Billing Units
Understand how text, image, audio, and video models are billed differently.
By modality
| Parameter | Type | Required | Description |
|---|---|---|---|
| Text / chat | tokens | required | Usually billed by input, output, cached, and sometimes reasoning tokens. |
| Embeddings | tokens or input units | required | Usually based on input text tokens or model-specific input units. |
| Image | images / resolution / quality | required | Often billed per generated image, resolution, quality, edit mode, or model unit. |
| Audio | duration / characters / tokens | required | May depend on input audio duration, generated speech length, characters, or tokens. |
| Video | seconds / clips / quality | required | Commonly billed by generated duration, clip count, resolution, or quality tier. |
How usage is reported
The console shows billable usage and charges together with request details such as model, status, and latency. Because reporting units differ by modality and model, review both the usage amount and the unit shown for each record.