Pricing
Pay as you go, per token, from a balance you top up. No subscription, no seats, no monthly fee.
Prices
In US dollars, per million tokens. Each request draws from your balance at its model's listed price.
| Model | Input | Cached input | Output | Context | Max output |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 Abliterated Refusals removed 20% off | 1M | 128K | |||
| DeepSeek V4.1 Flash 1017 Refusals kept | $0.08 | $0.01 | $0.32 | 1M | 128K |
Prices are per 1M tokens. Cached input is the price of input tokens served from the provider's cache. Context and max output are in tokens.
For high volume, the Company and Enterprise plans take up to 10% and 15% off DeepSeek V4.1 Flash 1017 Abliterated, with higher rate limits, for companies that spend $1,000+ and $5,000+ a day on usage.
Billing
You pay for what you use, from one balance.
- A prepaid balance
- Top up a balance and pay for the tokens you use. Nothing renews: no subscription, no seats, no monthly fee.
- Input and output
- Counted separately, each at the model's listed price per million tokens.
- Failed requests are free
- Requests that fail upstream are not billed.
- A key for every project
- Give each project its own key, and revoke one at any time. Every key draws from the same balance.
- Pay in crypto
- 160 coins, including BNB, BTC and ETH. Top up from the dashboard.
Questions
Is there a subscription?
No. You top up a balance and pay for the tokens you use. Nothing renews.
How is a request charged?
Input and output tokens are counted separately, each at the model's listed price per million tokens.
Do failed requests cost anything?
No. Requests that fail upstream are not billed.
How do I pay?
With crypto, from the dashboard: pick a coin and its network, then send the exact amount shown.