The Definitive Guide toAI Data Centers
Ask the GuideAccount
CalculatorsInference $/M tokens

Inference $/M tokens

Convert node cost per hour and token throughput into $/M tokens for self-hosted LLM inference, with the LLMflation price-decline context you should underwrite against.

Inference cost per million tokens

$1.9 / M tokens

Self-hosted worked example. Market self-serve fell ~$10 → ~$2.50 / M tokens in a year (LLMflation ~10×/yr) — underwrite inference with a price-decline curve, never flat → Ch 1.8.

All models are open — change any default to your case, then save, share a permalink, or export to CSV. See the full calculator suite.