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-5.4 mini OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Batch $0.4125 $2.475 $0.04125 Not published 13
Data Zone Priority $1.65 $9.90 $0.165 Not published 14
Data Zone Standard $0.825 - $0.90 $4.95 - $5.40 $0.0825 - $0.09 Not published 23
Global Batch $0.375 $2.25 $0.0375 Not published 24
Global Flex $0.375 $2.25 $0.0375 Not published 25
Global Priority $1.50 $9.00 $0.15 Not published 25
Global Standard $0.75 $4.50 $0.075 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
$0.0037125
Per month
$37.125

Across 13 published price regions.

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

50% cached input

Per request
$0.00315563
Per month
$31.55625

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-5.4 mini 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$0.4125 $2.475 $0.04125 Not published
East USeastus$0.4125 $2.475 $0.04125 Not published
East US 2eastus2$0.4125 $2.475 $0.04125 Not published
France Centralfrancecentral$0.4125 $2.475 $0.04125 Not published
Germany West Centralgermanywestcentral$0.4125 $2.475 $0.04125 Not published
North Central USnorthcentralus$0.4125 $2.475 $0.04125 Not published
Poland Centralpolandcentral$0.4125 $2.475 $0.04125 Not published
South Central USsouthcentralus$0.4125 $2.475 $0.04125 Not published
Spain Centralspaincentral$0.4125 $2.475 $0.04125 Not published
Sweden Centralswedencentral$0.4125 $2.475 $0.04125 Not published
West Europewesteurope$0.4125 $2.475 $0.04125 Not published
West USwestus$0.4125 $2.475 $0.04125 Not published
West US 3westus3$0.4125 $2.475 $0.04125 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
$0.01485
Per month
$148.50

Across 14 published price regions.

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

50% cached input

Per request
$0.0126225
Per month
$126.225

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-5.4 mini 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$1.65 $9.90 $0.165 Not published
East USeastus$1.65 $9.90 $0.165 Not published
East US 2eastus2$1.65 $9.90 $0.165 Not published
France Centralfrancecentral$1.65 $9.90 $0.165 Not published
Germany West Centralgermanywestcentral$1.65 $9.90 $0.165 Not published
North Central USnorthcentralus$1.65 $9.90 $0.165 Not published
North Europenortheurope$1.65 $9.90 $0.165 Not published
Poland Centralpolandcentral$1.65 $9.90 $0.165 Not published
South Central USsouthcentralus$1.65 $9.90 $0.165 Not published
Spain Centralspaincentral$1.65 $9.90 $0.165 Not published
Sweden Centralswedencentral$1.65 $9.90 $0.165 Not published
West Europewesteurope$1.65 $9.90 $0.165 Not published
West USwestus$1.65 $9.90 $0.165 Not published
West US 3westus3$1.65 $9.90 $0.165 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
$0.007425 - $0.0081
Per month
$74.25 - $81.00

Across 23 published price regions.

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

50% cached input

Per request
$0.00631125 - $0.006885
Per month
$63.1125 - $68.85

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-5.4 mini 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$0.90 $5.40 $0.09 Not published
Central Indiacentralindia$0.90 $5.40 $0.09 Not published
Central UScentralus$0.825 $4.95 $0.0825 Not published
East Asiaeastasia$0.90 $5.40 $0.09 Not published
East USeastus$0.825 $4.95 $0.0825 Not published
East US 2eastus2$0.825 $4.95 $0.0825 Not published
France Centralfrancecentral$0.825 $4.95 $0.0825 Not published
Germany West Centralgermanywestcentral$0.825 $4.95 $0.0825 Not published
Japan Eastjapaneast$0.90 $5.40 $0.09 Not published
Japan Westjapanwest$0.90 $5.40 $0.09 Not published
Jio India Westjioindiawest$0.90 $5.40 $0.09 Not published
Korea Centralkoreacentral$0.90 $5.40 $0.09 Not published
North Central USnorthcentralus$0.825 $4.95 $0.0825 Not published
North Europenortheurope$0.825 $4.95 $0.0825 Not published
Poland Centralpolandcentral$0.825 $4.95 $0.0825 Not published
South Central USsouthcentralus$0.825 $4.95 $0.0825 Not published
South Indiasouthindia$0.90 $5.40 $0.09 Not published
Southeast Asiasoutheastasia$0.90 $5.40 $0.09 Not published
Spain Centralspaincentral$0.825 $4.95 $0.0825 Not published
Sweden Centralswedencentral$0.825 $4.95 $0.0825 Not published
West Europewesteurope$0.825 $4.95 $0.0825 Not published
West USwestus$0.825 $4.95 $0.0825 Not published
West US 3westus3$0.825 $4.95 $0.0825 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
$0.003375
Per month
$33.75

Across 24 published price regions.

