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.

DeepSeek V4.1 Flash DeepSeek prices in USD per 1 million tokens.
Deployment typeInput / 1MOutput / 1MCached input / 1MCache write / 1MPrice regions
Global Standard $0.30 $1.20 $0.006 Not published 40
Data Zone Standard $0.33 - $0.36 $1.32 - $1.44 $0.0066 - $0.0072 Not published 22

The tables contain only this DeepSeek 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.

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
$0.0021
Per month
$21.00

Across 40 published price regions.

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

50% cached input

Per request
$0.001659
Per month
$16.59

Across 40 published price regions.

Customize workload or price region for Global Standard, 50% cached input
View 40 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.

DeepSeek V4.1 Flash 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$0.30 $1.20 $0.006 Not published
Belgium Centralbelgiumcentral$0.30 $1.20 $0.006 Not published
Brazil Southbrazilsouth$0.30 $1.20 $0.006 Not published
Canada Centralcanadacentral$0.30 $1.20 $0.006 Not published
Canada Eastcanadaeast$0.30 $1.20 $0.006 Not published
Central Indiacentralindia$0.30 $1.20 $0.006 Not published
Central UScentralus$0.30 $1.20 $0.006 Not published
East Asiaeastasia$0.30 $1.20 $0.006 Not published
East USeastus$0.30 $1.20 $0.006 Not published
East US 2eastus2$0.30 $1.20 $0.006 Not published
France Centralfrancecentral$0.30 $1.20 $0.006 Not published
Germany Northgermanynorth$0.30 $1.20 $0.006 Not published
Germany West Centralgermanywestcentral$0.30 $1.20 $0.006 Not published
Italy Northitalynorth$0.30 $1.20 $0.006 Not published
Japan Eastjapaneast$0.30 $1.20 $0.006 Not published
Japan Westjapanwest$0.30 $1.20 $0.006 Not published
Jio India Westjioindiawest$0.30 $1.20 $0.006 Not published
Korea Centralkoreacentral$0.30 $1.20 $0.006 Not published
Malaysia Westmalaysiawest$0.30 $1.20 $0.006 Not published
North Central USnorthcentralus$0.30 $1.20 $0.006 Not published
North Europenortheurope$0.30 $1.20 $0.006 Not published
Norway Eastnorwayeast$0.30 $1.20 $0.006 Not published
Poland Centralpolandcentral$0.30 $1.20 $0.006 Not published
Qatar Centralqatarcentral$0.30 $1.20 $0.006 Not published
South Africa Northsouthafricanorth$0.30 $1.20 $0.006 Not published
South Central USsouthcentralus$0.30 $1.20 $0.006 Not published
South Indiasouthindia$0.30 $1.20 $0.006 Not published
Southeast Asiasoutheastasia$0.30 $1.20 $0.006 Not published
Spain Centralspaincentral$0.30 $1.20 $0.006 Not published
Sweden Centralswedencentral$0.30 $1.20 $0.006 Not published
Switzerland Northswitzerlandnorth$0.30 $1.20 $0.006 Not published
Switzerland Westswitzerlandwest$0.30 $1.20 $0.006 Not published
UAE Northuaenorth$0.30 $1.20 $0.006 Not published
UK Southuksouth$0.30 $1.20 $0.006 Not published
UK Westukwest$0.30 $1.20 $0.006 Not published
West Central USwestcentralus$0.30 $1.20 $0.006 Not published
West Europewesteurope$0.30 $1.20 $0.006 Not published
West USwestus$0.30 $1.20 $0.006 Not published
West US 2westus2$0.30 $1.20 $0.006 Not published
West US 3westus3$0.30 $1.20 $0.006 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
$0.00231 - $0.00252
Per month
$23.10 - $25.20

Across 22 published price regions.

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

50% cached input

Per request
$0.001825 - $0.001991
Per month
$18.25 - $19.91

Across 22 published price regions.

Customize workload or price region for Data Zone Standard, 50% cached input
View 22 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.

DeepSeek V4.1 Flash 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)
Belgium Centralbelgiumcentral$0.36 $1.44 $0.0072 Not published
Central UScentralus$0.33 $1.32 $0.0066 Not published
East USeastus$0.33 $1.32 $0.0066 Not published
East US 2eastus2$0.33 $1.32 $0.0066 Not published
France Centralfrancecentral$0.36 $1.44 $0.0072 Not published
Germany Northgermanynorth$0.36 $1.44 $0.0072 Not published
Germany West Centralgermanywestcentral$0.36 $1.44 $0.0072 Not published
Italy Northitalynorth$0.36 $1.44 $0.0072 Not published
North Central USnorthcentralus$0.33 $1.32 $0.0066 Not published
North Europenortheurope$0.36 $1.44 $0.0072 Not published
Norway Eastnorwayeast$0.36 $1.44 $0.0072 Not published
Poland Centralpolandcentral$0.36 $1.44 $0.0072 Not published
South Central USsouthcentralus$0.33 $1.32 $0.0066 Not published
Spain Centralspaincentral$0.36 $1.44 $0.0072 Not published
Sweden Centralswedencentral$0.36 $1.44 $0.0072 Not published
Switzerland Northswitzerlandnorth$0.36 $1.44 $0.0072 Not published
Switzerland Westswitzerlandwest$0.36 $1.44 $0.0072 Not published
West Central USwestcentralus$0.33 $1.32 $0.0066 Not published
West Europewesteurope$0.36 $1.44 $0.0072 Not published
West USwestus$0.33 $1.32 $0.0066 Not published
West US 2westus2$0.33 $1.32 $0.0066 Not published
West US 3westus3$0.33 $1.32 $0.0066 Not published

Model information and limits

DeepSeek V4.1 Flash model for reasoning and agentic coding

Metadata model ID
deepseek-v4.1-flash
Metadata match
Exact model
Input modalities
Text, Image
Output modalities
Text
Context window (tokens)
1,000,000
Maximum input tokens
Not published
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.

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

Similar models

Models from the same family or provider, and similarly priced models from other providers. Prices are USD per 1M tokens in each model's headline deployment type.

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