai/gpt-4o",
      "apiBase": "https://api.aibottoken.com/v1",
      "apiKey": "YOUR_API_KEY"
    },
    {
      "title": "Gemini 2.5 Pro",
      "provider": "openai",
      "model": "google/gemini-2.5-pro",
      "apiBase": "https://api.aibottoken.com/v1",
      "apiKey": "YOUR_API_KEY"
    }
  ]
}

Direct API / SDK

If you call the API directly or use the OpenAI SDK, specify the model field in the request body:

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.aibottoken.com/v1',
})

// Use any supported model ID
const response = await client.chat.completions.create({
  model: 'anthropic/claude-3-5-sonnet',  // or gpt-4o, gemini-2.5-pro, etc.
  messages: [{ role: 'user', content: 'Hello!' }],
})

This is the most flexible approach — you can use a different model on every request with no UI required.

FAQ

I get "model_not_found" – what should I do?

Call GET /v1/models to see the exact model IDs available to your key. Make sure the model parameter matches exactly.

My API Key is only shown once – what if I miss it?

Save it immediately and use the "Download JSON Config" button as a backup. Lost keys require a new purchase.

The usage link redirects to the landing page.

Use the "View Usage" link on the purchase success page – it contains your unique token.

I paid but my key was not displayed.

Wait 5–10 seconds and refresh. If the issue persists, contact support with your Stripe transaction ID.