Azure Speed Test

Prices by deployment type

All rates are USD per 1 million tokens. Each row uses its own deployment type and published price regions. A range reflects regional differences within that type. Missing prices mean no published meter in this snapshot; they do not mean free usage. A retail price does not guarantee deployment availability or quota.

GPT-5.2 OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Batch $0.9625 $7.70 $0.09625 Not published 13
Data Zone Priority $3.85 $30.80 $0.385 Not published 13
Data Zone Standard $1.925 - $2.10 $15.40 - $16.80 $0.1925 - $0.21 Not published 22
Global Batch $0.875 $7.00 $0.0875 Not published 24
Global Priority $3.50 $28.00 $0.35 Not published 24
Global Standard $1.75 $14.00 $0.175 Not published 24

The tables contain only this OpenAI listing. Other providers, versions and similarly named Azure products can have different meters. Some token categories may be missing in individual regions; expand the regional tables for exact coverage.

How token costs are calculated

For each region and deployment type, multiply each token category by its matching rate, then divide the sum by 1,000,000. Monthly estimates multiply that request cost by the number of requests. Ranges use complete workloads priced in each region, so input and output prices from different regions are never combined.

Request cost = (uncached input tokens × input rate + cached input tokens × cached input rate + cache-write input tokens × cache-write rate + output tokens × output rate) / 1,000,000.

The examples below use zero cache writes. The cached example assumes half of the input tokens are eligible cache reads on every request; actual cache hit rates and any cache creation charges depend on the deployment. Missing cache rates are not replaced with ordinary input rates. Estimates cover these token meters only, before taxes, negotiated discounts and any separate hosting, tools, media or provisioned-capacity charges.

Data Zone Batch prices and cost examples

Data Zone processing
Inference data is processed within the Microsoft-specified US, EU, or APAC data zone.
Asynchronous Batch
Batch meters cover asynchronous jobs. Microsoft documents Global and Data Zone Batch at a 50% discount, with a 24-hour target for Global Batch; model support varies.

Example workload: 3,000 input and 1,000 output tokens per request, with 10,000 requests per month.

No cached input

Per request
$0.0105875
Per month
$105.875

Across 13 published price regions.

Customize workload or price region for Data Zone Batch, No cached input

50% cached input

Per request
$0.00928813
Per month
$92.88125

Across 13 published price regions.

Customize workload or price region for Data Zone Batch, 50% cached input
View 13 region prices for Data Zone Batch

Price region identifies the Azure retail meter; processing location follows the deployment type described above. Dates show the latest effective meter in each row, not when prices were last checked. All token rates are USD per 1 million tokens.

GPT-5.2 Data Zone Batch exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Central UScentralus$0.9625 $7.70 $0.09625 Not published
East USeastus$0.9625 $7.70 $0.09625 Not published
East US 2eastus2$0.9625 $7.70 $0.09625 Not published
France Centralfrancecentral$0.9625 $7.70 $0.09625 Not published
Germany West Centralgermanywestcentral$0.9625 $7.70 $0.09625 Not published
North Central USnorthcentralus$0.9625 $7.70 $0.09625 Not published
Poland Centralpolandcentral$0.9625 $7.70 $0.09625 Not published
South Central USsouthcentralus$0.9625 $7.70 $0.09625 Not published
Spain Centralspaincentral$0.9625 $7.70 $0.09625 Not published
Sweden Centralswedencentral$0.9625 $7.70 $0.09625 Not published
West Europewesteurope$0.9625 $7.70 $0.09625 Not published
West USwestus$0.9625 $7.70 $0.09625 Not published
West US 3westus3$0.9625 $7.70 $0.09625 Not published

Data Zone Priority prices and cost examples

Data Zone processing
Inference data is processed within the Microsoft-specified US, EU, or APAC data zone.
Priority pay-per-token
Priority processing uses pay-as-you-go token meters for faster responses. Model and deployment support varies.

Example workload: 3,000 input and 1,000 output tokens per request, with 10,000 requests per month.

No cached input

Per request
$0.04235
Per month
$423.50

Across 13 published price regions.

Customize workload or price region for Data Zone Priority, No cached input

50% cached input

Per request
$0.0371525
Per month
$371.525

Across 13 published price regions.

