Azure Speed Test

Prices by deployment type

Rates are USD per 1 million tokens. Ranges reflect regional differences. Not published means Azure has not listed a rate.

Global Standard

Input / 1M
$1.74
Output / 1M
$3.48
Cache rates and 40 price regions
Cached input / 1M
$0.145
Cache write / 1M
Not published

Data Zone Standard

Input / 1M
$1.91
Output / 1M
$3.83
Cache rates and 23 price regions
Cached input / 1M
$0.16
Cache write / 1M
Not published

Model information and limits

Open MoE flagship with million-token context for coding and long agent runs

Model ID
deepseek-v4-pro
Input modalities
Text
Output modalities
Text
Context window (tokens)
1,000,000
Maximum input tokens
Not published
Maximum output tokens
384,000
Reasoning
Yes
Tool calling
No
Structured output
Yes
Microsoft Foundry model catalog

Cost examples

Customize workload

Monthly token costs in USD, with no cache writes. Select a cost to adjust that workload. Long-context workloads are shown separately.

3,000 input and 1,000 output tokens per request; 10,000 requests per month.

Global Standard

No cached input / month
$87.00
50% cached input / month
$63.07

Data Zone Standard

No cached input / month
$95.60
50% cached input / month
$69.35
Per-request costs
Token costs per request for the stated workload.
Deployment typeNo cached input50% cached input
Global Standard $0.0087 $0.006308
Data Zone Standard $0.00956 $0.006935
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 price complete workloads in each region, so input and output rates 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 cached example assumes half of the input tokens are eligible cache reads on every request. Actual cache hit rates and cache creation charges depend on the deployment. Missing cache rates are not replaced with ordinary input rates.

Estimates cover the displayed token categories before taxes, negotiated discounts, and separate hosting, tools, media, or provisioned-capacity charges.

Some token limits are unknown. Verify that your deployment supports the workload before using these estimates.

Regional prices and deployment guidance

Choose a deployment type to see its processing scope and exact regional rates. Prices do not guarantee deployment availability or quota.

Global Standard 40 price regions
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.

Rates are USD per 1 million tokens. Scroll horizontally for all rates on a small screen.

DeepSeek V4 Pro Global Standard exact regional rates.
Price regionInput / 1MOutput / 1MCached input / 1MCache write / 1M
Australia Eastaustraliaeast $1.74 $3.48 $0.145 Not published
Belgium Centralbelgiumcentral $1.74 $3.48 $0.145 Not published
Brazil Southbrazilsouth $1.74 $3.48 $0.145 Not published
Canada Centralcanadacentral $1.74 $3.48 $0.145 Not published
Canada Eastcanadaeast $1.74 $3.48 $0.145 Not published
Central Indiacentralindia $1.74 $3.48 $0.145 Not published
Central UScentralus $1.74 $3.48 $0.145 Not published
East Asiaeastasia $1.74 $3.48 $0.145 Not published
East USeastus $1.74 $3.48 $0.145 Not published
East US 2eastus2 $1.74 $3.48 $0.145 Not published
France Centralfrancecentral $1.74 $3.48 $0.145 Not published
Germany Northgermanynorth $1.74 $3.48 $0.145 Not published
Germany West Centralgermanywestcentral $1.74 $3.48 $0.145 Not published
Italy Northitalynorth $1.74 $3.48 $0.145 Not published
Japan Eastjapaneast $1.74 $3.48 $0.145 Not published
Japan Westjapanwest $1.74 $3.48 $0.145 Not published
Jio India Westjioindiawest $1.74 $3.48 $0.145 Not published
Korea Centralkoreacentral $1.74 $3.48 $0.145 Not published
Malaysia Westmalaysiawest $1.74 $3.48 $0.145 Not published
North Central USnorthcentralus $1.74 $3.48 $0.145 Not published
North Europenortheurope $1.74 $3.48 $0.145 Not published
Norway Eastnorwayeast $1.74 $3.48 $0.145 Not published
Poland Centralpolandcentral $1.74 $3.48 $0.145 Not published
Qatar Centralqatarcentral $1.74 $3.48 $0.145 Not published
South Africa Northsouthafricanorth $1.74 $3.48 $0.145 Not published
South Central USsouthcentralus $1.74 $3.48 $0.145 Not published
South Indiasouthindia $1.74 $3.48 $0.145 Not published
Southeast Asiasoutheastasia $1.74 $3.48 $0.145 Not published
Spain Centralspaincentral $1.74 $3.48 $0.145 Not published
Sweden Centralswedencentral $1.74 $3.48 $0.145 Not published
Switzerland Northswitzerlandnorth $1.74 $3.48 $0.145 Not published
Switzerland Westswitzerlandwest $1.74 $3.48 $0.145 Not published
UAE Northuaenorth $1.74 $3.48 $0.145 Not published
UK Southuksouth $1.74 $3.48 $0.145 Not published
UK Westukwest $1.74 $3.48 $0.145 Not published
West Central USwestcentralus $1.74 $3.48 $0.145 Not published
West Europewesteurope $1.74 $3.48 $0.145 Not published
West USwestus $1.74 $3.48 $0.145 Not published
West US 2westus2 $1.74 $3.48 $0.145 Not published
West US 3westus3 $1.74 $3.48 $0.145 Not published
Data Zone Standard 23 price regions
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.

Rates are USD per 1 million tokens. Scroll horizontally for all rates on a small screen.

DeepSeek V4 Pro Data Zone Standard exact regional rates.
Price regionInput / 1MOutput / 1MCached input / 1MCache write / 1M
Belgium Centralbelgiumcentral $1.91 $3.83 $0.16 Not published
Central UScentralus $1.91 $3.83 $0.16 Not published
East USeastus $1.91 $3.83 $0.16 Not published
East US 2eastus2 $1.91 $3.83 $0.16 Not published
France Centralfrancecentral $1.91 $3.83 $0.16 Not published
Germany Northgermanynorth $1.91 $3.83 $0.16 Not published
Germany West Centralgermanywestcentral $1.91 $3.83 $0.16 Not published
Italy Northitalynorth $1.91 $3.83 $0.16 Not published
North Central USnorthcentralus $1.91 $3.83 $0.16 Not published
North Europenortheurope $1.91 $3.83 $0.16 Not published
Norway Eastnorwayeast $1.91 $3.83 $0.16 Not published
Poland Centralpolandcentral $1.91 $3.83 $0.16 Not published
South Central USsouthcentralus $1.91 $3.83 $0.16 Not published
Spain Centralspaincentral $1.91 $3.83 $0.16 Not published
Sweden Centralswedencentral $1.91 $3.83 $0.16 Not published
Switzerland Northswitzerlandnorth $1.91 $3.83 $0.16 Not published
Switzerland Westswitzerlandwest $1.91 $3.83 $0.16 Not published
UK Westukwest $1.91 $3.83 $0.16 Not published
West Central USwestcentralus $1.91 $3.83 $0.16 Not published
West Europewesteurope $1.91 $3.83 $0.16 Not published
West USwestus $1.91 $3.83 $0.16 Not published
West US 2westus2 $1.91 $3.83 $0.16 Not published
West US 3westus3 $1.91 $3.83 $0.16 Not published

Check the provider, Azure product, and deployment type for each listing; their prices are independent.

Similar models

Compare the current model with related and similarly priced models. Rates are USD per 1M tokens in each model's stated deployment type.

Official pricing and deployment guidance

Prices are Microsoft's public token rates for Azure Public. Provisioned throughput, fine-tuning, media, and sovereign-cloud pricing are separate.

Browse all Azure AI model prices