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-6 Astra OpenAI prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Data Zone Standard $11.00 - $12.00 $55.00 - $60.00 $1.10 - $1.20 $13.75 - $15.00 21
Data Zone Standard - Long context $22.00 - $24.00 $82.50 - $90.00 $2.20 - $2.40 $27.50 - $30.00 21
Global Standard $10.00 $50.00 $1.00 $12.50 27
Global Standard - Long context $20.00 $75.00 $2.00 $25.00 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 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
$0.088 - $0.096
Per month
$880.00 - $960.00

Across 21 published price regions.

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

50% cached input

Per request
$0.07315 - $0.0798
Per month
$731.50 - $798.00

Across 21 published price regions.

Customize workload or price region for Data Zone Standard, 50% cached input
View 21 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-6 Astra 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$12.00 $60.00 $1.20 $15.00
Central UScentralus$11.00 $55.00 $1.10 $13.75
East USeastus$11.00 $55.00 $1.10 $13.75
East US 2eastus2$11.00 $55.00 $1.10 $13.75
France Centralfrancecentral$12.00 $60.00 $1.20 $15.00
Germany West Centralgermanywestcentral$12.00 $60.00 $1.20 $15.00
Italy Northitalynorth$12.00 $60.00 $1.20 $15.00
Japan Eastjapaneast$12.00 $60.00 $1.20 $15.00
Korea Centralkoreacentral$12.00 $60.00 $1.20 $15.00
North Central USnorthcentralus$11.00 $55.00 $1.10 $13.75
Norway Eastnorwayeast$12.00 $60.00 $1.20 $15.00
Poland Centralpolandcentral$12.00 $60.00 $1.20 $15.00
South Central USsouthcentralus$11.00 $55.00 $1.10 $13.75
South Indiasouthindia$12.00 $60.00 $1.20 $15.00
Spain Centralspaincentral$12.00 $60.00 $1.20 $15.00
Sweden Centralswedencentral$12.00 $60.00 $1.20 $15.00
Switzerland Northswitzerlandnorth$12.00 $60.00 $1.20 $15.00
Switzerland Westswitzerlandwest$12.00 $60.00 $1.20 $15.00
West Europewesteurope$12.00 $60.00 $1.20 $15.00
West USwestus$11.00 $55.00 $1.10 $13.75
West US 3westus3$11.00 $55.00 $1.10 $13.75

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
$6.066522 - $6.618024
Per month
$60,665.22 - $66,180.24

Across 21 published price regions.

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

50% cached input

Per request
$3.3737121 - $3.6804132
Per month
$33,737.121 - $36,804.132

Across 21 published price regions.

Customize workload or price region for Data Zone Standard - Long context, 50% cached input
View 21 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-6 Astra 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$24.00 $90.00 $2.40 $30.00
Central UScentralus$22.00 $82.50 $2.20 $27.50
East USeastus$22.00 $82.50 $2.20 $27.50
East US 2eastus2$22.00 $82.50 $2.20 $27.50
France Centralfrancecentral$24.00 $90.00 $2.40 $30.00
Germany West Centralgermanywestcentral$24.00 $90.00 $2.40 $30.00
Italy Northitalynorth$24.00 $90.00 $2.40 $30.00
Japan Eastjapaneast$24.00 $90.00 $2.40 $30.00
Korea Centralkoreacentral$24.00 $90.00 $2.40 $30.00
North Central USnorthcentralus$22.00 $82.50 $2.20 $27.50
Norway Eastnorwayeast$24.00 $90.00 $2.40 $30.00
Poland Centralpolandcentral$24.00 $90.00 $2.40 $30.00
South Central USsouthcentralus$22.00 $82.50 $2.20 $27.50
South Indiasouthindia$24.00 $90.00 $2.40 $30.00
Spain Centralspaincentral$24.00 $90.00 $2.40 $30.00
Sweden Centralswedencentral$24.00 $90.00 $2.40 $30.00
Switzerland Northswitzerlandnorth$24.00 $90.00 $2.40 $30.00
Switzerland Westswitzerlandwest$24.00 $90.00 $2.40 $30.00
West Europewesteurope$24.00 $90.00 $2.40 $30.00
West USwestus$22.00 $82.50 $2.20 $27.50
West US 3westus3$22.00 $82.50 $2.20 $27.50

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
$0.08
Per month
$800.00

Across 27 published price regions.