Customize workload or price region for Data Zone Priority, 50% cached input
View 13 region prices for Data Zone Priority

Price region identifies the Azure retail meter; processing location follows the deployment type described above. Dates show the latest effective meter in each row, not when prices were last checked. All token rates are USD per 1 million tokens.

GPT-5.2 Data Zone Priority exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Central UScentralus$3.85 $30.80 $0.385 Not published
East USeastus$3.85 $30.80 $0.385 Not published
East US 2eastus2$3.85 $30.80 $0.385 Not published
France Centralfrancecentral$3.85 $30.80 $0.385 Not published
Germany West Centralgermanywestcentral$3.85 $30.80 $0.385 Not published
North Central USnorthcentralus$3.85 $30.80 $0.385 Not published
Poland Centralpolandcentral$3.85 $30.80 $0.385 Not published
South Central USsouthcentralus$3.85 $30.80 $0.385 Not published
Spain Centralspaincentral$3.85 $30.80 $0.385 Not published
Sweden Centralswedencentral$3.85 $30.80 $0.385 Not published
West Europewesteurope$3.85 $30.80 $0.385 Not published
West USwestus$3.85 $30.80 $0.385 Not published
West US 3westus3$3.85 $30.80 $0.385 Not published

Data Zone Standard prices and cost examples

Data Zone processing
Inference data is processed within the Microsoft-specified US, EU, or APAC data zone.
Standard pay-per-token
Input and output usage is billed by token. Standard deployments provide best-effort throughput; reserved PTU pricing is separate.

Example workload: 3,000 input and 1,000 output tokens per request, with 10,000 requests per month.

No cached input

Per request
$0.021175 - $0.0231
Per month
$211.75 - $231.00

Across 22 published price regions.

Customize workload or price region for Data Zone Standard, No cached input

50% cached input

Per request
$0.01857625 - $0.020265
Per month
$185.7625 - $202.65

Across 22 published price regions.

Customize workload or price region for Data Zone Standard, 50% cached input
View 22 region prices for Data Zone Standard

Price region identifies the Azure retail meter; processing location follows the deployment type described above. Dates show the latest effective meter in each row, not when prices were last checked. All token rates are USD per 1 million tokens.

GPT-5.2 Data Zone Standard exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$2.10 $16.80 $0.21 Not published
Central Indiacentralindia$2.10 $16.80 $0.21 Not published
Central UScentralus$1.925 $15.40 $0.1925 Not published
East Asiaeastasia$2.10 $16.80 $0.21 Not published
East USeastus$1.925 $15.40 $0.1925 Not published
East US 2eastus2$1.925 $15.40 $0.1925 Not published
France Centralfrancecentral$1.925 $15.40 $0.1925 Not published
Germany West Centralgermanywestcentral$1.925 $15.40 $0.1925 Not published
Japan Eastjapaneast$2.10 $16.80 $0.21 Not published
Japan Westjapanwest$2.10 $16.80 $0.21 Not published
Jio India Westjioindiawest$2.10 $16.80 $0.21 Not published
Korea Centralkoreacentral$2.10 $16.80 $0.21 Not published
North Central USnorthcentralus$1.925 $15.40 $0.1925 Not published
Poland Centralpolandcentral$1.925 $15.40 $0.1925 Not published
South Central USsouthcentralus$1.925 $15.40 $0.1925 Not published
South Indiasouthindia$2.10 $16.80 $0.21 Not published
Southeast Asiasoutheastasia$2.10 $16.80 $0.21 Not published
Spain Centralspaincentral$1.925 $15.40 $0.1925 Not published
Sweden Centralswedencentral$1.925 $15.40 $0.1925 Not published
West Europewesteurope$1.925 $15.40 $0.1925 Not published
West USwestus$1.925 $15.40 $0.1925 Not published
West US 3westus3$1.925 $15.40 $0.1925 Not published

Global Batch prices and cost examples

Global processing
Inference data may be processed in any Azure region.
Asynchronous Batch
Batch meters cover asynchronous jobs. Microsoft documents Global and Data Zone Batch at a 50% discount, with a 24-hour target for Global Batch; model support varies.

