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 nano OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Batch $0.11 $0.6875 $0.011 Not published 13
Data Zone Standard $0.22 - $0.24 $1.375 - $1.50 $0.022 - $0.024 Not published 23
Global Batch $0.10 $0.625 $0.01 Not published 24
Global Flex $0.10 $0.625 $0.01 Not published 25
Global Standard $0.20 $1.25 $0.02 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
$0.0010175
Per month
$10.175

Across 13 published price regions.

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

50% cached input

Per request
$0.000869
Per month
$8.69

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 nano 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$0.11 $0.6875 $0.011 Not published
East USeastus$0.11 $0.6875 $0.011 Not published
East US 2eastus2$0.11 $0.6875 $0.011 Not published
France Centralfrancecentral$0.11 $0.6875 $0.011 Not published
Germany West Centralgermanywestcentral$0.11 $0.6875 $0.011 Not published
North Central USnorthcentralus$0.11 $0.6875 $0.011 Not published
Poland Centralpolandcentral$0.11 $0.6875 $0.011 Not published
South Central USsouthcentralus$0.11 $0.6875 $0.011 Not published
Spain Centralspaincentral$0.11 $0.6875 $0.011 Not published
Sweden Centralswedencentral$0.11 $0.6875 $0.011 Not published
West Europewesteurope$0.11 $0.6875 $0.011 Not published
West USwestus$0.11 $0.6875 $0.011 Not published
West US 3westus3$0.11 $0.6875 $0.011 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
$0.002035 - $0.00222
Per month
$20.35 - $22.20

Across 23 published price regions.

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

50% cached input

Per request
$0.001738 - $0.001896
Per month
$17.38 - $18.96

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 nano 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$0.24 $1.50 $0.024 Not published
Central Indiacentralindia$0.24 $1.50 $0.024 Not published
Central UScentralus$0.22 $1.375 $0.022 Not published
East Asiaeastasia$0.24 $1.50 $0.024 Not published
East USeastus$0.22 $1.375 $0.022 Not published
East US 2eastus2$0.22 $1.375 $0.022 Not published
France Centralfrancecentral$0.22 $1.375 $0.022 Not published
Germany West Centralgermanywestcentral$0.22 $1.375 $0.022 Not published
Japan Eastjapaneast$0.24 $1.50 $0.024 Not published
Japan Westjapanwest$0.24 $1.50 $0.024 Not published
Jio India Westjioindiawest$0.24 $1.50 $0.024 Not published
Korea Centralkoreacentral$0.24 $1.50 $0.024 Not published
North Central USnorthcentralus$0.22 $1.375 $0.022 Not published
North Europenortheurope$0.22 $1.375 $0.022 Not published
Poland Centralpolandcentral$0.22 $1.375 $0.022 Not published
South Central USsouthcentralus$0.22 $1.375 $0.022 Not published
South Indiasouthindia$0.24 $1.50 $0.024 Not published
Southeast Asiasoutheastasia$0.24 $1.50 $0.024 Not published
Spain Centralspaincentral$0.22 $1.375 $0.022 Not published
Sweden Centralswedencentral$0.22 $1.375 $0.022 Not published
West Europewesteurope$0.22 $1.375 $0.022 Not published
West USwestus$0.22 $1.375 $0.022 Not published
West US 3westus3$0.22 $1.375 $0.022 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
$0.000925
Per month
$9.25

Across 24 published price regions.

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

50% cached input

Per request
$0.00079
Per month
$7.90

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 nano 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$0.10 $0.625 $0.01 Not published
Brazil Southbrazilsouth$0.10 $0.625 $0.01 Not published
Canada Eastcanadaeast$0.10 $0.625 $0.01 Not published
Central UScentralus$0.10 $0.625 $0.01 Not published
East USeastus$0.10 $0.625 $0.01 Not published
East US 2eastus2$0.10 $0.625 $0.01 Not published
France Centralfrancecentral$0.10 $0.625 $0.01 Not published
Germany West Centralgermanywestcentral$0.10 $0.625 $0.01 Not published
Japan Eastjapaneast$0.10 $0.625 $0.01 Not published
Korea Centralkoreacentral$0.10 $0.625 $0.01 Not published
North Central USnorthcentralus$0.10 $0.625 $0.01 Not published
Norway Eastnorwayeast$0.10 $0.625 $0.01 Not published
Poland Centralpolandcentral$0.10 $0.625 $0.01 Not published
South Africa Northsouthafricanorth$0.10 $0.625 $0.01 Not published
South Central USsouthcentralus$0.10 $0.625 $0.01 Not published
South Indiasouthindia$0.10 $0.625 $0.01 Not published
Spain Centralspaincentral$0.10 $0.625 $0.01 Not published
Sweden Centralswedencentral$0.10 $0.625 $0.01 Not published
Switzerland Northswitzerlandnorth$0.10 $0.625 $0.01 Not published
UAE Northuaenorth$0.10 $0.625 $0.01 Not published
UK Southuksouth$0.10 $0.625 $0.01 Not published
West Europewesteurope$0.10 $0.625 $0.01 Not published
West USwestus$0.10 $0.625 $0.01 Not published
West US 3westus3$0.10 $0.625 $0.01 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
$0.000925
Per month
$9.25

Across 25 published price regions.

