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-4.1 nano OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Batch $0.055 $0.22 Not published Not published 15
Data Zone Standard $0.11 $0.44 $0.028 Not published 15
Global Batch $0.05 $0.20 Not published Not published 27
Global Standard $0.10 $0.40 $0.025 Not published 28
Regional Standard $0.11 - $0.132 $0.44 - $0.528 $0.028 - $0.033 Not published 8

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.

Some model token limits are not published in the metadata. These are arithmetic cost examples; verify that your deployment supports the workload before using it.

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
$0.000385
Per month
$3.85

Across 15 published price regions.

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

50% cached input

Estimate unavailable

Published cached input 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 Data Zone Batch, 50% cached input
View 15 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-4.1 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$0.055 $0.22 Not published Not published
East USeastus$0.055 $0.22 Not published Not published
East US 2eastus2$0.055 $0.22 Not published Not published
France Centralfrancecentral$0.055 $0.22 Not published Not published
Germany West Centralgermanywestcentral$0.055 $0.22 Not published Not published
Italy Northitalynorth$0.055 $0.22 Not published Not published
North Central USnorthcentralus$0.055 $0.22 Not published Not published
North Europenortheurope$0.055 $0.22 Not published Not published
Poland Centralpolandcentral$0.055 $0.22 Not published Not published
South Central USsouthcentralus$0.055 $0.22 Not published Not published
Spain Centralspaincentral$0.055 $0.22 Not published Not published
Sweden Centralswedencentral$0.055 $0.22 Not published Not published
West Europewesteurope$0.055 $0.22 Not published Not published
West USwestus$0.055 $0.22 Not published Not published
West US 3westus3$0.055 $0.22 Not published 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
$0.00077
Per month
$7.70

Across 15 published price regions.

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

50% cached input

Per request
$0.000647
Per month
$6.47

Across 15 published price regions.

Customize workload or price region for Data Zone Standard, 50% cached input
View 15 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-4.1 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)
Central UScentralus$0.11 $0.44 $0.028 Not published
East USeastus$0.11 $0.44 $0.028 Not published
East US 2eastus2$0.11 $0.44 $0.028 Not published
France Centralfrancecentral$0.11 $0.44 $0.028 Not published
Germany West Centralgermanywestcentral$0.11 $0.44 $0.028 Not published
Italy Northitalynorth$0.11 $0.44 $0.028 Not published
North Central USnorthcentralus$0.11 $0.44 $0.028 Not published
North Europenortheurope$0.11 $0.44 $0.028 Not published
Poland Centralpolandcentral$0.11 $0.44 $0.028 Not published
South Central USsouthcentralus$0.11 $0.44 $0.028 Not published
Spain Centralspaincentral$0.11 $0.44 $0.028 Not published
Sweden Centralswedencentral$0.11 $0.44 $0.028 Not published
West Europewesteurope$0.11 $0.44 $0.028 Not published
West USwestus$0.11 $0.44 $0.028 Not published
West US 3westus3$0.11 $0.44 $0.028 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
$0.00035
Per month
$3.50

Across 27 published price regions.

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

50% cached input

Estimate unavailable

Published cached input 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 Batch, 50% cached input
View 27 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-4.1 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$0.05 $0.20 Not published Not published
Brazil Southbrazilsouth$0.05 $0.20 Not published Not published
Canada Eastcanadaeast$0.05 $0.20 Not published Not published
Central UScentralus$0.05 $0.20 Not published Not published
East USeastus$0.05 $0.20 Not published Not published
East US 2eastus2$0.05 $0.20 Not published Not published
France Centralfrancecentral$0.05 $0.20 Not published Not published
Germany West Centralgermanywestcentral$0.05 $0.20 Not published Not published
Italy Northitalynorth$0.05 $0.20 Not published Not published
Japan Eastjapaneast$0.05 $0.20 Not published Not published
Korea Centralkoreacentral$0.05 $0.20 Not published Not published
North Central USnorthcentralus$0.05 $0.20 Not published Not published
North Europenortheurope$0.05 $0.20 Not published Not published
Norway Eastnorwayeast$0.05 $0.20 Not published Not published
Poland Centralpolandcentral$0.05 $0.20 Not published Not published
South Africa Northsouthafricanorth$0.05 $0.20 Not published Not published
South Central USsouthcentralus$0.05 $0.20 Not published Not published
South Indiasouthindia$0.05 $0.20 Not published Not published
Southeast Asiasoutheastasia$0.05 $0.20 Not published Not published
Spain Centralspaincentral$0.05 $0.20 Not published Not published
Sweden Centralswedencentral$0.05 $0.20 Not published Not published
Switzerland Northswitzerlandnorth$0.05 $0.20 Not published Not published
UAE Northuaenorth$0.05 $0.20 Not published Not published
UK Southuksouth$0.05 $0.20 Not published Not published
West Europewesteurope$0.05 $0.20 Not published Not published
West USwestus$0.05 $0.20 Not published Not published
West US 3westus3$0.05 $0.20 Not published 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
$0.0007
Per month
$7.00

Across 28 published price regions.

