GPT-5.6 Luna Azure pricing

GPT-5.6 Luna costs $0.20 input and $1.20 output per 1M tokens on Azure (Global Standard). Compare 10 deployment types across 26 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.

GPT-5.6 Luna OpenAI token prices.
Deployment type	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M	Price regions
Global Standard	$0.20	$1.20	$0.02	$0.25	25
Data Zone Standard	$0.22	$1.32	$0.022	$0.275	13
Data Zone Standard - Long context	$0.44	$1.98	$0.044	$0.55	13
Global Standard - Long context	$0.40	$1.80	$0.04	$0.50	25
Data Zone Priority	$0.44	$2.64	$0.044	$0.55	13
Global Flex	$0.10	$0.60	$0.01	$0.125	25
Global Priority	$0.40	$2.40	$0.04	$0.50	24
Data Zone Priority - Long context	$0.88	$3.96	$0.088	$1.10	13
Global Flex - Long context	$0.20	$0.90	$0.02	$0.25	25
Global Priority - Long context	$0.80	$3.60	$0.08	$1.00	25

Global Standard

Input / 1M: $0.20
Output / 1M: $1.20

Cache rates and 25 price regions

Cached input / 1M: $0.02
Cache write / 1M: $0.25

Data Zone Standard

Input / 1M: $0.22
Output / 1M: $1.32

Cache rates and 13 price regions

Cached input / 1M: $0.022
Cache write / 1M: $0.275

Data Zone Standard - Long context

Input / 1M: $0.44
Output / 1M: $1.98

Cache rates and 13 price regions

Cached input / 1M: $0.044
Cache write / 1M: $0.55

Global Standard - Long context

Input / 1M: $0.40
Output / 1M: $1.80

Cache rates and 25 price regions

Cached input / 1M: $0.04
Cache write / 1M: $0.50

Data Zone Priority

Input / 1M: $0.44
Output / 1M: $2.64

Cache rates and 13 price regions

Cached input / 1M: $0.044
Cache write / 1M: $0.55

Global Flex

Input / 1M: $0.10
Output / 1M: $0.60

Cache rates and 25 price regions

Cached input / 1M: $0.01
Cache write / 1M: $0.125

Global Priority

Input / 1M: $0.40
Output / 1M: $2.40

Cache rates and 24 price regions

Cached input / 1M: $0.04
Cache write / 1M: $0.50

Data Zone Priority - Long context

Input / 1M: $0.88
Output / 1M: $3.96

Cache rates and 13 price regions

Cached input / 1M: $0.088
Cache write / 1M: $1.10

Global Flex - Long context

Input / 1M: $0.20
Output / 1M: $0.90

Cache rates and 25 price regions

Cached input / 1M: $0.02
Cache write / 1M: $0.25

Global Priority - Long context

Input / 1M: $0.80
Output / 1M: $3.60

Cache rates and 25 price regions

Cached input / 1M: $0.08
Cache write / 1M: $1.00

Model information and limits

Cost-efficient GPT-5.6 model for fast, high-volume workloads

Model ID: gpt-5.6-luna
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

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	$18.00	$15.30
Data Zone Standard	$19.80	$16.83
Data Zone Priority	$39.60	$33.66
Global Flex	$9.00	$7.65
Global Priority	$36.00	$30.60

Global Standard

No cached input / month: $18.00
50% cached input / month: $15.30

Data Zone Standard

No cached input / month: $19.80
50% cached input / month: $16.83

Data Zone Priority

No cached input / month: $39.60
50% cached input / month: $33.66

Global Flex

No cached input / month: $9.00
50% cached input / month: $7.65

Global Priority

No cached input / month: $36.00
50% cached input / month: $30.60

Per-request costs

Token costs per request for the stated workload.
Deployment type	No cached input	50% cached input
Global Standard	$0.0018	$0.00153
Data Zone Standard	$0.00198	$0.001683
Data Zone Priority	$0.00396	$0.003366
Global Flex	$0.0009	$0.000765
Global Priority	$0.0036	$0.00306

