Claude, GPT, and Gemini channels
Create an API key for a Claude, GPT, or Gemini channel. The channel selects the protocol and which model IDs that key can call.
Compare model API pricingClaude, GPT, and Gemini API gateway
AI in IDE is an independent third-party API gateway for Claude, GPT, and Gemini. Buy a subscription or a top-up — each subscription tier has its own quota — then point your own client at the API key.
Install Node.js 22+, then run:
npm install -g @anthropic-ai/claude-code
export ANTHROPIC_BASE_URL='https://api.aiinide.com'
export ANTHROPIC_AUTH_TOKEN="sk-proj-YOUR_KEY"
claudeAn API gateway, not another editor
One account sells access to Claude, GPT, and Gemini. Your editor or CLI stays the client.
Subscriptions and top-ups
Subscription tiers carry different quotas. A top-up is a separate balance. The account setting chooses which balance is spent first.
Compare plansConfigure your own client
Setup guides show the base URL and API key for Claude Code, Cursor, VS Code, and other clients. Editing and agent behavior belong to those clients.
What AI in IDE is
AI in IDE is an independent third-party API gateway. It sells Claude, GPT, and Gemini access as API quota. It does not edit your repository: Claude Code, Cursor, VS Code, and similar tools remain the clients you configure.
Three providers, one account
Claude keys use the AWSQ or CCMAX channel, GPT keys use Codex, and Gemini keys use the Gemini channel. Each key calls only the models that channel accepts.
Subscriptions and top-ups
A subscription tier includes its own quota. A top-up adds a separate balance. By default the top-up is spent first; the account can switch that order.
Your client stays in charge
Put the gateway base URL and API key into the client you already use. Code edits, agents, and IDE features are that client's, not this site's.
How the gateway is used
Pick a channel
AWSQ and CCMAX speak the Claude protocols. Codex speaks the OpenAI Responses protocol. Gemini speaks generateContent. The channel also sets the quota multiplier.
Buy quota
Choose a subscription tier on the pricing page, or add a top-up. The tier's quota is the amount stored for that plan. A top-up is purchased separately, from $50–$2,000 of API quota.
Point a client at the key
Follow the guide for the client you use and set its base URL and API key. The gateway meters the request. The client does the editing.
Terminal
$I'm new to this codebase. Can you explain it to me?
⏺I'll analyze the Excalidraw codebase structure and provide a high-level overview.
⏺Analyze(what: "Excalidraw codebase structure and provide a high-level overview of what it is, its main components, and how they're organized. Focus on understanding the project's purpose, architecture, and key features.")
Excalidraw is an open-source virtual whiteboard application with a hand-drawn style. It's designed for creating diagrams, wireframes, and collaborative drawings.
## Purpose
• Web-based drawing tool with infinite canvas
• Hand-drawn aesthetic with support for shapes, arrows, text
• End-to-end encrypted collaboration
• Works offline as a PWA (Progressive Web App)
## Architecture
The project is organized as a monorepo with these main components:
1. Core Package (packages/excalidraw)
• React component library for embedding Excalidraw in any application
• Handles drawing, rendering, and core functionality
• Uses roughjs for the hand-drawn style
• Includes export capabilities (PNG, SVG)
• Handles drawing, rendering, and core functionality
• Uses roughjs for the hand-drawn style
• Includes export capabilities (PNG, SVG)
2. Web Application (excalidraw-app/)
• Full-featured web app at excalidraw.com
• Built on top of the core package
• Adds collaboration features, local storage, sharing
• Built on top of the core package
• Adds collaboration features, local storage, sharing
3. Support Packages
• common - Shared utilities and constants
• element - Element manipulation and type definitions
• math - Mathematical functions for drawing
• utils - General utility functions
• element - Element manipulation and type definitions
• math - Mathematical functions for drawing
• utils - General utility functions
4. Examples
• Integration examples (Next.js, browser script)
• Shows how to embed Excalidraw in different environments
• Shows how to embed Excalidraw in different environments
5. Documentation (dev-docs/)
• API documentation
• Integration guides
• Component documentation
• Integration guides
• Component documentation
## Key Features
• Real-time collaboration with end-to-end encryption
• Export to various formats (PNG, SVG, JSON)
• Customizable drawing tools
• Dark mode support
• Localization
• Library of shapes and components
• Arrow bindings and labels
• Image support
## Technology Stack
• React for UI
• TypeScript for type safety
• Firebase for collaboration backend
• Jotai for state management
• Vite for development and building
• IndexedDB/LocalStorage for offline storage
The architecture allows for both using Excalidraw as a component in other applications and as a standalone web application with additional features.
