Methodology
How we validate AI API pricing data
Model Cost Comparison is the canonical calculator for workload-based LLM pricing. Rates are last validated Jun 2026. This page documents sources, refresh cadence, and what the calculator does not model.
Data pipeline
- Baseline sync from OpenRouter and official provider pricing pages.
- Cross-validation against external aggregators; mismatches flagged as “Needs review”.
- Weekly GitHub Actions refresh (Mondays) updates validated JSON on this domain.
- Calculator reads ai-provider-pricing-validated.json at build and runtime.
Cost formula
Monthly estimate = (non-cached input tokens × input $/MTok) + (cached input tokens × cached $/MTok when published) + (output tokens × output $/MTok), scaled to messages/month × tokens/message. If a model has no cached rate, cached tokens bill at the normal input rate.
Confidence tiers
- Verified — official source confirmed by at least one external aggregator.
- Estimated — official price only; no external confirmation yet.
- Needs review — mismatch between sources; confirm on the vendor page before billing.
Not included in estimates
Tool-call fees, web search grounding, vector storage, image tokenization, regional multipliers, taxes, and enterprise discounts are not modeled. Add those from your provider console when they apply.
Canonical tool vs article
The interactive calculator lives at modelcostcomparison.com. A long-form article with additional context remains on nicolalazzari.ai and points here as the canonical tool URL.