Pricing
Simple plans for every coding agent
One key for every major model. Pick a monthly plan for a fixed usage budget, or pay per token from a prepaid balance.
Pay as you go
No subscription. Top up a balance and pay per token.
What you get
- All 43 models at list price
- Balance never expires
- Free tokens from the faucet
- Also works as a fallback when a plan runs out
Promo Starter Deepseek
One shared monthly allowance across every model.
Billed monthly
Get startedWhat you get
- $0.56 of model usage every month
- 1 modelsincl. DeepSeek V4.1 Flash
- 250M bonus tokens on DeepSeek V4.1 Flash
- Pay once by VA, QRIS, USDT, PayPal or bank transfer
- Upgrade anytime; the unused part is credited
Compare plans
Swipe sideways to compare all plans
| Feature | Pay as you go | Promo Starter Deepseek |
|---|---|---|
| Price per month | $0 | $0.56 |
| Usage per month | List price | $0.56 |
| Models | 43 | 1 |
| Bonus tokens | — | 250,000,000 |
| Prorated upgrades | — | |
| Prepaid balance |
Questions
Can I change plans later?
Yes. A pricier plan starts right away and the unused part of your current plan is taken off the price. A cheaper plan starts when the current one ends.
What happens when my allowance runs out?
The model stops serving for that window and the API returns a 402 with the exact reset time. Other models stay available. You can opt in to fall back to your prepaid balance.
Do I need to change my code?
No. The gateway speaks the OpenAI chat-completions and Anthropic messages formats. Change the base URL and key, keep your SDK.
Can I see usage per model?
Yes. The console shows allowance and usage per model for the monthly window, plus a request log.
Which providers serve my requests?
You never pick a provider. The router ranks healthy upstreams by price, latency, cache affinity, and quality.