272,001 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
Data Zone Standard - Long context	$1,216.60	$678.04
Global Standard - Long context	$1,106.00	$616.40
Data Zone Priority - Long context	$2,433.21	$1,356.08
Global Flex - Long context	$553.00	$308.20
Global Priority - Long context	$2,212.01	$1,232.80

Data Zone Standard - Long context

No cached input / month: $1,216.60
50% cached input / month: $678.04

Global Standard - Long context

No cached input / month: $1,106.00
50% cached input / month: $616.40

Data Zone Priority - Long context

No cached input / month: $2,433.21
50% cached input / month: $1,356.08

Global Flex - Long context

No cached input / month: $553.00
50% cached input / month: $308.20

Global Priority - Long context

No cached input / month: $2,212.01
50% cached input / month: $1,232.80

Per-request costs

Token costs per request for the stated workload.
Deployment type	No cached input	50% cached input
Data Zone Standard - Long context	$0.1217	$0.0678
Global Standard - Long context	$0.1106	$0.06164
Data Zone Priority - Long context	$0.2433	$0.1356
Global Flex - Long context	$0.0553	$0.03082
Global Priority - Long context	$0.2212	$0.1233

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.

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 25 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.

GPT-5.6 Luna Global Standard exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.20	$1.20	$0.02	$0.25
Brazil Southbrazilsouth	$0.20	$1.20	$0.02	$0.25
Canada Eastcanadaeast	$0.20	$1.20	$0.02	$0.25
Central UScentralus	$0.20	$1.20	$0.02	$0.25
East USeastus	$0.20	$1.20	$0.02	$0.25
East US 2eastus2	$0.20	$1.20	$0.02	$0.25
France Centralfrancecentral	$0.20	$1.20	$0.02	$0.25
Germany West Centralgermanywestcentral	$0.20	$1.20	$0.02	$0.25
Japan Eastjapaneast	$0.20	$1.20	$0.02	$0.25
Korea Centralkoreacentral	$0.20	$1.20	$0.02	$0.25
North Central USnorthcentralus	$0.20	$1.20	$0.02	$0.25
Norway Eastnorwayeast	$0.20	$1.20	$0.02	$0.25
Poland Centralpolandcentral	$0.20	$1.20	$0.02	$0.25
Qatar Centralqatarcentral	$0.20	$1.20	$0.02	$0.25
South Africa Northsouthafricanorth	$0.20	$1.20	$0.02	$0.25
South Central USsouthcentralus	$0.20	$1.20	$0.02	$0.25
South Indiasouthindia	$0.20	$1.20	$0.02	$0.25
Spain Centralspaincentral	$0.20	$1.20	$0.02	$0.25
Sweden Centralswedencentral	$0.20	$1.20	$0.02	$0.25
Switzerland Northswitzerlandnorth	$0.20	$1.20	$0.02	$0.25
UAE Northuaenorth	$0.20	$1.20	$0.02	$0.25
UK Southuksouth	$0.20	$1.20	$0.02	$0.25
West Europewesteurope	$0.20	$1.20	$0.02	$0.25
West USwestus	$0.20	$1.20	$0.02	$0.25
West US 3westus3	$0.20	$1.20	$0.02	$0.25

Data Zone Standard 13 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.

GPT-5.6 Luna Data Zone Standard exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Central UScentralus	$0.22	$1.32	$0.022	$0.275
East USeastus	$0.22	$1.32	$0.022	$0.275
East US 2eastus2	$0.22	$1.32	$0.022	$0.275
France Centralfrancecentral	$0.22	$1.32	$0.022	$0.275
Germany West Centralgermanywestcentral	$0.22	$1.32	$0.022	$0.275
North Central USnorthcentralus	$0.22	$1.32	$0.022	$0.275
Poland Centralpolandcentral	$0.22	$1.32	$0.022	$0.275
South Central USsouthcentralus	$0.22	$1.32	$0.022	$0.275
Spain Centralspaincentral	$0.22	$1.32	$0.022	$0.275
Sweden Centralswedencentral	$0.22	$1.32	$0.022	$0.275
West Europewesteurope	$0.22	$1.32	$0.022	$0.275
West USwestus	$0.22	$1.32	$0.022	$0.275
West US 3westus3	$0.22	$1.32	$0.022	$0.275

Data Zone Standard - Long context 13 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.

