usage object.
The chunk is billed from that object, at the rates on abstract.inc/pricing.
Units
completion_tokens counts the whole chunk the model computed.
A smaller action_horizon returns fewer rows but does not lower completion_tokens.
Picasso costs 0.005 per million cached input tokens, and $0.25 per million actions. These rates apply to both chat completions and WebSocket observations.
Read
usage from each answer. Do not compute it yourself.
A JPEG count is not a token count.
How a chunk is metered
- Before the model runs, the API reserves the chunk’s maximum cost against your monthly spend limit.
- If that reservation would cross the limit, the API refuses the request with HTTP 429
spend_limit_exceeded. The model does not run. - When the answer arrives, the API settles the chunk from its
usage, at the rates fixed when the request was submitted. - A chunk the model never delivered settles at zero. This covers errors, mid-stream failures, and closed sockets.
usage.
Metered cost is enforced against your hard monthly spend limit.