No subscriptions to start, no markup games. The same per-token rate whether you send one request or a million — top up and go.
Most pricing pages make you do the math. We don't. Pick a model and drag the sliders — see your bill instantly.
Credit never expires and applies to any model. Pick a pack — we show how long it lasts at the usage you set above. The match for your estimate is highlighted.
Need a custom amount or invoicing? Talk to us →
Usage is billed per token at the same rate on every plan. Higher tiers add limits, support and controls.
| Feature | Free | Pro | Enterprise |
|---|---|---|---|
| Per-token rate | At cost | At cost | Discounted |
| All models & custom providers | ✓ | ✓ | ✓ |
| Streaming & auto-failover | ✓ | ✓ | ✓ |
| Multi-key load-balancing | — | ✓ | ✓ |
| Usage analytics & budgets | — | ✓ | ✓ |
| SSO & team roles | — | — | ✓ |
| SLA & dedicated routing | — | — | ✓ |
| Support | Community | Dedicated |
No. Usage is billed at the underlying model's per-token rate. Paid plans add features and limits, not a per-token markup.
Both. Start with pre-paid credits (no card, no subscription). Pro/Enterprise add a monthly platform fee for higher limits and controls; usage is still pay-as-you-go.
Requests return a 402 until you top up. Enable auto-top-up to avoid interruptions. You're never charged for failed requests.
Yes. Set monthly budgets and per-key limits in the dashboard. We alert you before you hit them.
Cards via Stripe in USD, plus local methods for Vietnam. Invoicing is available on Enterprise.
Get a free API key, integrate in minutes, pay only for what you use.
Get your free API key →