o4 mini 0416 Azure pricing

o4 mini 0416 costs $1.10 input and $4.40 output per 1M tokens on Azure (Global Standard). Compare 5 deployment types across 30 price regions.

OpenAIText generationUSD / 1M tokens

Estimate token cost

Prices by deployment type

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

o4 mini 0416 OpenAI token prices.
Deployment type	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M	Price regions
Global Standard	$1.10	$4.40	$0.275	Not published	26
Data Zone Standard	$1.21 - $1.32	$4.84 - $5.28	$0.303 - $0.33	Not published	23
Regional Standard	$1.21 - $1.331	$4.84 - $5.324	$0.303 - $0.333	Not published	7
Data Zone Batch	$0.605 - $0.66	$2.42 - $2.64	Not published	Not published	23
Global Batch	$0.55	$2.20	Not published	Not published	25

Global Standard

Input / 1M: $1.10
Output / 1M: $4.40

Cache rates and 26 price regions

Cached input / 1M: $0.275
Cache write / 1M: Not published

Data Zone Standard

Input / 1M: $1.21 - $1.32
Output / 1M: $4.84 - $5.28

Cache rates and 23 price regions

Cached input / 1M: $0.303 - $0.33
Cache write / 1M: Not published

Regional Standard

Input / 1M: $1.21 - $1.331
Output / 1M: $4.84 - $5.324

Cache rates and 7 price regions

Cached input / 1M: $0.303 - $0.333
Cache write / 1M: Not published

Data Zone Batch

Input / 1M: $0.605 - $0.66
Output / 1M: $2.42 - $2.64

Cache rates and 23 price regions

Cached input / 1M: Not published
Cache write / 1M: Not published

Global Batch

Input / 1M: $0.55
Output / 1M: $2.20

Cache rates and 25 price regions

Cached input / 1M: Not published
Cache write / 1M: Not published

Model information and limits

Fast o-series model for compact reasoning, coding, and tool use

Input modalities: Not published
Output modalities: Not published
Context window (tokens): 200,000
Maximum input tokens: Not published
Maximum output tokens: 100,000
Reasoning: Yes
Tool calling: Yes
Structured output: Not published

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.

Monthly costs for the stated workload, by deployment type and cache usage.
Deployment type	No cached input / month	50% cached input / month
Global Standard	$77.00	$64.63
Data Zone Standard	$84.70 - $92.40	$71.10 - $77.55
Regional Standard	$84.70 - $93.17	$71.10 - $78.20
Data Zone Batch	$42.35 - $46.20	Published cached input prices are missing for this workload in one or more matching price regions. Select a region with complete prices.
Global Batch	$38.50	Published cached input prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

Global Standard

No cached input / month: $77.00
50% cached input / month: $64.63

Data Zone Standard

No cached input / month: $84.70 - $92.40
50% cached input / month: $71.10 - $77.55

Regional Standard

No cached input / month: $84.70 - $93.17
50% cached input / month: $71.10 - $78.20

Data Zone Batch

No cached input / month: $42.35 - $46.20
50% cached input / month: Published cached input prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

Global Batch

No cached input / month: $38.50
50% cached input / month: Published cached input prices are missing for this workload in one or more matching price regions. Select a region with complete prices.

Per-request costs

Token costs per request for the stated workload.
Deployment type	No cached input	50% cached input
Global Standard	$0.0077	$0.006463
Data Zone Standard	$0.00847 - $0.00924	$0.00711 - $0.007755
Regional Standard	$0.00847 - $0.009317	$0.00711 - $0.00782
Data Zone Batch	$0.004235 - $0.00462	Unavailable
Global Batch	$0.00385	Unavailable

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 26 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.

