Pay for tokens, nothing else
No subscription, no seat fees, no monthly minimum. Add credit, call any live model, and see the cost of every request.
Top up from $5. Credit is spent per token at each model's rate.
- Every live model with one key
- Per-token billing at listed rates
- Card payments via Stripe Checkout
- Unlimited API keys
- Per-request usage log & costs
- Automatic upstream retries
Planning high volume, need invoicing, or want a model that isn't live yet? Tell us what you need and we'll reply with what we can actually offer.
- Model requests
- Volume questions
- Billing & invoices
How credits work
Pick an amount (from $5) in the dashboard and pay with Stripe Checkout. Credit appears once Stripe confirms payment.
Each request deducts prompt tokens × input rate plus completion tokens × output rate.
The usage tab lists every request with model, tokens and cost.
No auto-recharge. At zero balance requests stop until you add more.
Live model rates
What the gateway charges right now, per 1M tokens, with example costs computed from those rates.
| Model | Input | Output | Chat reply | Summarise a 10-page doc | 1M tokens in + 1M out |
|---|---|---|---|---|---|
| Loading live rates… | |||||
Chat reply = 1,000 in / 500 out tokens. Summary = 8,000 in / 600 out. Models marked “Coming soon” in the catalog are not billed because they can't be called yet.
Estimate your bill
What's included — and what isn't (yet)
- OpenAI-compatible Chat Completions & streaming
- Multiple API keys per account
- Usage log with per-request cost
- Stripe card payments
- Subscriptions or bundled plans
- Free tier / free models
- Contractual SLAs
- Team workspaces & SSO