$
Choose Your Plan
Flexible pricing plans for developers with different needs, from personal learning to team collaboration, there's always one that suits you
Lite
$12.99/month
Monthly quota
$100
Features
Quota for Claude, GPT and Gemini
Up to 3 API keys in the dashboard
Claude tokens at channel rates
Most Popular
Pro
$69.99/month
Monthly quota
$500
Features
Quota for Claude, GPT and Gemini
Up to 10 API keys in the dashboard
Claude tokens: 10% off channel rates
Team
$222/month
Monthly quota
$2000
Features
Quota for Claude, GPT and Gemini
Up to 50 API keys in the dashboard
Claude tokens: 15% off channel rates
Channels and usage billing
Each API key uses one channel: Claude on AWSQ or CCMAX, GPT on Codex, and Gemini on Gemini. Fable is available only on CCMAX; Mythos is unavailable.
Token usage is calculated from model rates and channel multipliers: AWSQ 0.8×, CCMAX 2×, Codex 0.8×, Gemini 0.5×.
Pro and Team membership discounts apply to Claude token charges after the channel multiplier, not to GPT or Gemini. They reduce quota consumption; they do not add quota or change the purchase price.
View model rates and availabilityAll plans include:
Secure payment
Instant access
Cancel anytime
Compare plan quotas and billing intervals on the pricing page.
View pricingPricing Table
How a channel spends dollar quota
The dollar quota you buy stays the amount you bought. The channel multiplier changes how quickly a request spends it.
Channel affects consumption speed, not your purchased quota
AWSQ consumes your purchased quota at 0.8× speed and supports claude-opus-5-5 and claude-sonnet-5-5. Fable is unavailable.
In our experience, CCMAX is generally more stable and responds faster than AWSQ, often delivering better results with the same model. Choose CCMAX for the experience, or AWSQ for lower cost.
Model
AWSQ · 10 models
Prices are per 1M tokens
| Model | Input | Cache | Output |
|---|---|---|---|
claude-sonnet-5-5 New | $2.00$1.60 | $0.20$0.16 | $10.00$8.00 |
claude-opus-4-7 | $5.00$4.00 | $0.50$0.40 | $25.00$20.00 |
claude-opus-5-5 New | $4.00$3.20 | $0.20$0.16 | $20.00$16.00 |
claude-opus-5 | $5.00$4.00 | $0.50$0.40 | $25.00$20.00 |
claude-sonnet-5 Default | $3.00$2.40 | $0.30$0.24 | $15.00$12.00 |
claude-sonnet-4-6 | $3.00$2.40 | $0.30$0.24 | $15.00$12.00 |
claude-opus-4-8 | $5.00$4.00 | $0.50$0.40 | $25.00$20.00 |
claude-opus-4-6 | $5.00$4.00 | $0.50$0.40 | $25.00$20.00 |
claude-opus-4-5-20251101 | $5.00$4.00 | $0.50$0.40 | $25.00$20.00 |
claude-haiku-4-5-20251001 | $1.00$0.80 | $0.10$0.08 | $5.00$4.00 |
Channel multipliers
AWSQ and Codex use 0.8×, CCMAX uses 2×, and Gemini uses 0.5× of the configured model price. The multiplier changes consumption, not the quota you bought.
Frequently Asked Questions
How the API gateway sells quota, and how to point your own client at a key.
Still have questions?
Contact our support team