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 nano OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Batch $0.0275 $0.22 $0.00275 Not published 12
Data Zone Standard $0.055 $0.44 $0.0055 Not published 15
Global Batch $0.025 $0.20 $0.0025 Not published 23
Global Standard $0.05 $0.40 $0.005 Not published 27

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
$0.0003025
Per month
$3.025

Across 12 published price regions.

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

50% cached input

Per request
$0.00026538
Per month
$2.65375

Across 12 published price regions.

Customize workload or price region for Data Zone Batch, 50% cached input
View 12 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 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)
East USeastus$0.0275 $0.22 $0.00275 Not published
East US 2eastus2$0.0275 $0.22 $0.00275 Not published
France Centralfrancecentral$0.0275 $0.22 $0.00275 Not published
Germany West Centralgermanywestcentral$0.0275 $0.22 $0.00275 Not published
North Central USnorthcentralus$0.0275 $0.22 $0.00275 Not published
Poland Centralpolandcentral$0.0275 $0.22 $0.00275 Not published
South Central USsouthcentralus$0.0275 $0.22 $0.00275 Not published
Spain Centralspaincentral$0.0275 $0.22 $0.00275 Not published
Sweden Centralswedencentral$0.0275 $0.22 $0.00275 Not published
West Europewesteurope$0.0275 $0.22 $0.00275 Not published
West USwestus$0.0275 $0.22 $0.00275 Not published
West US 3westus3$0.0275 $0.22 $0.00275 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
$0.000605
Per month
$6.05

Across 15 published price regions.

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

50% cached input

Per request
$0.00053075
Per month
$5.3075

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-5 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$0.055 $0.44 $0.0055 Not published
East USeastus$0.055 $0.44 $0.0055 Not published
East US 2eastus2$0.055 $0.44 $0.0055 Not published
France Centralfrancecentral$0.055 $0.44 $0.0055 Not published
Germany West Centralgermanywestcentral$0.055 $0.44 $0.0055 Not published
Italy Northitalynorth$0.055 $0.44 $0.0055 Not published
North Central USnorthcentralus$0.055 $0.44 $0.0055 Not published
North Europenortheurope$0.055 $0.44 $0.0055 Not published
Poland Centralpolandcentral$0.055 $0.44 $0.0055 Not published
South Central USsouthcentralus$0.055 $0.44 $0.0055 Not published
Spain Centralspaincentral$0.055 $0.44 $0.0055 Not published
Sweden Centralswedencentral$0.055 $0.44 $0.0055 Not published
West Europewesteurope$0.055 $0.44 $0.0055 Not published
West USwestus$0.055 $0.44 $0.0055 Not published
West US 3westus3$0.055 $0.44 $0.0055 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
$0.000275
Per month
$2.75

Across 23 published price regions.

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

50% cached input

Per request
$0.00024125
Per month
$2.4125

Across 23 published price regions.

Customize workload or price region for Global Batch, 50% cached input
View 23 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 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$0.025 $0.20 $0.0025 Not published
Brazil Southbrazilsouth$0.025 $0.20 $0.0025 Not published
Canada Eastcanadaeast$0.025 $0.20 $0.0025 Not published
East USeastus$0.025 $0.20 $0.0025 Not published
East US 2eastus2$0.025 $0.20 $0.0025 Not published
France Centralfrancecentral$0.025 $0.20 $0.0025 Not published
Germany West Centralgermanywestcentral$0.025 $0.20 $0.0025 Not published
Japan Eastjapaneast$0.025 $0.20 $0.0025 Not published
Korea Centralkoreacentral$0.025 $0.20 $0.0025 Not published
North Central USnorthcentralus$0.025 $0.20 $0.0025 Not published
Norway Eastnorwayeast$0.025 $0.20 $0.0025 Not published
Poland Centralpolandcentral$0.025 $0.20 $0.0025 Not published
South Africa Northsouthafricanorth$0.025 $0.20 $0.0025 Not published
South Central USsouthcentralus$0.025 $0.20 $0.0025 Not published
South Indiasouthindia$0.025 $0.20 $0.0025 Not published
Spain Centralspaincentral$0.025 $0.20 $0.0025 Not published
Sweden Centralswedencentral$0.025 $0.20 $0.0025 Not published
Switzerland Northswitzerlandnorth$0.025 $0.20 $0.0025 Not published
UAE Northuaenorth$0.025 $0.20 $0.0025 Not published
UK Southuksouth$0.025 $0.20 $0.0025 Not published
West Europewesteurope$0.025 $0.20 $0.0025 Not published
West USwestus$0.025 $0.20 $0.0025 Not published
West US 3westus3$0.025 $0.20 $0.0025 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
$0.00055
Per month
$5.50

Across 27 published price regions.

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

50% cached input

Per request
$0.0004825
Per month
$4.825

Across 27 published price regions.

Customize workload or price region for Global Standard, 50% cached input
View 27 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 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$0.05 $0.40 $0.005 Not published
Brazil Southbrazilsouth$0.05 $0.40 $0.005 Not published
Canada Eastcanadaeast$0.05 $0.40 $0.005 Not published
Central UScentralus$0.05 $0.40 $0.005 Not published
East USeastus$0.05 $0.40 $0.005 Not published
East US 2eastus2$0.05 $0.40 $0.005 Not published
France Centralfrancecentral$0.05 $0.40 $0.005 Not published
Germany West Centralgermanywestcentral$0.05 $0.40 $0.005 Not published
Italy Northitalynorth$0.05 $0.40 $0.005 Not published
Japan Eastjapaneast$0.05 $0.40 $0.005 Not published
Korea Centralkoreacentral$0.05 $0.40 $0.005 Not published
North Central USnorthcentralus$0.05 $0.40 $0.005 Not published
North Europenortheurope$0.05 $0.40 $0.005 Not published
Norway Eastnorwayeast$0.05 $0.40 $0.005 Not published
Poland Centralpolandcentral$0.05 $0.40 $0.005 Not published
South Africa Northsouthafricanorth$0.05 $0.40 $0.005 Not published
South Central USsouthcentralus$0.05 $0.40 $0.005 Not published
South Indiasouthindia$0.05 $0.40 $0.005 Not published
Southeast Asiasoutheastasia$0.05 $0.40 $0.005 Not published
Spain Centralspaincentral$0.05 $0.40 $0.005 Not published
Sweden Centralswedencentral$0.05 $0.40 $0.005 Not published
Switzerland Northswitzerlandnorth$0.05 $0.40 $0.005 Not published
UAE Northuaenorth$0.05 $0.40 $0.005 Not published
UK Southuksouth$0.05 $0.40 $0.005 Not published
West Europewesteurope$0.05 $0.40 $0.005 Not published
West USwestus$0.05 $0.40 $0.005 Not published
West US 3westus3$0.05 $0.40 $0.005 Not published

Model information and limits

Compact GPT model for low-latency assistance and high-volume workloads

Metadata model ID
gpt-5-nano
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
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