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

50% cached input

Per request
$0.00286875
Per month
$28.6875

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-5.4 mini 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$0.375 $2.25 $0.0375 Not published
Brazil Southbrazilsouth$0.375 $2.25 $0.0375 Not published
Canada Eastcanadaeast$0.375 $2.25 $0.0375 Not published
Central UScentralus$0.375 $2.25 $0.0375 Not published
East USeastus$0.375 $2.25 $0.0375 Not published
East US 2eastus2$0.375 $2.25 $0.0375 Not published
France Centralfrancecentral$0.375 $2.25 $0.0375 Not published
Germany West Centralgermanywestcentral$0.375 $2.25 $0.0375 Not published
Japan Eastjapaneast$0.375 $2.25 $0.0375 Not published
Korea Centralkoreacentral$0.375 $2.25 $0.0375 Not published
North Central USnorthcentralus$0.375 $2.25 $0.0375 Not published
Norway Eastnorwayeast$0.375 $2.25 $0.0375 Not published
Poland Centralpolandcentral$0.375 $2.25 $0.0375 Not published
South Africa Northsouthafricanorth$0.375 $2.25 $0.0375 Not published
South Central USsouthcentralus$0.375 $2.25 $0.0375 Not published
South Indiasouthindia$0.375 $2.25 $0.0375 Not published
Spain Centralspaincentral$0.375 $2.25 $0.0375 Not published
Sweden Centralswedencentral$0.375 $2.25 $0.0375 Not published
Switzerland Northswitzerlandnorth$0.375 $2.25 $0.0375 Not published
UAE Northuaenorth$0.375 $2.25 $0.0375 Not published
UK Southuksouth$0.375 $2.25 $0.0375 Not published
West Europewesteurope$0.375 $2.25 $0.0375 Not published
West USwestus$0.375 $2.25 $0.0375 Not published
West US 3westus3$0.375 $2.25 $0.0375 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

Per request
$0.003375
Per month
$33.75

Across 25 published price regions.

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

50% cached input

Per request
$0.00286875
Per month
$28.6875

Across 25 published price regions.

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-5.4 mini 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$0.375 $2.25 $0.0375 Not published
Brazil Southbrazilsouth$0.375 $2.25 $0.0375 Not published
Canada Eastcanadaeast$0.375 $2.25 $0.0375 Not published
Central UScentralus$0.375 $2.25 $0.0375 Not published
East USeastus$0.375 $2.25 $0.0375 Not published
East US 2eastus2$0.375 $2.25 $0.0375 Not published
France Centralfrancecentral$0.375 $2.25 $0.0375 Not published
Germany West Centralgermanywestcentral$0.375 $2.25 $0.0375 Not published
Japan Eastjapaneast$0.375 $2.25 $0.0375 Not published
Korea Centralkoreacentral$0.375 $2.25 $0.0375 Not published
Malaysia Westmalaysiawest$0.375 $2.25 $0.0375 Not published
North Central USnorthcentralus$0.375 $2.25 $0.0375 Not published
Norway Eastnorwayeast$0.375 $2.25 $0.0375 Not published
Poland Centralpolandcentral$0.375 $2.25 $0.0375 Not published
South Africa Northsouthafricanorth$0.375 $2.25 $0.0375 Not published
South Central USsouthcentralus$0.375 $2.25 $0.0375 Not published
South Indiasouthindia$0.375 $2.25 $0.0375 Not published
Spain Centralspaincentral$0.375 $2.25 $0.0375 Not published
Sweden Centralswedencentral$0.375 $2.25 $0.0375 Not published
Switzerland Northswitzerlandnorth$0.375 $2.25 $0.0375 Not published
UAE Northuaenorth$0.375 $2.25 $0.0375 Not published
UK Southuksouth$0.375 $2.25 $0.0375 Not published
West Europewesteurope$0.375 $2.25 $0.0375 Not published
West USwestus$0.375 $2.25 $0.0375 Not published
West US 3westus3$0.375 $2.25 $0.0375 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
$0.0135
Per month
$135.00

Across 25 published price regions.

