Evaluators
Cost
Track the financial impact of your prompts with accurate cost measurement.
The Cost evaluator calculates costs based on actual token usage returned by the LLM Provider and it’s public pricing.
Examples
OpenAI GPT-4.1
OpenAI GPT-4.1
Anthropic Claude Sonnet 4
Anthropic Claude Sonnet 4
All costs are displayed in USD currency.
Setting Cost Thresholds
1
Select the Cost Evaluator from the action menu.
2
Link a dataset and provide the input to the evaluator using the comparison operator.
less than: Keep costs below your thresholdgreater than: Flag expensive responses above your limitequal to: Match exact cost requirements
3
After executing, you will receive the results for all the prompts that passed or failed the evaluation.