Long-context prices apply. The token threshold that activates them is model-specific. Applies above 272,000 input tokens.

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

GPT-5.6 Luna Data Zone Standard - Long context exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Central UScentralus	$0.44	$1.98	$0.044	$0.55
East USeastus	$0.44	$1.98	$0.044	$0.55
East US 2eastus2	$0.44	$1.98	$0.044	$0.55
France Centralfrancecentral	$0.44	$1.98	$0.044	$0.55
Germany West Centralgermanywestcentral	$0.44	$1.98	$0.044	$0.55
North Central USnorthcentralus	$0.44	$1.98	$0.044	$0.55
Poland Centralpolandcentral	$0.44	$1.98	$0.044	$0.55
South Central USsouthcentralus	$0.44	$1.98	$0.044	$0.55
Spain Centralspaincentral	$0.44	$1.98	$0.044	$0.55
Sweden Centralswedencentral	$0.44	$1.98	$0.044	$0.55
West Europewesteurope	$0.44	$1.98	$0.044	$0.55
West USwestus	$0.44	$1.98	$0.044	$0.55
West US 3westus3	$0.44	$1.98	$0.044	$0.55

Global Standard - Long context 25 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.

Long-context prices apply. The token threshold that activates them is model-specific. Applies above 272,000 input tokens.

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

GPT-5.6 Luna Global Standard - Long context exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.40	$1.80	$0.04	$0.50
Brazil Southbrazilsouth	$0.40	$1.80	$0.04	$0.50
Canada Eastcanadaeast	$0.40	$1.80	$0.04	$0.50
Central UScentralus	$0.40	$1.80	$0.04	$0.50
East USeastus	$0.40	$1.80	$0.04	$0.50
East US 2eastus2	$0.40	$1.80	$0.04	$0.50
France Centralfrancecentral	$0.40	$1.80	$0.04	$0.50
Germany West Centralgermanywestcentral	$0.40	$1.80	$0.04	$0.50
Japan Eastjapaneast	$0.40	$1.80	$0.04	$0.50
Korea Centralkoreacentral	$0.40	$1.80	$0.04	$0.50
North Central USnorthcentralus	$0.40	$1.80	$0.04	$0.50
Norway Eastnorwayeast	$0.40	$1.80	$0.04	$0.50
Poland Centralpolandcentral	$0.40	$1.80	$0.04	$0.50
Qatar Centralqatarcentral	$0.40	$1.80	$0.04	$0.50
South Africa Northsouthafricanorth	$0.40	$1.80	$0.04	$0.50
South Central USsouthcentralus	$0.40	$1.80	$0.04	$0.50
South Indiasouthindia	$0.40	$1.80	$0.04	$0.50
Spain Centralspaincentral	$0.40	$1.80	$0.04	$0.50
Sweden Centralswedencentral	$0.40	$1.80	$0.04	$0.50
Switzerland Northswitzerlandnorth	$0.40	$1.80	$0.04	$0.50
UAE Northuaenorth	$0.40	$1.80	$0.04	$0.50
UK Southuksouth	$0.40	$1.80	$0.04	$0.50
West Europewesteurope	$0.40	$1.80	$0.04	$0.50
West USwestus	$0.40	$1.80	$0.04	$0.50
West US 3westus3	$0.40	$1.80	$0.04	$0.50

Data Zone Priority 13 price regions

Data Zone processing: Inference data is processed within the Microsoft-specified US, EU, or APAC data zone.
Priority pay-per-token: Priority processing uses pay-as-you-go token prices for faster responses. Model and deployment support varies.