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

50% cached input

Per request
$0.011475
Per month
$114.75

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-5.4 mini 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$1.50 $9.00 $0.15 Not published
Brazil Southbrazilsouth$1.50 $9.00 $0.15 Not published
Canada Eastcanadaeast$1.50 $9.00 $0.15 Not published
Central UScentralus$1.50 $9.00 $0.15 Not published
East USeastus$1.50 $9.00 $0.15 Not published
East US 2eastus2$1.50 $9.00 $0.15 Not published
France Centralfrancecentral$1.50 $9.00 $0.15 Not published
Germany West Centralgermanywestcentral$1.50 $9.00 $0.15 Not published
Japan Eastjapaneast$1.50 $9.00 $0.15 Not published
Korea Centralkoreacentral$1.50 $9.00 $0.15 Not published
North Central USnorthcentralus$1.50 $9.00 $0.15 Not published
North Europenortheurope$1.50 $9.00 $0.15 Not published
Norway Eastnorwayeast$1.50 $9.00 $0.15 Not published
Poland Centralpolandcentral$1.50 $9.00 $0.15 Not published
South Africa Northsouthafricanorth$1.50 $9.00 $0.15 Not published
South Central USsouthcentralus$1.50 $9.00 $0.15 Not published
South Indiasouthindia$1.50 $9.00 $0.15 Not published
Spain Centralspaincentral$1.50 $9.00 $0.15 Not published
Sweden Centralswedencentral$1.50 $9.00 $0.15 Not published
Switzerland Northswitzerlandnorth$1.50 $9.00 $0.15 Not published
UAE Northuaenorth$1.50 $9.00 $0.15 Not published
UK Southuksouth$1.50 $9.00 $0.15 Not published
West Europewesteurope$1.50 $9.00 $0.15 Not published
West USwestus$1.50 $9.00 $0.15 Not published
West US 3westus3$1.50 $9.00 $0.15 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
$0.00675
Per month
$67.50

Across 25 published price regions.

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

50% cached input

Per request
$0.0057375
Per month
$57.375

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-5.4 mini 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$0.75 $4.50 $0.075 Not published
Brazil Southbrazilsouth$0.75 $4.50 $0.075 Not published
Canada Eastcanadaeast$0.75 $4.50 $0.075 Not published
Central UScentralus$0.75 $4.50 $0.075 Not published
East USeastus$0.75 $4.50 $0.075 Not published
East US 2eastus2$0.75 $4.50 $0.075 Not published
France Centralfrancecentral$0.75 $4.50 $0.075 Not published
Germany West Centralgermanywestcentral$0.75 $4.50 $0.075 Not published
Japan Eastjapaneast$0.75 $4.50 $0.075 Not published
Korea Centralkoreacentral$0.75 $4.50 $0.075 Not published
North Central USnorthcentralus$0.75 $4.50 $0.075 Not published
North Europenortheurope$0.75 $4.50 $0.075 Not published
Norway Eastnorwayeast$0.75 $4.50 $0.075 Not published
Poland Centralpolandcentral$0.75 $4.50 $0.075 Not published
South Africa Northsouthafricanorth$0.75 $4.50 $0.075 Not published
South Central USsouthcentralus$0.75 $4.50 $0.075 Not published
South Indiasouthindia$0.75 $4.50 $0.075 Not published
Spain Centralspaincentral$0.75 $4.50 $0.075 Not published
Sweden Centralswedencentral$0.75 $4.50 $0.075 Not published
Switzerland Northswitzerlandnorth$0.75 $4.50 $0.075 Not published
UAE Northuaenorth$0.75 $4.50 $0.075 Not published
UK Southuksouth$0.75 $4.50 $0.075 Not published
West Europewesteurope$0.75 $4.50 $0.075 Not published
West USwestus$0.75 $4.50 $0.075 Not published
West US 3westus3$0.75 $4.50 $0.075 Not published

Model information and limits

Strong small GPT for coding subagents, quick tool use, and high-volume work

Metadata model ID
gpt-5.4-mini
Metadata match
model
Input modalities
text, image, pdf
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