What does 1M tokens really cost?
On-Prem vs Cloud GPUs vs APIs
Prices in EUR | Updated January 2026
On-Premise
Your own hardware
€
W
tok/s
€/kWh
Cost per 1M tokens
€3.84
Electricity: €0.28 | Hardware: €3.56
Full Self-Hosting Equation
Elec: (W × €/kWh) / (3.6 × tok/s)
HW: (CGPU × Q × 1000) / (L × U × 3.6 × tok/s)
* Excludes cooling, maintenance, and infrastructure
Cloud GPU
Rented compute
$/hr
tok/s
Cost per 1M tokens
€4.17
Formula
($/hr × Q) / (tok/s × 3600) × 1,000,000
* Based on RunPod, Lambda Labs, Vast.ai pricing
API Providers
Pay per token
Cost per 1M tokens (blended)
€5.00
Input: $3.00/M | Output: $15.00/M
Model Pricing (per 1M tokens)
Input:
$3.00
Output:
$15.00
Monthly Usage Estimate
Set your expected monthly token usage for cost comparison across all options.
M tokens
M tokens
12 M tokens
Comparison Summary
| Option | $ / 1M tokens | Monthly Cost | Savings vs API |
|---|
Assumptions: On-premise includes electricity and hardware amortization (excludes cooling, maintenance, infrastructure).
Cloud GPU pricing based on independent providers. API pricing as of January 2026. Blended API cost uses 5:1 input/output ratio.
Sales Notes
- * Key Benefit 1: Helps prospects understand true TCO of AI infrastructure
- * Key Benefit 2: Shows self-hosted models can be 10-100x cheaper than APIs
- * Key Benefit 3: Demonstrates Dypsis expertise in AI cost optimization
- * Ideal Customer: Companies spending >$10k/month on API calls or considering GPU infrastructure