GPT-5.6 terra on Azure OpenAI

GPT-5.6 terra prices on Azure OpenAI for Global, Data Zone and Regional deployments, provisioned throughput (PTU) minimums and throughput, and a worked cost example.

Reference

Price per 1M tokens

USD list prices for Standard (pay per token) and Batch deployments, model version 2026-07-09.

DeploymentInputCached inputOutputBatch in / out
Global not in our data yet
Data Zone not in our data yet
Regional not in our data yet

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%. GPT-5.6 terra is a reasoning model: its hidden reasoning tokens are billed as output.

Provisioned throughput (PTU)

Deployment parameters from Microsoft Learn.

Global / Data Zone minimum
15 PTU, steps of 5
Regional minimum
50 PTU, steps of 50
Input tokens / min per PTU
3,000
1 output token counts as
6 input tokens
Smallest Global deployment
$3,900 / month reserved
Fully used PTU, per 1M tokens
$1.98

"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.

Worked example

1M requests a month, 1,500 input and 300 output tokens each, peak 3× the average, Global deployment.

Standard (Global)—
Provisioned, hourly$58,400
Provisioned, 1-month reservation$20,800
Provisioned, 1-year reservation$17,680

PTUs: peak 226,027 normalized tokens a minute → 80 PTUs, about 31% used on average.

Change the numbers in the calculator
« GPT-5.6 luna GPT-5.6 sol »

Other models

Frequently asked questions

How many PTUs does GPT-5.6 terra need?

At least 15 PTUs on Global or Data Zone (then steps of 5) and 50 on Regional. Each PTU handles 3,000 input tokens a minute, and one output token counts as 6 input tokens.