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

GPT-5.6 Luna Data Zone Priority exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Central UScentralus	$0.44	$2.64	$0.044	$0.55
East USeastus	$0.44	$2.64	$0.044	$0.55
East US 2eastus2	$0.44	$2.64	$0.044	$0.55
France Centralfrancecentral	$0.44	$2.64	$0.044	$0.55
Germany West Centralgermanywestcentral	$0.44	$2.64	$0.044	$0.55
North Central USnorthcentralus	$0.44	$2.64	$0.044	$0.55
Poland Centralpolandcentral	$0.44	$2.64	$0.044	$0.55
South Central USsouthcentralus	$0.44	$2.64	$0.044	$0.55
Spain Centralspaincentral	$0.44	$2.64	$0.044	$0.55
Sweden Centralswedencentral	$0.44	$2.64	$0.044	$0.55
West Europewesteurope	$0.44	$2.64	$0.044	$0.55
West USwestus	$0.44	$2.64	$0.044	$0.55
West US 3westus3	$0.44	$2.64	$0.044	$0.55

Global Flex 25 price regions

Global processing: Inference data may be processed in any Azure region.
Flex pay-per-token: Input and output usage is billed at the model's published Flex token rates. Model and deployment support varies.

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

GPT-5.6 Luna Global Flex exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.10	$0.60	$0.01	$0.125
Brazil Southbrazilsouth	$0.10	$0.60	$0.01	$0.125
Canada Eastcanadaeast	$0.10	$0.60	$0.01	$0.125
Central UScentralus	$0.10	$0.60	$0.01	$0.125
East USeastus	$0.10	$0.60	$0.01	$0.125
East US 2eastus2	$0.10	$0.60	$0.01	$0.125
France Centralfrancecentral	$0.10	$0.60	$0.01	$0.125
Germany West Centralgermanywestcentral	$0.10	$0.60	$0.01	$0.125
Japan Eastjapaneast	$0.10	$0.60	$0.01	$0.125
Korea Centralkoreacentral	$0.10	$0.60	$0.01	$0.125
Malaysia Westmalaysiawest	$0.10	$0.60	$0.01	$0.125
North Central USnorthcentralus	$0.10	$0.60	$0.01	$0.125
Norway Eastnorwayeast	$0.10	$0.60	$0.01	$0.125
Poland Centralpolandcentral	$0.10	$0.60	$0.01	$0.125
South Africa Northsouthafricanorth	$0.10	$0.60	$0.01	$0.125
South Central USsouthcentralus	$0.10	$0.60	$0.01	$0.125
South Indiasouthindia	$0.10	$0.60	$0.01	$0.125
Spain Centralspaincentral	$0.10	$0.60	$0.01	$0.125
Sweden Centralswedencentral	$0.10	$0.60	$0.01	$0.125
Switzerland Northswitzerlandnorth	$0.10	$0.60	$0.01	$0.125
UAE Northuaenorth	$0.10	$0.60	$0.01	$0.125
UK Southuksouth	$0.10	$0.60	$0.01	$0.125
West Europewesteurope	$0.10	$0.60	$0.01	$0.125
West USwestus	$0.10	$0.60	$0.01	$0.125
West US 3westus3	$0.10	$0.60	$0.01	$0.125

Global Priority 24 price regions

Global processing: Inference data may be processed in any Azure region.
Priority pay-per-token: Priority processing uses pay-as-you-go token prices for faster responses. Model and deployment support varies.

