Published from the same signed price schedule used by billing and the console. Priced in US dollars.
| Model | Input | Output | Billing basis |
|---|---|---|---|
| gpt-5.6-sol | $8.00 | $45.00 | Per 1M tokens |
| gpt-5.6-terra | $3.00 | $18.00 | Per 1M tokens |
| o3 | $3.00 | $12.00 | Per 1M tokens |
These are the input and output token rates used for API billing, not provider acquisition costs or a preview formula. Any separate fee or tax applicable to your account is disclosed in your signed terms before a charge is accepted.
Funds are reserved before a request runs, then settled against actual usage.
The request starts only when your available balance can cover its reservation.
Input and output tokens are taken from the provider's usage report.
Actual usage replaces the reservation. The unused amount returns to your balance.
You pay only for provider-reported usage. Any unused reserved amount returns to your balance.
No. A request starts only when the available balance can cover its reservation.
No. Funded balance remains available until it is used or refunded under the terms.
No. Usage is prepaid from the first request.