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-5.5 OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Batch $2.75 $16.50 $0.275 Not published 13
Data Zone Batch - Long context $5.50 $24.75 $0.55 Not published 13
Data Zone Priority $13.75 $82.50 $1.375 Not published 14
Data Zone Standard $5.50 - $6.00 $33.00 - $36.00 $0.55 - $0.60 Not published 23
Data Zone Standard - Long context $11.00 - $12.00 $49.50 - $54.00 $1.10 - $1.20 Not published 23
Global Batch $2.50 $15.00 $0.25 Not published 24
Global Batch - Long context $5.00 $22.50 $0.50 Not published 24
Global Flex $2.50 Not published $0.25 Not published 25
Global Flex - Long context $5.00 Not published Not published Not published 25
Global Priority $12.50 $75.00 $1.25 Not published 25
Global Standard $5.00 $30.00 $0.50 Not published 25
Global Standard - Long context $10.00 $45.00 $1.00 Not published 25

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
$0.02475
Per month
$247.50

Across 13 published price regions.

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

50% cached input

Per request
$0.0210375
Per month
$210.375

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-5.5 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$2.75 $16.50 $0.275 Not published
East USeastus$2.75 $16.50 $0.275 Not published
East US 2eastus2$2.75 $16.50 $0.275 Not published
France Centralfrancecentral$2.75 $16.50 $0.275 Not published
Germany West Centralgermanywestcentral$2.75 $16.50 $0.275 Not published
North Central USnorthcentralus$2.75 $16.50 $0.275 Not published
Poland Centralpolandcentral$2.75 $16.50 $0.275 Not published
South Central USsouthcentralus$2.75 $16.50 $0.275 Not published
Spain Centralspaincentral$2.75 $16.50 $0.275 Not published
Sweden Centralswedencentral$2.75 $16.50 $0.275 Not published
West Europewesteurope$2.75 $16.50 $0.275 Not published
West USwestus$2.75 $16.50 $0.275 Not published
West US 3westus3$2.75 $16.50 $0.275 Not published

Data Zone Batch - Long context 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.

Long-context meter selected. The token threshold that activates it is model-specific.

Example workload: 272,001 input and 1,000 output tokens per request, with 10,000 requests per month. This input length is above the published 272,000-token long-context pricing threshold.

No cached input

Per request
$1.5207555
Per month
$15,207.555

Across 13 published price regions.

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

50% cached input

Per request
$0.84755303
Per month
$8,475.53025

Across 13 published price regions.

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

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-5.5 Data Zone Batch - Long context exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Central UScentralus$5.50 $24.75 $0.55 Not published
East USeastus$5.50 $24.75 $0.55 Not published
East US 2eastus2$5.50 $24.75 $0.55 Not published
France Centralfrancecentral$5.50 $24.75 $0.55 Not published
Germany West Centralgermanywestcentral$5.50 $24.75 $0.55 Not published
North Central USnorthcentralus$5.50 $24.75 $0.55 Not published
Poland Centralpolandcentral$5.50 $24.75 $0.55 Not published
South Central USsouthcentralus$5.50 $24.75 $0.55 Not published
Spain Centralspaincentral$5.50 $24.75 $0.55 Not published
Sweden Centralswedencentral$5.50 $24.75 $0.55 Not published
West Europewesteurope$5.50 $24.75 $0.55 Not published
West USwestus$5.50 $24.75 $0.55 Not published
West US 3westus3$5.50 $24.75 $0.55 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
$0.12375
Per month
$1,237.50

Across 14 published price regions.

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

50% cached input

Per request
$0.1051875
Per month
$1,051.875

Across 14 published price regions.

