Prompt Compare
Run two system prompts, or two models, on the same inputs and read the answers side by side with their speed and cost.
Your key stays in this browser and is sent only to api.anthropic.com. This page has no server. Each run calls the API once per input and per side: use a key with a spending limit.
Variant A
Variant B
Test inputs
Summary
| Avg. first token | Avg. total time | Output tokens | Total cost |
|---|
Speed and cost are measured. Quality is yours to judge: read the answers below. Costs are estimates from list prices.