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

50% cached input

Per request
$0.0665
Per month
$665.00

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-6 Astra 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$10.00 $50.00 $1.00 $12.50
Brazil Southbrazilsouth$10.00 $50.00 $1.00 $12.50
Canada Centralcanadacentral$10.00 $50.00 $1.00 $12.50
Canada Eastcanadaeast$10.00 $50.00 $1.00 $12.50
Central UScentralus$10.00 $50.00 $1.00 $12.50
East USeastus$10.00 $50.00 $1.00 $12.50
East US 2eastus2$10.00 $50.00 $1.00 $12.50
France Centralfrancecentral$10.00 $50.00 $1.00 $12.50
Germany West Centralgermanywestcentral$10.00 $50.00 $1.00 $12.50
Italy Northitalynorth$10.00 $50.00 $1.00 $12.50
Japan Eastjapaneast$10.00 $50.00 $1.00 $12.50
Korea Centralkoreacentral$10.00 $50.00 $1.00 $12.50
North Central USnorthcentralus$10.00 $50.00 $1.00 $12.50
Norway Eastnorwayeast$10.00 $50.00 $1.00 $12.50
Poland Centralpolandcentral$10.00 $50.00 $1.00 $12.50
South Africa Northsouthafricanorth$10.00 $50.00 $1.00 $12.50
South Central USsouthcentralus$10.00 $50.00 $1.00 $12.50
South Indiasouthindia$10.00 $50.00 $1.00 $12.50
Spain Centralspaincentral$10.00 $50.00 $1.00 $12.50
Sweden Centralswedencentral$10.00 $50.00 $1.00 $12.50
Switzerland Northswitzerlandnorth$10.00 $50.00 $1.00 $12.50
Switzerland Westswitzerlandwest$10.00 $50.00 $1.00 $12.50
UAE Northuaenorth$10.00 $50.00 $1.00 $12.50
UK Southuksouth$10.00 $50.00 $1.00 $12.50
West Europewesteurope$10.00 $50.00 $1.00 $12.50
West USwestus$10.00 $50.00 $1.00 $12.50
West US 3westus3$10.00 $50.00 $1.00 $12.50

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
$5.51502
Per month
$55,150.20

Across 27 published price regions.

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

50% cached input

Per request
$3.067011
Per month
$30,670.11

Across 27 published price regions.

Customize workload or price region for Global Standard - Long context, 50% cached input
View 27 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-6 Astra 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$20.00 $75.00 $2.00 $25.00
Brazil Southbrazilsouth$20.00 $75.00 $2.00 $25.00
Canada Centralcanadacentral$20.00 $75.00 $2.00 $25.00
Canada Eastcanadaeast$20.00 $75.00 $2.00 $25.00
Central UScentralus$20.00 $75.00 $2.00 $25.00
East USeastus$20.00 $75.00 $2.00 $25.00
East US 2eastus2$20.00 $75.00 $2.00 $25.00
France Centralfrancecentral$20.00 $75.00 $2.00 $25.00
Germany West Centralgermanywestcentral$20.00 $75.00 $2.00 $25.00
Italy Northitalynorth$20.00 $75.00 $2.00 $25.00
Japan Eastjapaneast$20.00 $75.00 $2.00 $25.00
Korea Centralkoreacentral$20.00 $75.00 $2.00 $25.00
North Central USnorthcentralus$20.00 $75.00 $2.00 $25.00
Norway Eastnorwayeast$20.00 $75.00 $2.00 $25.00
Poland Centralpolandcentral$20.00 $75.00 $2.00 $25.00
South Africa Northsouthafricanorth$20.00 $75.00 $2.00 $25.00
South Central USsouthcentralus$20.00 $75.00 $2.00 $25.00
South Indiasouthindia$20.00 $75.00 $2.00 $25.00
Spain Centralspaincentral$20.00 $75.00 $2.00 $25.00
Sweden Centralswedencentral$20.00 $75.00 $2.00 $25.00
Switzerland Northswitzerlandnorth$20.00 $75.00 $2.00 $25.00
Switzerland Westswitzerlandwest$20.00 $75.00 $2.00 $25.00
UAE Northuaenorth$20.00 $75.00 $2.00 $25.00
UK Southuksouth$20.00 $75.00 $2.00 $25.00
West Europewesteurope$20.00 $75.00 $2.00 $25.00
West USwestus$20.00 $75.00 $2.00 $25.00
West US 3westus3$20.00 $75.00 $2.00 $25.00

Model information and limits

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Metadata model ID
gpt-6-astra
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