Customize workload or price region for Data Zone Priority, 50% cached input
View 14 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-5.5 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$13.75 $82.50 $1.375 Not published
East USeastus$13.75 $82.50 $1.375 Not published
East US 2eastus2$13.75 $82.50 $1.375 Not published
France Centralfrancecentral$13.75 $82.50 $1.375 Not published
Germany West Centralgermanywestcentral$13.75 $82.50 $1.375 Not published
North Central USnorthcentralus$13.75 $82.50 $1.375 Not published
North Europenortheurope$13.75 $82.50 $1.375 Not published
Poland Centralpolandcentral$13.75 $82.50 $1.375 Not published
South Central USsouthcentralus$13.75 $82.50 $1.375 Not published
Spain Centralspaincentral$13.75 $82.50 $1.375 Not published
Sweden Centralswedencentral$13.75 $82.50 $1.375 Not published
West Europewesteurope$13.75 $82.50 $1.375 Not published
West USwestus$13.75 $82.50 $1.375 Not published
West US 3westus3$13.75 $82.50 $1.375 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
$0.0495 - $0.054
Per month
$495.00 - $540.00

Across 23 published price regions.

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

50% cached input

Per request
$0.042075 - $0.0459
Per month
$420.75 - $459.00

Across 23 published price regions.

Customize workload or price region for Data Zone Standard, 50% cached input
View 23 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-5.5 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$6.00 $36.00 $0.60 Not published
Central Indiacentralindia$6.00 $36.00 $0.60 Not published
Central UScentralus$5.50 $33.00 $0.55 Not published
East Asiaeastasia$6.00 $36.00 $0.60 Not published
East USeastus$5.50 $33.00 $0.55 Not published
East US 2eastus2$5.50 $33.00 $0.55 Not published
France Centralfrancecentral$5.50 $33.00 $0.55 Not published
Germany West Centralgermanywestcentral$5.50 $33.00 $0.55 Not published
Japan Eastjapaneast$6.00 $36.00 $0.60 Not published
Japan Westjapanwest$6.00 $36.00 $0.60 Not published
Jio India Westjioindiawest$6.00 $36.00 $0.60 Not published
Korea Centralkoreacentral$6.00 $36.00 $0.60 Not published
North Central USnorthcentralus$5.50 $33.00 $0.55 Not published
North Europenortheurope$5.50 $33.00 $0.55 Not published
Poland Centralpolandcentral$5.50 $33.00 $0.55 Not published
South Central USsouthcentralus$5.50 $33.00 $0.55 Not published
South Indiasouthindia$6.00 $36.00 $0.60 Not published
Southeast Asiasoutheastasia$6.00 $36.00 $0.60 Not published
Spain Centralspaincentral$5.50 $33.00 $0.55 Not published
Sweden Centralswedencentral$5.50 $33.00 $0.55 Not published
West Europewesteurope$5.50 $33.00 $0.55 Not published
West USwestus$5.50 $33.00 $0.55 Not published
West US 3westus3$5.50 $33.00 $0.55 Not published

Data Zone Standard - Long context 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.

Long-context meter selected. The token threshold that activates it is model-specific.

Example workload: 272,001 input and 1,000 output tokens per request, with 10,000 requests per month. This input length is above the published 272,000-token long-context pricing threshold.

No cached input

Per request
$3.041511 - $3.318012
Per month
$30,415.11 - $33,180.12

Across 23 published price regions.

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

50% cached input

Per request
$1.69510605 - $1.8492066
Per month
$16,951.0605 - $18,492.066

Across 23 published price regions.

Customize workload or price region for Data Zone Standard - Long context, 50% cached input
View 23 region prices for Data Zone Standard - Long context

