USD list prices for Standard (pay per token) and Batch deployments, model version 2025-04-14.
| Deployment | Input | Cached input | Output | Batch in / out |
|---|---|---|---|---|
| Global | $0.100 | $0.025 | $0.400 | $0.050 / $0.200 |
| Data Zone | $0.110 | $0.028 | $0.440 | $0.055 / $0.220 |
| Regional | $0.110 | $0.028 | $0.440 | — |
Source: Azure Retail Prices API, refreshed 15 Oct 2026. Data Zone and Regional prices for eastus2. "list": price not yet confirmed by the weekly refresh; Data Zone list prices are Global + 10%.
Deployment parameters from Microsoft Learn.
"Fully used" is the 1-month Global reservation divided by everything one PTU can process in a month, in normalized tokens. Real deployments are sized for peak and run below that on average.
Prompts over 128K tokens aren't supported on provisioned deployments.
1M requests a month, 1,500 input and 300 output tokens each, peak 3× the average, Global deployment.
| Standard (Global) | $270.00 |
| Batch | $135.00 |
| Provisioned, hourly | $10,950 |
| Provisioned, 1-month reservation | $3,900 |
| Provisioned, 1-year reservation | $3,315 |
PTUs: peak 184,932 normalized tokens a minute → 15 PTUs, about 7% used on average.
Change the numbers in the calculatorOn a Global Standard deployment, $0.100 per million input tokens and $0.400 per million output tokens, with cached input at $0.025 per million. Data Zone costs about 10% more and Batch about half. Prices are USD list prices.
At least 15 PTUs on Global or Data Zone (then steps of 5) and 25 on Regional. Each PTU handles 59,400 input tokens a minute, and one output token counts as 4 input tokens.
A fully used Global PTU on a 1-month reservation costs about $0.100 per million normalized tokens, against $0.100 per million input tokens on Standard. Real deployments are sized for peak load and run well below 100% on average, so Standard is usually cheaper unless the load is high and steady.