Koskamo
Navigation

Estimate AI workload costs

An estimated total cost for a specific AI workload based on input/output token counts and request volume, aiding in budget forecasting.

How it works

Read-onlyFinance and payments

The agent uses the calculate_cost tool to estimate expenses for a hypothetical workload. It inputs parameters such as input tokens, cached input tokens, output tokens, and the number of requests. The tool returns the calculated cost based on current pricing data, allowing the user to forecast spending.

Prompt

Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.

Prompt for Estimate AI workload costs
Calculate the estimated cost for a workload with 1000 input tokens, 500 cached input tokens, 200 output tokens, and 1000 requests using the gpt-4o model.

MCP servers it needs

Source

The vendor page this playbook is drawn from, and the passage that supports it.

calculate_cost Estimate workload cost from input, cached input, output, and request count.
AI Pricing Hub MCP Server | AI Pricing Hub

Each playbook is drawn from the vendor page it cites and reviewed by Koskamo before it is published. Koskamo does not run these servers or your agent: check what each tool will do before you let it act on your accounts.

More playbooks like this