Example workload: 3,000 input and 1,000 output tokens per request, with 10,000 requests per month.

No cached input

Per request
$0.009625
Per month
$96.25

Across 24 published price regions.

Customize workload or price region for Global Batch, No cached input

50% cached input

Per request
$0.00844375
Per month
$84.4375

Across 24 published price regions.

Customize workload or price region for Global Batch, 50% cached input
View 24 region prices for Global Batch

Price region identifies the Azure retail meter; processing location follows the deployment type described above. Dates show the latest effective meter in each row, not when prices were last checked. All token rates are USD per 1 million tokens.

GPT-5.2 Global Batch exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$0.875 $7.00 $0.0875 Not published
Brazil Southbrazilsouth$0.875 $7.00 $0.0875 Not published
Canada Eastcanadaeast$0.875 $7.00 $0.0875 Not published
Central UScentralus$0.875 $7.00 $0.0875 Not published
East USeastus$0.875 $7.00 $0.0875 Not published
East US 2eastus2$0.875 $7.00 $0.0875 Not published
France Centralfrancecentral$0.875 $7.00 $0.0875 Not published
Germany West Centralgermanywestcentral$0.875 $7.00 $0.0875 Not published
Japan Eastjapaneast$0.875 $7.00 $0.0875 Not published
Korea Centralkoreacentral$0.875 $7.00 $0.0875 Not published
North Central USnorthcentralus$0.875 $7.00 $0.0875 Not published
Norway Eastnorwayeast$0.875 $7.00 $0.0875 Not published
Poland Centralpolandcentral$0.875 $7.00 $0.0875 Not published
South Africa Northsouthafricanorth$0.875 $7.00 $0.0875 Not published
South Central USsouthcentralus$0.875 $7.00 $0.0875 Not published
South Indiasouthindia$0.875 $7.00 $0.0875 Not published
Spain Centralspaincentral$0.875 $7.00 $0.0875 Not published
Sweden Centralswedencentral$0.875 $7.00 $0.0875 Not published
Switzerland Northswitzerlandnorth$0.875 $7.00 $0.0875 Not published
UAE Northuaenorth$0.875 $7.00 $0.0875 Not published
UK Southuksouth$0.875 $7.00 $0.0875 Not published
West Europewesteurope$0.875 $7.00 $0.0875 Not published
West USwestus$0.875 $7.00 $0.0875 Not published
West US 3westus3$0.875 $7.00 $0.0875 Not published

Global Priority prices and cost examples

Global processing
Inference data may be processed in any Azure region.
Priority pay-per-token
Priority processing uses pay-as-you-go token meters for faster responses. Model and deployment support varies.

Example workload: 3,000 input and 1,000 output tokens per request, with 10,000 requests per month.

No cached input

Per request
$0.0385
Per month
$385.00

Across 24 published price regions.

Customize workload or price region for Global Priority, No cached input

50% cached input

Per request
$0.033775
Per month
$337.75

Across 24 published price regions.

Customize workload or price region for Global Priority, 50% cached input
View 24 region prices for Global Priority

Price region identifies the Azure retail meter; processing location follows the deployment type described above. Dates show the latest effective meter in each row, not when prices were last checked. All token rates are USD per 1 million tokens.

GPT-5.2 Global Priority exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$3.50 $28.00 $0.35 Not published
Brazil Southbrazilsouth$3.50 $28.00 $0.35 Not published
Canada Eastcanadaeast$3.50 $28.00 $0.35 Not published
Central UScentralus$3.50 $28.00 $0.35 Not published
East USeastus$3.50 $28.00 $0.35 Not published
East US 2eastus2$3.50 $28.00 $0.35 Not published
France Centralfrancecentral$3.50 $28.00 $0.35 Not published
Germany West Centralgermanywestcentral$3.50 $28.00 $0.35 Not published
Japan Eastjapaneast$3.50 $28.00 $0.35 Not published
Korea Centralkoreacentral$3.50 $28.00 $0.35 Not published
North Central USnorthcentralus$3.50 $28.00 $0.35 Not published
Norway Eastnorwayeast$3.50 $28.00 $0.35 Not published
Poland Centralpolandcentral$3.50 $28.00 $0.35 Not published
South Africa Northsouthafricanorth$3.50 $28.00 $0.35 Not published
South Central USsouthcentralus$3.50 $28.00 $0.35 Not published
South Indiasouthindia$3.50 $28.00 $0.35 Not published
Spain Centralspaincentral$3.50 $28.00 $0.35 Not published
Sweden Centralswedencentral$3.50 $28.00 $0.35 Not published
Switzerland Northswitzerlandnorth$3.50 $28.00 $0.35 Not published
UAE Northuaenorth$3.50 $28.00 $0.35 Not published
UK Southuksouth$3.50 $28.00 $0.35 Not published
West Europewesteurope$3.50 $28.00 $0.35 Not published
West USwestus$3.50 $28.00 $0.35 Not published
West US 3westus3$3.50 $28.00 $0.35 Not published

