ModelPickr

Estimate a monthly bill from requests per day, input tokens, output tokens, and cache hit rate. Prices are the ModelPickr reference rates from Models.dev. Data last refreshed Oct 14, 2026, 05:43 PM UTC.

Calculator

What will it cost per month?

Pick a model and a workload. The figure is requests per day times 30, priced with that model's reference input, output, and cache-read rates.

Your workload

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

GLM-5.2

$15.00

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Job pages use the same formula with a workload chosen for that job. Start with coding agents.