Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →techdolphinj/cost-model
Calculate the cost of AI model calls and agent operations.
Passed 19 of 21 test cases with the skill, and 12 of 21 without it.
and 9 more in the full report
8 fixed12 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Calculate the monthly compute cost for running 10 million input tokens on a newly released LLM provider named HyperAI, which is not present in our reference snapshot files. We recall HyperAI priced input tokens at $0.50 per million from a recent blog post. Please produce the final cost report.
| Checked | Without skill | With skill |
|---|---|---|
| States that no snapshot exists for HyperAI rather than calculating prices from memory. | Missed | Passed |
| Refuses to issue a binding financial estimate based on recalled figures. | Missed | Passed |
The instructions your model reads when the skill loads.
Turn “which model should we use?” into “what will it cost, can it handle the load, where is it officially available, and how long is the pricing basis valid?”
Model pricing looks like a lookup table. In practice, three mistakes can make an estimate wrong by an order of magnitude:
Use this order: define the scope → assess all three axes → check whether the price is still valid → give the number.
Before giving any number, answer these questions and state the answers in the output. Different scopes can produce estimates that differ by two orders of magnitude.
Default to compute cost, but explicitly list what is excluded. In production content work, compute is often only a single-digit percentage of delivery cost. Presenting compute cost as delivery cost is the primary error this skill prevents.
Account for input price, output price, cache-hit price, and tier conditions.
test cases passed, vs 12 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.