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

GPT-5.6 Luna Global Priority exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.40	$2.40	$0.04	$0.50
Brazil Southbrazilsouth	$0.40	$2.40	$0.04	$0.50
Canada Eastcanadaeast	$0.40	$2.40	$0.04	$0.50
Central UScentralus	$0.40	$2.40	$0.04	$0.50
East USeastus	$0.40	$2.40	$0.04	$0.50
East US 2eastus2	$0.40	$2.40	$0.04	$0.50
France Centralfrancecentral	$0.40	$2.40	$0.04	$0.50
Germany West Centralgermanywestcentral	$0.40	$2.40	$0.04	$0.50
Japan Eastjapaneast	$0.40	$2.40	$0.04	$0.50
Korea Centralkoreacentral	$0.40	$2.40	$0.04	$0.50
North Central USnorthcentralus	$0.40	$2.40	$0.04	$0.50
Norway Eastnorwayeast	$0.40	$2.40	$0.04	$0.50
Poland Centralpolandcentral	$0.40	$2.40	$0.04	$0.50
South Africa Northsouthafricanorth	$0.40	$2.40	$0.04	$0.50
South Central USsouthcentralus	$0.40	$2.40	$0.04	$0.50
South Indiasouthindia	$0.40	$2.40	$0.04	$0.50
Spain Centralspaincentral	$0.40	$2.40	$0.04	$0.50
Sweden Centralswedencentral	$0.40	$2.40	$0.04	$0.50
Switzerland Northswitzerlandnorth	$0.40	$2.40	$0.04	$0.50
UAE Northuaenorth	$0.40	$2.40	$0.04	$0.50
UK Southuksouth	$0.40	$2.40	$0.04	$0.50
West Europewesteurope	$0.40	$2.40	$0.04	$0.50
West USwestus	$0.40	$2.40	$0.04	$0.50
West US 3westus3	$0.40	$2.40	$0.04	$0.50

Data Zone Priority - Long context 13 price regions

Data Zone processing: Inference data is processed within the Microsoft-specified US, EU, or APAC data zone.
Priority pay-per-token: Priority processing uses pay-as-you-go token prices for faster responses. Model and deployment support varies.

Long-context prices apply. The token threshold that activates them is model-specific. Applies above 272,000 input tokens.

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

GPT-5.6 Luna Data Zone Priority - Long context exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Central UScentralus	$0.88	$3.96	$0.088	$1.10
East USeastus	$0.88	$3.96	$0.088	$1.10
East US 2eastus2	$0.88	$3.96	$0.088	$1.10
France Centralfrancecentral	$0.88	$3.96	$0.088	$1.10
Germany West Centralgermanywestcentral	$0.88	$3.96	$0.088	$1.10
North Central USnorthcentralus	$0.88	$3.96	$0.088	$1.10
Poland Centralpolandcentral	$0.88	$3.96	$0.088	$1.10
South Central USsouthcentralus	$0.88	$3.96	$0.088	$1.10
Spain Centralspaincentral	$0.88	$3.96	$0.088	$1.10
Sweden Centralswedencentral	$0.88	$3.96	$0.088	$1.10
West Europewesteurope	$0.88	$3.96	$0.088	$1.10
West USwestus	$0.88	$3.96	$0.088	$1.10
West US 3westus3	$0.88	$3.96	$0.088	$1.10

Global Flex - Long context 25 price regions

Global processing: Inference data may be processed in any Azure region.
Flex pay-per-token: Input and output usage is billed at the model's published Flex token rates. Model and deployment support varies.

Long-context prices apply. The token threshold that activates them is model-specific. Applies above 272,000 input tokens.

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

GPT-5.6 Luna Global Flex - Long context exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.20	$0.90	$0.02	$0.25
Brazil Southbrazilsouth	$0.20	$0.90	$0.02	$0.25
Canada Eastcanadaeast	$0.20	$0.90	$0.02	$0.25
Central UScentralus	$0.20	$0.90	$0.02	$0.25
East USeastus	$0.20	$0.90	$0.02	$0.25
East US 2eastus2	$0.20	$0.90	$0.02	$0.25
France Centralfrancecentral	$0.20	$0.90	$0.02	$0.25
Germany West Centralgermanywestcentral	$0.20	$0.90	$0.02	$0.25
Japan Eastjapaneast	$0.20	$0.90	$0.02	$0.25
Korea Centralkoreacentral	$0.20	$0.90	$0.02	$0.25
Malaysia Westmalaysiawest	$0.20	$0.90	$0.02	$0.25
North Central USnorthcentralus	$0.20	$0.90	$0.02	$0.25
Norway Eastnorwayeast	$0.20	$0.90	$0.02	$0.25
Poland Centralpolandcentral	$0.20	$0.90	$0.02	$0.25
South Africa Northsouthafricanorth	$0.20	$0.90	$0.02	$0.25
South Central USsouthcentralus	$0.20	$0.90	$0.02	$0.25
South Indiasouthindia	$0.20	$0.90	$0.02	$0.25
Spain Centralspaincentral	$0.20	$0.90	$0.02	$0.25
Sweden Centralswedencentral	$0.20	$0.90	$0.02	$0.25
Switzerland Northswitzerlandnorth	$0.20	$0.90	$0.02	$0.25
UAE Northuaenorth	$0.20	$0.90	$0.02	$0.25
UK Southuksouth	$0.20	$0.90	$0.02	$0.25
West Europewesteurope	$0.20	$0.90	$0.02	$0.25
West USwestus	$0.20	$0.90	$0.02	$0.25
West US 3westus3	$0.20	$0.90	$0.02	$0.25