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-5.5 Data Zone Standard - Long context exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$12.00 $54.00 $1.20 Not published
Central Indiacentralindia$12.00 $54.00 $1.20 Not published
Central UScentralus$11.00 $49.50 $1.10 Not published
East Asiaeastasia$12.00 $54.00 $1.20 Not published
East USeastus$11.00 $49.50 $1.10 Not published
East US 2eastus2$11.00 $49.50 $1.10 Not published
France Centralfrancecentral$11.00 $49.50 $1.10 Not published
Germany West Centralgermanywestcentral$11.00 $49.50 $1.10 Not published
Japan Eastjapaneast$12.00 $54.00 $1.20 Not published
Japan Westjapanwest$12.00 $54.00 $1.20 Not published
Jio India Westjioindiawest$12.00 $54.00 $1.20 Not published
Korea Centralkoreacentral$12.00 $54.00 $1.20 Not published
North Central USnorthcentralus$11.00 $49.50 $1.10 Not published
North Europenortheurope$11.00 $49.50 $1.10 Not published
Poland Centralpolandcentral$11.00 $49.50 $1.10 Not published
South Central USsouthcentralus$11.00 $49.50 $1.10 Not published
South Indiasouthindia$12.00 $54.00 $1.20 Not published
Southeast Asiasoutheastasia$12.00 $54.00 $1.20 Not published
Spain Centralspaincentral$11.00 $49.50 $1.10 Not published
Sweden Centralswedencentral$11.00 $49.50 $1.10 Not published
West Europewesteurope$11.00 $49.50 $1.10 Not published
West USwestus$11.00 $49.50 $1.10 Not published
West US 3westus3$11.00 $49.50 $1.10 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
$0.0225
Per month
$225.00

Across 24 published price regions.

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

50% cached input

Per request
$0.019125
Per month
$191.25

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-5.5 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$2.50 $15.00 $0.25 Not published
Brazil Southbrazilsouth$2.50 $15.00 $0.25 Not published
Canada Eastcanadaeast$2.50 $15.00 $0.25 Not published
Central UScentralus$2.50 $15.00 $0.25 Not published
East USeastus$2.50 $15.00 $0.25 Not published
East US 2eastus2$2.50 $15.00 $0.25 Not published
France Centralfrancecentral$2.50 $15.00 $0.25 Not published
Germany West Centralgermanywestcentral$2.50 $15.00 $0.25 Not published
Japan Eastjapaneast$2.50 $15.00 $0.25 Not published
Korea Centralkoreacentral$2.50 $15.00 $0.25 Not published
North Central USnorthcentralus$2.50 $15.00 $0.25 Not published
Norway Eastnorwayeast$2.50 $15.00 $0.25 Not published
Poland Centralpolandcentral$2.50 $15.00 $0.25 Not published
South Africa Northsouthafricanorth$2.50 $15.00 $0.25 Not published
South Central USsouthcentralus$2.50 $15.00 $0.25 Not published
South Indiasouthindia$2.50 $15.00 $0.25 Not published
Spain Centralspaincentral$2.50 $15.00 $0.25 Not published
Sweden Centralswedencentral$2.50 $15.00 $0.25 Not published
Switzerland Northswitzerlandnorth$2.50 $15.00 $0.25 Not published
UAE Northuaenorth$2.50 $15.00 $0.25 Not published
UK Southuksouth$2.50 $15.00 $0.25 Not published
West Europewesteurope$2.50 $15.00 $0.25 Not published
West USwestus$2.50 $15.00 $0.25 Not published
West US 3westus3$2.50 $15.00 $0.25 Not published

Global Batch - Long context 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.

Long-context meter selected. The token threshold that activates it is model-specific.

Example workload: 272,001 input and 1,000 output tokens per request, with 10,000 requests per month. This input length is above the published 272,000-token long-context pricing threshold.

No cached input

Per request
$1.382505
Per month
$13,825.05

Across 24 published price regions.

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

50% cached input

Per request
$0.77050275
Per month
$7,705.0275

Across 24 published price regions.