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

50% cached input

Per request
$0.0005875
Per month
$5.875

Across 28 published price regions.

Customize workload or price region for Global Standard, 50% cached input
View 28 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-4.1 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$0.10 $0.40 $0.025 Not published
Brazil Southbrazilsouth$0.10 $0.40 $0.025 Not published
Canada Eastcanadaeast$0.10 $0.40 $0.025 Not published
Central UScentralus$0.10 $0.40 $0.025 Not published
East USeastus$0.10 $0.40 $0.025 Not published
East US 2eastus2$0.10 $0.40 $0.025 Not published
France Centralfrancecentral$0.10 $0.40 $0.025 Not published
Germany West Centralgermanywestcentral$0.10 $0.40 $0.025 Not published
Italy Northitalynorth$0.10 $0.40 $0.025 Not published
Japan Eastjapaneast$0.10 $0.40 $0.025 Not published
Korea Centralkoreacentral$0.10 $0.40 $0.025 Not published
North Central USnorthcentralus$0.10 $0.40 $0.025 Not published
North Europenortheurope$0.10 $0.40 $0.025 Not published
Norway Eastnorwayeast$0.10 $0.40 $0.025 Not published
Poland Centralpolandcentral$0.10 $0.40 $0.025 Not published
South Africa Northsouthafricanorth$0.10 $0.40 $0.025 Not published
South Central USsouthcentralus$0.10 $0.40 $0.025 Not published
South Indiasouthindia$0.10 $0.40 $0.025 Not published
Southeast Asiasoutheastasia$0.10 $0.40 $0.025 Not published
Spain Centralspaincentral$0.10 $0.40 $0.025 Not published
Sweden Centralswedencentral$0.10 $0.40 $0.025 Not published
Switzerland Northswitzerlandnorth$0.10 $0.40 $0.025 Not published
UAE Northuaenorth$0.10 $0.40 $0.025 Not published
UK Southuksouth$0.10 $0.40 $0.025 Not published
West Europewesteurope$0.10 $0.40 $0.025 Not published
West USwestus$0.10 $0.40 $0.025 Not published
West US 2westus2$0.10 $0.40 $0.025 Not published
West US 3westus3$0.10 $0.40 $0.025 Not published

Regional Standard prices and cost examples

Single-region processing
Inference data is processed in the deployment region. Microsoft names the pay-per-token deployment type Standard; this directory uses Regional Standard to make its scope explicit.
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
$0.00077 - $0.000924
Per month
$7.70 - $9.24

Across 8 published price regions.

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

50% cached input

Per request
$0.000647 - $0.0007755
Per month
$6.47 - $7.755

Across 8 published price regions.

Customize workload or price region for Regional Standard, 50% cached input
View 8 region prices for Regional 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-4.1 nano Regional Standard exact regional rates in USD per 1 million tokens.
Azure Public price regionInput / 1MOutput / 1MCached input / 1MCache write / 1MMeter effective dates (UTC)
East USeastus$0.11 $0.44 $0.028 Not published
East US 2eastus2$0.11 $0.44 $0.028 Not published
North Central USnorthcentralus$0.11 $0.44 $0.028 Not published
North Europenortheurope$0.132 $0.528 $0.033 Not published
South Central USsouthcentralus$0.11 $0.44 $0.028 Not published
Sweden Centralswedencentral$0.121 $0.484 $0.031 Not published
West USwestus$0.11 $0.44 $0.028 Not published
West US 3westus3$0.11 $0.44 $0.028 Not published

Model information and limits

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

Metadata model ID
gpt-4.1-nano
Metadata match
model
Input modalities
text, image
Output modalities
text
Context window (tokens)
1,047,576
Maximum input tokens
Not published
Maximum output tokens
32,768
Reasoning
No
Tool calling
Yes
Structured output
Not published

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