LLM cost estimator
Paste a prompt or drop in token counts and see the monthly cost across 19 models from 10 providers — ranked by price and cross-referenced with each model's quality for your task, so “cheapest” never means “too weak.”
Describe one call
Token counts are approximate — real tokenization is model-specific. Text stays in your browser.
Models scoring below this on chat are dimmed, not hidden.
Estimate results
Add a prompt (or token counts) and a call volume to see costs across every model.
Workload plan Pro
Blend every prompt type you run into one monthly bill, route each to its best-value model, and see what smart routing saves against running a single premium model for everything.
Unlock the workload planner with Pro
Stack unlimited scenarios, get per-scenario routing and export the plan as CSV. The single-call estimator above stays free.
Get notified when prices change
We watch the catalog for list-price changes. Opt in with just an email — no account, unsubscribe in one click anytime.
Estimating from real numbers beats guessing
Import a usage CSV from any provider and WeavePrism turns these estimates into concrete, ranked savings moves grounded in your last 30 days.
Start free