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

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-5.5 Global Batch - Long context exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$5.00 $22.50 $0.50 Not published
Brazil Southbrazilsouth$5.00 $22.50 $0.50 Not published
Canada Eastcanadaeast$5.00 $22.50 $0.50 Not published
Central UScentralus$5.00 $22.50 $0.50 Not published
East USeastus$5.00 $22.50 $0.50 Not published
East US 2eastus2$5.00 $22.50 $0.50 Not published
France Centralfrancecentral$5.00 $22.50 $0.50 Not published
Germany West Centralgermanywestcentral$5.00 $22.50 $0.50 Not published
Japan Eastjapaneast$5.00 $22.50 $0.50 Not published
Korea Centralkoreacentral$5.00 $22.50 $0.50 Not published
North Central USnorthcentralus$5.00 $22.50 $0.50 Not published
Norway Eastnorwayeast$5.00 $22.50 $0.50 Not published
Poland Centralpolandcentral$5.00 $22.50 $0.50 Not published
South Africa Northsouthafricanorth$5.00 $22.50 $0.50 Not published
South Central USsouthcentralus$5.00 $22.50 $0.50 Not published
South Indiasouthindia$5.00 $22.50 $0.50 Not published
Spain Centralspaincentral$5.00 $22.50 $0.50 Not published
Sweden Centralswedencentral$5.00 $22.50 $0.50 Not published
Switzerland Northswitzerlandnorth$5.00 $22.50 $0.50 Not published
UAE Northuaenorth$5.00 $22.50 $0.50 Not published
UK Southuksouth$5.00 $22.50 $0.50 Not published
West Europewesteurope$5.00 $22.50 $0.50 Not published
West USwestus$5.00 $22.50 $0.50 Not published
West US 3westus3$5.00 $22.50 $0.50 Not published

Global Flex prices and cost examples

Global processing
Inference data may be processed in any Azure region.
Flex pay-per-token
Input and output usage is billed at the model's published Flex token rates. 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

Estimate unavailable

Published output prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

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

50% cached input

Estimate unavailable

Published output prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

Customize workload or price region for Global Flex, 50% cached input
View 25 region prices for Global Flex

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-5.5 Global Flex exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$2.50 Not published $0.25 Not published
Brazil Southbrazilsouth$2.50 Not published $0.25 Not published
Canada Eastcanadaeast$2.50 Not published $0.25 Not published
Central UScentralus$2.50 Not published $0.25 Not published
East USeastus$2.50 Not published $0.25 Not published
East US 2eastus2$2.50 Not published $0.25 Not published
France Centralfrancecentral$2.50 Not published $0.25 Not published
Germany West Centralgermanywestcentral$2.50 Not published $0.25 Not published
Japan Eastjapaneast$2.50 Not published $0.25 Not published
Korea Centralkoreacentral$2.50 Not published $0.25 Not published
Malaysia Westmalaysiawest$2.50 Not published $0.25 Not published
North Central USnorthcentralus$2.50 Not published $0.25 Not published
Norway Eastnorwayeast$2.50 Not published $0.25 Not published
Poland Centralpolandcentral$2.50 Not published $0.25 Not published
South Africa Northsouthafricanorth$2.50 Not published $0.25 Not published
South Central USsouthcentralus$2.50 Not published $0.25 Not published
South Indiasouthindia$2.50 Not published $0.25 Not published
Spain Centralspaincentral$2.50 Not published $0.25 Not published
Sweden Centralswedencentral$2.50 Not published $0.25 Not published
Switzerland Northswitzerlandnorth$2.50 Not published $0.25 Not published
UAE Northuaenorth$2.50 Not published $0.25 Not published
UK Southuksouth$2.50 Not published $0.25 Not published
West Europewesteurope$2.50 Not published $0.25 Not published
West USwestus$2.50 Not published $0.25 Not published
West US 3westus3$2.50 Not published $0.25 Not published

Global Flex - Long context prices and cost examples

Global processing
Inference data may be processed in any Azure region.
Flex pay-per-token
Input and output usage is billed at the model's published Flex token rates. Model and deployment support varies.

Long-context meter selected. The token threshold that activates it is model-specific.

Example workload: 272,001 input and 1,000 output tokens per request, with 10,000 requests per month. This input length is above the published 272,000-token long-context pricing threshold.

No cached input

Estimate unavailable

Published output prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

Customize workload or price region for Global Flex - Long context, No cached input

50% cached input

Estimate unavailable

Published cached input and output prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

Customize workload or price region for Global Flex - Long context, 50% cached input
View 25 region prices for Global Flex - Long context