o4 mini 0416 Global Standard exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$1.10	$4.40	$0.275	Not published
Brazil Southbrazilsouth	$1.10	$4.40	$0.275	Not published
Canada Eastcanadaeast	$1.10	$4.40	$0.275	Not published
Central UScentralus	$1.10	$4.40	$0.275	Not published
East USeastus	$1.10	$4.40	$0.275	Not published
East US 2eastus2	$1.10	$4.40	$0.275	Not published
France Centralfrancecentral	$1.10	$4.40	$0.275	Not published
Germany West Centralgermanywestcentral	$1.10	$4.40	$0.275	Not published
Italy Northitalynorth	$1.10	$4.40	$0.275	Not published
Japan Eastjapaneast	$1.10	$4.40	$0.275	Not published
Korea Centralkoreacentral	$1.10	$4.40	$0.275	Not published
North Central USnorthcentralus	$1.10	$4.40	$0.275	Not published
Norway Eastnorwayeast	$1.10	$4.40	$0.275	Not published
Poland Centralpolandcentral	$1.10	$4.40	$0.275	Not published
South Africa Northsouthafricanorth	$1.10	$4.40	$0.275	Not published
South Central USsouthcentralus	$1.10	$4.40	$0.275	Not published
South Indiasouthindia	$1.10	$4.40	$0.275	Not published
Southeast Asiasoutheastasia	$1.10	$4.40	$0.275	Not published
Spain Centralspaincentral	$1.10	$4.40	$0.275	Not published
Sweden Centralswedencentral	$1.10	$4.40	$0.275	Not published
Switzerland Northswitzerlandnorth	$1.10	$4.40	$0.275	Not published
UAE Northuaenorth	$1.10	$4.40	$0.275	Not published
UK Southuksouth	$1.10	$4.40	$0.275	Not published
West Europewesteurope	$1.10	$4.40	$0.275	Not published
West USwestus	$1.10	$4.40	$0.275	Not published
West US 3westus3	$1.10	$4.40	$0.275	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.

o4 mini 0416 Data Zone Standard exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$1.32	$5.28	$0.33	Not published
Central Indiacentralindia	$1.32	$5.28	$0.33	Not published
Central UScentralus	$1.21	$4.84	$0.303	Not published
East Asiaeastasia	$1.32	$5.28	$0.33	Not published
East USeastus	$1.21	$4.84	$0.303	Not published
East US 2eastus2	$1.21	$4.84	$0.303	Not published
France Centralfrancecentral	$1.21	$4.84	$0.303	Not published
Germany West Centralgermanywestcentral	$1.21	$4.84	$0.303	Not published
Italy Northitalynorth	$1.21	$4.84	$0.303	Not published
Japan Eastjapaneast	$1.32	$5.28	$0.33	Not published
Japan Westjapanwest	$1.32	$5.28	$0.33	Not published
Jio India Westjioindiawest	$1.32	$5.28	$0.33	Not published
Korea Centralkoreacentral	$1.32	$5.28	$0.33	Not published
North Central USnorthcentralus	$1.21	$4.84	$0.303	Not published
Poland Centralpolandcentral	$1.21	$4.84	$0.303	Not published
South Central USsouthcentralus	$1.21	$4.84	$0.303	Not published
South Indiasouthindia	$1.32	$5.28	$0.33	Not published
Southeast Asiasoutheastasia	$1.32	$5.28	$0.33	Not published
Spain Centralspaincentral	$1.21	$4.84	$0.303	Not published
Sweden Centralswedencentral	$1.21	$4.84	$0.303	Not published
West Europewesteurope	$1.21	$4.84	$0.303	Not published
West USwestus	$1.21	$4.84	$0.303	Not published
West US 3westus3	$1.21	$4.84	$0.303	Not published

Regional Standard 7 price regions

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.

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

o4 mini 0416 Regional Standard exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
East USeastus	$1.21	$4.84	$0.303	Not published
East US 2eastus2	$1.21	$4.84	$0.303	Not published
North Central USnorthcentralus	$1.21	$4.84	$0.303	Not published
South Central USsouthcentralus	$1.21	$4.84	$0.303	Not published
Sweden Centralswedencentral	$1.331	$5.324	$0.333	Not published
West USwestus	$1.21	$4.84	$0.303	Not published
West US 3westus3	$1.21	$4.84	$0.303	Not published

Data Zone Batch 23 price regions

Data Zone processing: Inference data is processed within the Microsoft-specified US, EU, or APAC data zone.
Asynchronous Batch: Batch prices 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.

