License-Key Auth
One key. Zero config. Your VS Code extension activates instantly — no accounts to manage in-editor.
🚀 Now with GPT-4o, Claude 3.5 Sonnet & Gemini 1.5 Pro — all on one key
Stop Wrestling AI.
Start Shipping.
One license key. Every model. Zero chaos. The only AI gateway that handles billing, limits, and model routing — so you just code.
See It In Action
Your AI Pair Programmer That Actually Gets It
Watch CWAI turn a vague prompt into production-ready code in 12ms. No context switching. No context loss. Just flow.
12345
678910
1112131415
user_auth.py
models.py
views.py
+3
from cwai import CWAI
from fastapi import FastAPI
app = FastAPI()
client = CWAI(license_key="cwai_live_...")
@app.post("/generate")
async def generate(prompt: str):
return await client.complete(prompt)
zsh
bash
fish
~
cwai dev --watch
✓ License validated: cwai_live_abc123...
→ Resolving dependencies...
✓ GPT-4o connected (12ms)
→ Hot reload: ACTIVE
→ File watcher: ACTIVE (user_auth.py, models.py, views.py)
⚠ TypeScript config not found, using defaults
✓ Dev server ready at http://localhost:8000
~
█
Real-Time Usage
LIVE
0
Requests/min
0
Avg Latency (ms)
0
Uptime %
0
Tokens Today
Model Distribution
Why CWAI
Built for Developers Who Ship
Every feature designed to keep you in flow state — not fighting infrastructure.
Flat-Rate, Predictable
Per-tenant token budgets and sliding-window limits keep costs bounded. No surprise bills — ever.
Self-Serve Billing
Stripe-powered checkout, cards, and plan changes — all on your dashboard. No sales calls needed.
Enterprise Security
SOC 2 compliant. Encrypted at rest and in transit. Your code never leaves your control.
Real-Time Analytics
Token usage, latency, costs — all in real time. Know exactly what you're spending.
12+ Models, One Key
GPT-4o, Claude 3.5, Gemini 1.5, Llama 3.1 — switch models without changing code.
0
Models Available
0
ms Avg Latency
0
Uptime SLA
0
Devs Shipping
Social Proof
Loved by Developers Who Ship
Don't take our word for it. These devs stopped wrestling and started shipping.
"CWAI cut our AI integration time from weeks to hours. The license-key model means zero friction for our team — we just code."
"Flat-rate billing changed everything. We went from unpredictable API costs to a fixed monthly budget. Finance loves it."
"The license-key auth is genius. Our developers never leave VS Code. No OAuth flows, no token refresh — it just works."
"Switched from managing 5 different API keys to one license key. My team reclaimed 6 hours/week. That's 300+ hours/year back to shipping."
"The model switching is insane. One parameter change and I'm on Claude instead of GPT. Zero code changes. This is how AI should work."
Questions
Frequently Asked
Everything you need to know before you start.
How does the license key work?
Your license key is a single string (e.g., cwai_live_abc123...) that you paste into the VS Code extension settings. It authenticates your tenant, provisions your token budget, and enables all models instantly. No OAuth, no browser redirects, no token refresh — just paste and code.
What models are included?
All major models: GPT-4o, GPT-4o-mini, Claude 3.5 Sonnet, Claude 3 Haiku, Gemini 1.5 Pro, Gemini 1.5 Flash, Llama 3.1 405B/70B/8B, and more. New models are added within days of release. You switch models with a single parameter — no code changes needed.
How does flat-rate billing work?
You pay a fixed monthly price per tier (Standard, Professional, Enterprise). Each tier includes a generous token budget. If you exceed it, you're rate-limited — not charged extra. No surprise bills, ever. Upgrade or downgrade anytime in your dashboard.
Can I use my own API keys?
Yes! Bring your own keys for any provider (OpenAI, Anthropic, Google, etc.) and CWAI will route requests through them. You get CWAI's enforcement, analytics, and billing on top of your own keys. Perfect for teams with existing enterprise agreements.
Is my code sent to CWAI servers?
No. CWAI acts as a proxy — your code goes from your editor → CWAI gateway → model provider → back to you. We never store your code. We only log metadata: token counts, latency, model used, and success/failure status for your analytics dashboard.
What happens if I exceed my token budget?
You'll be rate-limited (sliding window) until your budget resets or you upgrade. No overage charges, no service interruption for other tenants. You'll see a clear warning in your dashboard and the VS Code extension before you hit the limit.
Ready to Code Without Chaos?
Join 2,800+ developers who've stopped wrestling with AI integration and started shipping.
Start Free — No Credit Card
No credit card required · 14-day free trial · Cancel anytime
SOC 2 Certified
99.9% Uptime SLA
24/7 Support