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-5.5 Global Flex - Long context exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$5.00 Not published Not published Not published
Brazil Southbrazilsouth$5.00 Not published Not published Not published
Canada Eastcanadaeast$5.00 Not published Not published Not published
Central UScentralus$5.00 Not published Not published Not published
East USeastus$5.00 Not published Not published Not published
East US 2eastus2$5.00 Not published Not published Not published
France Centralfrancecentral$5.00 Not published Not published Not published
Germany West Centralgermanywestcentral$5.00 Not published Not published Not published
Japan Eastjapaneast$5.00 Not published Not published Not published
Korea Centralkoreacentral$5.00 Not published Not published Not published
Malaysia Westmalaysiawest$5.00 Not published Not published Not published
North Central USnorthcentralus$5.00 Not published Not published Not published
Norway Eastnorwayeast$5.00 Not published Not published Not published
Poland Centralpolandcentral$5.00 Not published Not published Not published
South Africa Northsouthafricanorth$5.00 Not published Not published Not published
South Central USsouthcentralus$5.00 Not published Not published Not published
South Indiasouthindia$5.00 Not published Not published Not published
Spain Centralspaincentral$5.00 Not published Not published Not published
Sweden Centralswedencentral$5.00 Not published Not published Not published
Switzerland Northswitzerlandnorth$5.00 Not published Not published Not published
UAE Northuaenorth$5.00 Not published Not published Not published
UK Southuksouth$5.00 Not published Not published Not published
West Europewesteurope$5.00 Not published Not published Not published
West USwestus$5.00 Not published Not published Not published
West US 3westus3$5.00 Not published Not published 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
$0.1125
Per month
$1,125.00

Across 25 published price regions.

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

50% cached input

Per request
$0.095625
Per month
$956.25

Across 25 published price regions.

Customize workload or price region for Global Priority, 50% cached input
View 25 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-5.5 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$12.50 $75.00 $1.25 Not published
Brazil Southbrazilsouth$12.50 $75.00 $1.25 Not published
Canada Eastcanadaeast$12.50 $75.00 $1.25 Not published
Central UScentralus$12.50 $75.00 $1.25 Not published
East USeastus$12.50 $75.00 $1.25 Not published
East US 2eastus2$12.50 $75.00 $1.25 Not published
France Centralfrancecentral$12.50 $75.00 $1.25 Not published
Germany West Centralgermanywestcentral$12.50 $75.00 $1.25 Not published
Japan Eastjapaneast$12.50 $75.00 $1.25 Not published
Korea Centralkoreacentral$12.50 $75.00 $1.25 Not published
North Central USnorthcentralus$12.50 $75.00 $1.25 Not published
North Europenortheurope$12.50 $75.00 $1.25 Not published
Norway Eastnorwayeast$12.50 $75.00 $1.25 Not published
Poland Centralpolandcentral$12.50 $75.00 $1.25 Not published
South Africa Northsouthafricanorth$12.50 $75.00 $1.25 Not published
South Central USsouthcentralus$12.50 $75.00 $1.25 Not published
South Indiasouthindia$12.50 $75.00 $1.25 Not published
Spain Centralspaincentral$12.50 $75.00 $1.25 Not published
Sweden Centralswedencentral$12.50 $75.00 $1.25 Not published
Switzerland Northswitzerlandnorth$12.50 $75.00 $1.25 Not published
UAE Northuaenorth$12.50 $75.00 $1.25 Not published
UK Southuksouth$12.50 $75.00 $1.25 Not published
West Europewesteurope$12.50 $75.00 $1.25 Not published
West USwestus$12.50 $75.00 $1.25 Not published
West US 3westus3$12.50 $75.00 $1.25 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
$0.045
Per month
$450.00

Across 25 published price regions.

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

50% cached input

Per request
$0.03825
Per month
$382.50

Across 25 published price regions.