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

o4 mini 0416 Data Zone Batch exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.66	$2.64	Not published	Not published
Central Indiacentralindia	$0.66	$2.64	Not published	Not published
Central UScentralus	$0.605	$2.42	Not published	Not published
East Asiaeastasia	$0.66	$2.64	Not published	Not published
East USeastus	$0.605	$2.42	Not published	Not published
East US 2eastus2	$0.605	$2.42	Not published	Not published
France Centralfrancecentral	$0.605	$2.42	Not published	Not published
Germany West Centralgermanywestcentral	$0.605	$2.42	Not published	Not published
Italy Northitalynorth	$0.605	$2.42	Not published	Not published
Japan Eastjapaneast	$0.66	$2.64	Not published	Not published
Japan Westjapanwest	$0.66	$2.64	Not published	Not published
Jio India Westjioindiawest	$0.66	$2.64	Not published	Not published
Korea Centralkoreacentral	$0.66	$2.64	Not published	Not published
North Central USnorthcentralus	$0.605	$2.42	Not published	Not published
Poland Centralpolandcentral	$0.605	$2.42	Not published	Not published
South Central USsouthcentralus	$0.605	$2.42	Not published	Not published
South Indiasouthindia	$0.66	$2.64	Not published	Not published
Southeast Asiasoutheastasia	$0.66	$2.64	Not published	Not published
Spain Centralspaincentral	$0.605	$2.42	Not published	Not published
Sweden Centralswedencentral	$0.605	$2.42	Not published	Not published
West Europewesteurope	$0.605	$2.42	Not published	Not published
West USwestus	$0.605	$2.42	Not published	Not published
West US 3westus3	$0.605	$2.42	Not published	Not published

Global Batch 25 price regions

Global processing: Inference data may be processed in any Azure region.
Asynchronous Batch: Batch prices 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.

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

o4 mini 0416 Global Batch exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.55	$2.20	Not published	Not published
Brazil Southbrazilsouth	$0.55	$2.20	Not published	Not published
Canada Eastcanadaeast	$0.55	$2.20	Not published	Not published
Central UScentralus	$0.55	$2.20	Not published	Not published
East USeastus	$0.55	$2.20	Not published	Not published
East US 2eastus2	$0.55	$2.20	Not published	Not published
France Centralfrancecentral	$0.55	$2.20	Not published	Not published
Germany West Centralgermanywestcentral	$0.55	$2.20	Not published	Not published
Italy Northitalynorth	$0.55	$2.20	Not published	Not published
Japan Eastjapaneast	$0.55	$2.20	Not published	Not published
Korea Centralkoreacentral	$0.55	$2.20	Not published	Not published
North Central USnorthcentralus	$0.55	$2.20	Not published	Not published
Norway Eastnorwayeast	$0.55	$2.20	Not published	Not published
Poland Centralpolandcentral	$0.55	$2.20	Not published	Not published
South Africa Northsouthafricanorth	$0.55	$2.20	Not published	Not published
South Central USsouthcentralus	$0.55	$2.20	Not published	Not published
South Indiasouthindia	$0.55	$2.20	Not published	Not published
Spain Centralspaincentral	$0.55	$2.20	Not published	Not published
Sweden Centralswedencentral	$0.55	$2.20	Not published	Not published
Switzerland Northswitzerlandnorth	$0.55	$2.20	Not published	Not published
UAE Northuaenorth	$0.55	$2.20	Not published	Not published
UK Southuksouth	$0.55	$2.20	Not published	Not published
West Europewesteurope	$0.55	$2.20	Not published	Not published
West USwestus	$0.55	$2.20	Not published	Not published
West US 3westus3	$0.55	$2.20	Not published	Not published

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.

o4 mini 0416
OpenAI · Current model · Global Standard
Input
$1.10
Output
$4.40
o3 mini 0131
OpenAI · Same family · Global Standard
Input
$1.10
Output
$4.40
Compare
GPT-6.1 Sol
OpenAI · Same provider · Global Standard
Input
$2.00
Output
$10.00
Compare
GPT-6 Luna
OpenAI · Same provider · Global Standard
Input
$0.10
Output
$0.50
Compare
DeepSeek V3
DeepSeek · Similar price · Global Standard
Input
$1.14
Output
$4.56
Compare
DeepSeek V3 0324
DeepSeek · Similar price · Global Standard
Input
$1.14
Output
$4.56
Compare
GPT-6 Sol
OpenAI · Same provider · Global Standard
Input
$2.00
Output
$10.00
Compare

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.

Microsoft Foundry pricing
Review the official platform pricing overview and Azure purchasing guidance.
Microsoft Foundry model catalog
Browse the broader official model catalog, providers, APIs, and capabilities.
Foundry Models sold by Azure
Check model IDs, context windows, APIs, capabilities, and lifecycle guidance.
Azure OpenAI pricing
Review Microsoft's public model tables and current Azure OpenAI list prices.
Foundry deployment types
Understand data processing scope, pay-per-token, Batch, and provisioned PTUs.

Browse all Azure AI model prices