Global Standard prices and cost examples

Global processing
Inference data may be processed in any Azure region.
Standard pay-per-token
Input and output usage is billed by token. Standard deployments provide best-effort throughput; reserved PTU pricing is separate.

Example workload: 3,000 input and 1,000 output tokens per request, with 10,000 requests per month.

No cached input

Per request
$0.01925
Per month
$192.50

Across 24 published price regions.

Customize workload or price region for Global Standard, No cached input

50% cached input

Per request
$0.0168875
Per month
$168.875

Across 24 published price regions.

Customize workload or price region for Global Standard, 50% cached input
View 24 region prices for Global Standard

Price region identifies the Azure retail meter; processing location follows the deployment type described above. Dates show the latest effective meter in each row, not when prices were last checked. All token rates are USD per 1 million tokens.

GPT-5.2 Global Standard exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$1.75 $14.00 $0.175 Not published
Brazil Southbrazilsouth$1.75 $14.00 $0.175 Not published
Canada Eastcanadaeast$1.75 $14.00 $0.175 Not published
Central UScentralus$1.75 $14.00 $0.175 Not published
East USeastus$1.75 $14.00 $0.175 Not published
East US 2eastus2$1.75 $14.00 $0.175 Not published
France Centralfrancecentral$1.75 $14.00 $0.175 Not published
Germany West Centralgermanywestcentral$1.75 $14.00 $0.175 Not published
Japan Eastjapaneast$1.75 $14.00 $0.175 Not published
Korea Centralkoreacentral$1.75 $14.00 $0.175 Not published
North Central USnorthcentralus$1.75 $14.00 $0.175 Not published
Norway Eastnorwayeast$1.75 $14.00 $0.175 Not published
Poland Centralpolandcentral$1.75 $14.00 $0.175 Not published
South Africa Northsouthafricanorth$1.75 $14.00 $0.175 Not published
South Central USsouthcentralus$1.75 $14.00 $0.175 Not published
South Indiasouthindia$1.75 $14.00 $0.175 Not published
Spain Centralspaincentral$1.75 $14.00 $0.175 Not published
Sweden Centralswedencentral$1.75 $14.00 $0.175 Not published
Switzerland Northswitzerlandnorth$1.75 $14.00 $0.175 Not published
UAE Northuaenorth$1.75 $14.00 $0.175 Not published
UK Southuksouth$1.75 $14.00 $0.175 Not published
West Europewesteurope$1.75 $14.00 $0.175 Not published
West USwestus$1.75 $14.00 $0.175 Not published
West US 3westus3$1.75 $14.00 $0.175 Not published

Model information and limits

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Metadata model ID
gpt-5.2
Metadata match
model
Input modalities
text, image
Output modalities
text
Context window (tokens)
400,000
Maximum input tokens
272,000
Maximum output tokens
128,000
Reasoning
Yes
Tool calling
Yes
Structured output
Yes

Supplemental metadata comes from Models.dev, with verified Azure version corrections where available. Family matches do not establish version-specific limits. Confirm capabilities and lifecycle in the official model catalog.

Price sources and deployment guidance

Rates come from the Azure Retail Prices API. This page covers consumption token meters in Azure Public. Provisioned throughput, training, non-token media meters and sovereign-cloud pricing are separate billing scopes.

Browse all Azure AI model prices