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

50% cached input

Per request
$0.00079
Per month
$7.90

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 nano 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$0.10 $0.625 $0.01 Not published
Brazil Southbrazilsouth$0.10 $0.625 $0.01 Not published
Canada Eastcanadaeast$0.10 $0.625 $0.01 Not published
Central UScentralus$0.10 $0.625 $0.01 Not published
East USeastus$0.10 $0.625 $0.01 Not published
East US 2eastus2$0.10 $0.625 $0.01 Not published
France Centralfrancecentral$0.10 $0.625 $0.01 Not published
Germany West Centralgermanywestcentral$0.10 $0.625 $0.01 Not published
Japan Eastjapaneast$0.10 $0.625 $0.01 Not published
Korea Centralkoreacentral$0.10 $0.625 $0.01 Not published
Malaysia Westmalaysiawest$0.10 $0.625 $0.01 Not published
North Central USnorthcentralus$0.10 $0.625 $0.01 Not published
Norway Eastnorwayeast$0.10 $0.625 $0.01 Not published
Poland Centralpolandcentral$0.10 $0.625 $0.01 Not published
South Africa Northsouthafricanorth$0.10 $0.625 $0.01 Not published
South Central USsouthcentralus$0.10 $0.625 $0.01 Not published
South Indiasouthindia$0.10 $0.625 $0.01 Not published
Spain Centralspaincentral$0.10 $0.625 $0.01 Not published
Sweden Centralswedencentral$0.10 $0.625 $0.01 Not published
Switzerland Northswitzerlandnorth$0.10 $0.625 $0.01 Not published
UAE Northuaenorth$0.10 $0.625 $0.01 Not published
UK Southuksouth$0.10 $0.625 $0.01 Not published
West Europewesteurope$0.10 $0.625 $0.01 Not published
West USwestus$0.10 $0.625 $0.01 Not published
West US 3westus3$0.10 $0.625 $0.01 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
$0.00185
Per month
$18.50

Across 25 published price regions.

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

50% cached input

Per request
$0.00158
Per month
$15.80

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 nano 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$0.20 $1.25 $0.02 Not published
Brazil Southbrazilsouth$0.20 $1.25 $0.02 Not published
Canada Eastcanadaeast$0.20 $1.25 $0.02 Not published
Central UScentralus$0.20 $1.25 $0.02 Not published
East USeastus$0.20 $1.25 $0.02 Not published
East US 2eastus2$0.20 $1.25 $0.02 Not published
France Centralfrancecentral$0.20 $1.25 $0.02 Not published
Germany West Centralgermanywestcentral$0.20 $1.25 $0.02 Not published
Japan Eastjapaneast$0.20 $1.25 $0.02 Not published
Korea Centralkoreacentral$0.20 $1.25 $0.02 Not published
North Central USnorthcentralus$0.20 $1.25 $0.02 Not published
North Europenortheurope$0.20 $1.25 $0.02 Not published
Norway Eastnorwayeast$0.20 $1.25 $0.02 Not published
Poland Centralpolandcentral$0.20 $1.25 $0.02 Not published
South Africa Northsouthafricanorth$0.20 $1.25 $0.02 Not published
South Central USsouthcentralus$0.20 $1.25 $0.02 Not published
South Indiasouthindia$0.20 $1.25 $0.02 Not published
Spain Centralspaincentral$0.20 $1.25 $0.02 Not published
Sweden Centralswedencentral$0.20 $1.25 $0.02 Not published
Switzerland Northswitzerlandnorth$0.20 $1.25 $0.02 Not published
UAE Northuaenorth$0.20 $1.25 $0.02 Not published
UK Southuksouth$0.20 $1.25 $0.02 Not published
West Europewesteurope$0.20 $1.25 $0.02 Not published
West USwestus$0.20 $1.25 $0.02 Not published
West US 3westus3$0.20 $1.25 $0.02 Not published

Model information and limits

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

Metadata model ID
gpt-5.4-nano
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