Global Priority - Long context 25 price regions

Global processing: Inference data may be processed in any Azure region.
Priority pay-per-token: Priority processing uses pay-as-you-go token prices for faster responses. Model and deployment support varies.

Long-context prices apply. The token threshold that activates them is model-specific. Applies above 272,000 input tokens.

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

GPT-5.6 Luna Global Priority - Long context exact regional rates.
Price region	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M
Australia Eastaustraliaeast	$0.80	$3.60	$0.08	$1.00
Brazil Southbrazilsouth	$0.80	$3.60	$0.08	$1.00
Canada Eastcanadaeast	$0.80	$3.60	$0.08	$1.00
Central UScentralus	$0.80	$3.60	$0.08	$1.00
East USeastus	$0.80	$3.60	$0.08	$1.00
East US 2eastus2	$0.80	$3.60	$0.08	$1.00
France Centralfrancecentral	$0.80	$3.60	$0.08	$1.00
Germany West Centralgermanywestcentral	$0.80	$3.60	$0.08	$1.00
Japan Eastjapaneast	$0.80	$3.60	$0.08	$1.00
Korea Centralkoreacentral	$0.80	$3.60	$0.08	$1.00
Malaysia Westmalaysiawest	$0.80	$3.60	$0.08	$1.00
North Central USnorthcentralus	$0.80	$3.60	$0.08	$1.00
Norway Eastnorwayeast	$0.80	$3.60	$0.08	$1.00
Poland Centralpolandcentral	$0.80	$3.60	$0.08	$1.00
South Africa Northsouthafricanorth	$0.80	$3.60	$0.08	$1.00
South Central USsouthcentralus	$0.80	$3.60	$0.08	$1.00
South Indiasouthindia	$0.80	$3.60	$0.08	$1.00
Spain Centralspaincentral	$0.80	$3.60	$0.08	$1.00
Sweden Centralswedencentral	$0.80	$3.60	$0.08	$1.00
Switzerland Northswitzerlandnorth	$0.80	$3.60	$0.08	$1.00
UAE Northuaenorth	$0.80	$3.60	$0.08	$1.00
UK Southuksouth	$0.80	$3.60	$0.08	$1.00
West Europewesteurope	$0.80	$3.60	$0.08	$1.00
West USwestus	$0.80	$3.60	$0.08	$1.00
West US 3westus3	$0.80	$3.60	$0.08	$1.00

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.

GPT-5.6 Luna
OpenAI · Current model · Global Standard
Input
$0.20
Output
$1.20
GPT-6 Luna
OpenAI · Same family · Global Standard
Input
$0.10
Output
$0.50
Compare
GPT-6.1 Sol
OpenAI · Same provider · Global Standard
Input
$2.00
Output
$10.00
Compare
GPT-6 Sol
OpenAI · Same provider · Global Standard
Input
$2.00
Output
$10.00
Compare
Code 1.1 Flash
Microsoft · Similar price · Global Standard
Input
$0.20
Output
$1.20
Compare
Llama 3.3 70B
Meta · Similar price · Global Standard
Input
$0.71
Output
$0.71
Compare
GPT-6 Astra
OpenAI · Same provider · Global Standard
Input
$10.00
Output
$50.00
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