LLM cost calculator

Enter monthly input and output token volume, choose a cloud model, and compare the estimated API bill with a purchased or rented GPU setup.

Token Usage

Monthly input tokens: 10M0.1M – 1,000M tokensMonthly output tokens: 3M0.1M – 300M tokens

Model

Released 2026-05 · current

GPU

Buy $1,800 · Rent $0.74/hr

Amortize over: 24 months12 – 48 monthsGPU usage: 12h/dayElectricity: $0.12/kWhUS avg: ~$0.12/kWh

Self-hosting recommended

Cloud API

$125

per month

Self-hosted

$94.44

per month

Self-hosting saves $30.56/month

Input tokens (10M @ $5/1M)$50.00

Output tokens (3M @ $25/1M)$75.00

Cloud total$125

GPU amortization (NVIDIA RTX 4090 ÷ 24mo)$75.00

Electricity (450W × 12h/day)$19.44

Local total$94.44

Rent NVIDIA RTX 4090

via RunPod — from $0.74/hr