Billing and usage
View model usage and charges in the GetRun console.
View usage
Open usage records in the GetRun console to review model calls by time.
- Model: the model used for the call.
- API: Responses, Messages, Chat Completions, or Images.
- Time: when the call started and completed.
- Usage: input, output, and cached tokens where available.
- Charge: the actual charge for the call.
Retries and charges
Each retry is a new model call and may create additional usage and charges. count_tokens does not incur a model-call charge.