- email: Account email
- start_time: Request start timestamp
- end_time: Request end timestamp
- usage_type: Type of usage (e.g., TEXT_COMPLETION_INFERENCE_USAGE)
- accelerator_type: GPU/hardware type used
- accelerator_seconds: Compute time in seconds
- base_model_name: The model used
- model_bucket: Model category
- parameter_count: Model size
- prompt_tokens: Input tokens
- completion_tokens: Output tokens
- Run
firectl export billing-metrics --help
to see available flags (e.g., time range filters). - You can automate exports in cron/jobs and load the CSV into your internal systems.
- The account metrics API (
/v1/accounts/<account-id>/metrics
) currently returns only on-demand and reserved usage. Serverless usage is not included there. Use the CLI export above for serverless.