GPT-6 Luna Azure Pricing
GPT-6 Luna costs $0.10 input and $0.50 output per 1M tokens on Azure (Global Standard). Compare 4 deployment types across 26 price regions. Azure lists it under Azure OpenAI GPT6 in Microsoft Foundry.
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.
| Deployment type | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Price regions |
|---|---|---|---|---|---|
| Data Zone Standard | $0.11 - $0.12 | $0.55 - $0.60 | $0.011 - $0.012 | $0.1375 - $0.15 | 13 |
| Data Zone Standard - Long context | $0.22 - $0.24 | $0.825 - $0.90 | $0.022 - $0.024 | $0.275 - $0.30 | 13 |
| Global Standard | $0.10 | $0.50 | $0.01 | $0.125 | 26 |
| Global Standard - Long context | $0.20 | $0.75 | $0.02 | $0.25 | 26 |
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
- $0.00088 - $0.00096
- Per month
- $8.80 - $9.60
Across 13 published price regions.
Customize workload or price region for Data Zone Standard, No cached input50% cached input
- Per request
- $0.0007315 - $0.000798
- Per month
- $7.315 - $7.98
Across 13 published price regions.
Customize workload or price region for Data Zone Standard, 50% cached inputView 13 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.
| Azure Public price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Meter effective dates (UTC) |
|---|---|---|---|---|---|
| Central UScentralus | $0.11 | $0.55 | $0.011 | $0.1375 | |
| East USeastus | $0.11 | $0.55 | $0.011 | $0.1375 | |
| East US 2eastus2 | $0.11 | $0.55 | $0.011 | $0.1375 | |
| France Centralfrancecentral | $0.12 | $0.60 | $0.012 | $0.15 | |
| Germany West Centralgermanywestcentral | $0.12 | $0.60 | $0.012 | $0.15 | |
| North Central USnorthcentralus | $0.11 | $0.55 | $0.011 | $0.1375 | |
| Poland Centralpolandcentral | $0.12 | $0.60 | $0.012 | $0.15 | |
| South Central USsouthcentralus | $0.11 | $0.55 | $0.011 | $0.1375 | |
| Spain Centralspaincentral | $0.12 | $0.60 | $0.012 | $0.15 | |
| Sweden Centralswedencentral | $0.12 | $0.60 | $0.012 | $0.15 | |
| West Europewesteurope | $0.12 | $0.60 | $0.012 | $0.15 | |
| West USwestus | $0.11 | $0.55 | $0.011 | $0.1375 | |
| West US 3westus3 | $0.11 | $0.55 | $0.011 | $0.1375 |
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
- $0.06066522 - $0.06618024
- Per month
- $606.6522 - $661.8024
Across 13 published price regions.
Customize workload or price region for Data Zone Standard - Long context, No cached input50% cached input
- Per request
- $0.03373712 - $0.03680413
- Per month
- $337.37121 - $368.04132
Across 13 published price regions.
Customize workload or price region for Data Zone Standard - Long context, 50% cached inputView 13 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.
| Azure Public price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Meter effective dates (UTC) |
|---|---|---|---|---|---|
| Central UScentralus | $0.22 | $0.825 | $0.022 | $0.275 | |
| East USeastus | $0.22 | $0.825 | $0.022 | $0.275 | |
| East US 2eastus2 | $0.22 | $0.825 | $0.022 | $0.275 | |
| France Centralfrancecentral | $0.24 | $0.90 | $0.024 | $0.30 | |
| Germany West Centralgermanywestcentral | $0.24 | $0.90 | $0.024 | $0.30 | |
| North Central USnorthcentralus | $0.22 | $0.825 | $0.022 | $0.275 | |
| Poland Centralpolandcentral | $0.24 | $0.90 | $0.024 | $0.30 | |
| South Central USsouthcentralus | $0.22 | $0.825 | $0.022 | $0.275 | |
| Spain Centralspaincentral | $0.24 | $0.90 | $0.024 | $0.30 | |
| Sweden Centralswedencentral | $0.24 | $0.90 | $0.024 | $0.30 | |
| West Europewesteurope | $0.24 | $0.90 | $0.024 | $0.30 | |
| West USwestus | $0.22 | $0.825 | $0.022 | $0.275 | |
| West US 3westus3 | $0.22 | $0.825 | $0.022 | $0.275 |
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
- $0.0008
- Per month
- $8.00
Across 26 published price regions.
Customize workload or price region for Global Standard, No cached input50% cached input
- Per request
- $0.000665
- Per month
- $6.65
Across 26 published price regions.
Customize workload or price region for Global Standard, 50% cached inputView 26 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.
| Azure Public price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Meter effective dates (UTC) |
|---|---|---|---|---|---|
| Australia Eastaustraliaeast | $0.10 | $0.50 | $0.01 | $0.125 | |
| Brazil Southbrazilsouth | $0.10 | $0.50 | $0.01 | $0.125 | |
| Canada Eastcanadaeast | $0.10 | $0.50 | $0.01 | $0.125 | |
| Central UScentralus | $0.10 | $0.50 | $0.01 | $0.125 | |
| East USeastus | $0.10 | $0.50 | $0.01 | $0.125 | |
| East US 2eastus2 | $0.10 | $0.50 | $0.01 | $0.125 | |
| France Centralfrancecentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| Germany West Centralgermanywestcentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| Indonesia Centralindonesiacentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| Japan Eastjapaneast | $0.10 | $0.50 | $0.01 | $0.125 | |
| Korea Centralkoreacentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| Malaysia Westmalaysiawest | $0.10 | $0.50 | $0.01 | $0.125 | |
| North Central USnorthcentralus | $0.10 | $0.50 | $0.01 | $0.125 | |
| Norway Eastnorwayeast | $0.10 | $0.50 | $0.01 | $0.125 | |
| Poland Centralpolandcentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| South Africa Northsouthafricanorth | $0.10 | $0.50 | $0.01 | $0.125 | |
| South Central USsouthcentralus | $0.10 | $0.50 | $0.01 | $0.125 | |
| South Indiasouthindia | $0.10 | $0.50 | $0.01 | $0.125 | |
| Spain Centralspaincentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| Sweden Centralswedencentral | $0.10 | $0.50 | $0.01 | $0.125 | |
| Switzerland Northswitzerlandnorth | $0.10 | $0.50 | $0.01 | $0.125 | |
| UAE Northuaenorth | $0.10 | $0.50 | $0.01 | $0.125 | |
| UK Southuksouth | $0.10 | $0.50 | $0.01 | $0.125 | |
| West Europewesteurope | $0.10 | $0.50 | $0.01 | $0.125 | |
| West USwestus | $0.10 | $0.50 | $0.01 | $0.125 | |
| West US 3westus3 | $0.10 | $0.50 | $0.01 | $0.125 |
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
- $0.0551502
- Per month
- $551.502
Across 26 published price regions.
Customize workload or price region for Global Standard - Long context, No cached input50% cached input
- Per request
- $0.03067011
- Per month
- $306.7011
Across 26 published price regions.
Customize workload or price region for Global Standard - Long context, 50% cached inputView 26 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.
| Azure Public price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Meter effective dates (UTC) |
|---|---|---|---|---|---|
| Australia Eastaustraliaeast | $0.20 | $0.75 | $0.02 | $0.25 | |
| