Cost estimation

The cost estimation is calculated for every chat interaction between the Open WebUI user and the AI model with the following formula:

cost = (prompt_tokens / 1000) * model_prompt_multiplier + (completion_tokens / 1000) * model_completion_multiplier

Each multiplier comes from the pricing.json file, which is structured in a way that each model has a multiplier for the prompt tokens and completion tokens.

If the cost estimation deviates from the actual costs of your environment, you can calculate new multipliers and update your pricing.json.