// Pricing
Simple, transparent pricing
One-time purchases — buy a pack of usage credits, use them, and top up whenever you need more. No subscription, no auto-renewal.
Starter Pack
StarterOne-time purchase
- ✓All open cloud models
- ✓Starter usage credits included
- ✓Up to 1 concurrent deployment
- ✓OpenAI-compatible API
- ✓Email support
Pro Pack
Most popularOne-time purchase
- ✓All open cloud models
- ✓More usage credits included
- ✓Up to 3 concurrent deployments
- ✓OpenAI-compatible API
- ✓Email support
Max Pack
Best valueOne-time purchase
- ✓Everything in Pro
- ✓Maximum usage credits included
- ✓Up to 10 concurrent deployments
- ✓Priority compute
- ✓Priority support
Every pack is a one-time purchase that adds usage credits to your account — no subscription and no automatic renewal. Buy another pack whenever you need more. Credits are drawn down by the compute your workloads actually use. See our Terms of Service and Refund Policy for details.
// FAQ
Frequently asked questions
Is this a subscription?
No. Each pack is a one-time purchase that adds usage credits to your account. Nothing auto-renews — when your credits run low, you simply buy another pack.
What happens when my credits run out?
Your deployments pause until you top up. Buy any pack again to add more credits, or move up to a larger pack for more credits and concurrency. We email you the moment you reach 90% of your balance.
What does each pack include?
Every pack runs all open cloud models; what changes is how many credits you get and how many models you can run at once. Starter runs one at a time, Pro up to three, and Max up to ten — with progressively more credits.
Do I have to bring my own GPUs?
No. Everything runs on managed, GPU-backed cloud infrastructure — nothing for you to provision, rent, or operate.
Which models can I run?
Every open cloud model listed on our Models page — text, vision, tools, and thinking models — plus new ones as they ship. GLM-5.2 is the current highlight.
Do the models support tool calling and agents?
Yes — we expose the tool-calling features each provider ships, ready for agent workflows; the precise behavior comes down to the model itself.
What model weights do you run?
We run each provider’s officially released weights, with hardware acceleration switched on wherever it’s available.
How are credits measured?
Credits are drawn down by the compute your runs actually use — mainly GPU time — rather than a fixed token count. Bigger or heavier models spend them faster. Check your remaining balance anytime in your account.
Do credits expire?
Any expiry terms for purchased credits are disclosed at checkout before you buy. In general, your purchased credits remain available on your account for use on the platform.
Is the API compatible with OpenAI?
Yes. Aim your existing OpenAI client at our base URL and leave your code as-is. The Docs have the details.
Do you train on my data?
No — your prompts and outputs are never used to train models. Our Privacy Policy covers exactly how data is handled.
How do refunds work?
Credits that have already been used are non-refundable unless the law requires otherwise. For unused balances, billing errors, or duplicate charges, contact support — see our Refund Policy.