Customize workload or price region for Global Standard, 50% cached input
View 25 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-5.5 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$5.00 $30.00 $0.50 Not published
Brazil Southbrazilsouth$5.00 $30.00 $0.50 Not published
Canada Eastcanadaeast$5.00 $30.00 $0.50 Not published
Central UScentralus$5.00 $30.00 $0.50 Not published
East USeastus$5.00 $30.00 $0.50 Not published
East US 2eastus2$5.00 $30.00 $0.50 Not published
France Centralfrancecentral$5.00 $30.00 $0.50 Not published
Germany West Centralgermanywestcentral$5.00 $30.00 $0.50 Not published
Japan Eastjapaneast$5.00 $30.00 $0.50 Not published
Korea Centralkoreacentral$5.00 $30.00 $0.50 Not published
North Central USnorthcentralus$5.00 $30.00 $0.50 Not published
North Europenortheurope$5.00 $30.00 $0.50 Not published
Norway Eastnorwayeast$5.00 $30.00 $0.50 Not published
Poland Centralpolandcentral$5.00 $30.00 $0.50 Not published
South Africa Northsouthafricanorth$5.00 $30.00 $0.50 Not published
South Central USsouthcentralus$5.00 $30.00 $0.50 Not published
South Indiasouthindia$5.00 $30.00 $0.50 Not published
Spain Centralspaincentral$5.00 $30.00 $0.50 Not published
Sweden Centralswedencentral$5.00 $30.00 $0.50 Not published
Switzerland Northswitzerlandnorth$5.00 $30.00 $0.50 Not published
UAE Northuaenorth$5.00 $30.00 $0.50 Not published
UK Southuksouth$5.00 $30.00 $0.50 Not published
West Europewesteurope$5.00 $30.00 $0.50 Not published
West USwestus$5.00 $30.00 $0.50 Not published
West US 3westus3$5.00 $30.00 $0.50 Not published

Global Standard - Long context 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.

Long-context meter selected. The token threshold that activates it is model-specific.

Example workload: 272,001 input and 1,000 output tokens per request, with 10,000 requests per month. This input length is above the published 272,000-token long-context pricing threshold.

No cached input

Per request
$2.76501
Per month
$27,650.10

Across 25 published price regions.

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

50% cached input

Per request
$1.5410055
Per month
$15,410.055

Across 25 published price regions.

Customize workload or price region for Global Standard - Long context, 50% cached input
View 25 region prices for Global Standard - Long context

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-5.5 Global Standard - Long context exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
Australia Eastaustraliaeast$10.00 $45.00 $1.00 Not published
Brazil Southbrazilsouth$10.00 $45.00 $1.00 Not published
Canada Eastcanadaeast$10.00 $45.00 $1.00 Not published
Central UScentralus$10.00 $45.00 $1.00 Not published
East USeastus$10.00 $45.00 $1.00 Not published
East US 2eastus2$10.00 $45.00 $1.00 Not published
France Centralfrancecentral$10.00 $45.00 $1.00 Not published
Germany West Centralgermanywestcentral$10.00 $45.00 $1.00 Not published
Japan Eastjapaneast$10.00 $45.00 $1.00 Not published
Korea Centralkoreacentral$10.00 $45.00 $1.00 Not published
North Central USnorthcentralus$10.00 $45.00 $1.00 Not published
North Europenortheurope$10.00 $45.00 $1.00 Not published
Norway Eastnorwayeast$10.00 $45.00 $1.00 Not published
Poland Centralpolandcentral$10.00 $45.00 $1.00 Not published
South Africa Northsouthafricanorth$10.00 $45.00 $1.00 Not published
South Central USsouthcentralus$10.00 $45.00 $1.00 Not published
South Indiasouthindia$10.00 $45.00 $1.00 Not published
Spain Centralspaincentral$10.00 $45.00 $1.00 Not published
Sweden Centralswedencentral$10.00 $45.00 $1.00 Not published
Switzerland Northswitzerlandnorth$10.00 $45.00 $1.00 Not published
UAE Northuaenorth$10.00 $45.00 $1.00 Not published
UK Southuksouth$10.00 $45.00 $1.00 Not published
West Europewesteurope$10.00 $45.00 $1.00 Not published
West USwestus$10.00 $45.00 $1.00 Not published
West US 3westus3$10.00 $45.00 $1.00 Not published

Model information and limits

Default frontier GPT for coding, computer use, research, and knowledge work

Metadata model ID
gpt-5.5
Metadata match
model
Input modalities
text, image, pdf
Output modalities
text
Context window (tokens)
1,050,000
Maximum input tokens
922,000
Maximum output tokens
128,000
Long-context pricing starts above (input tokens)
272,000
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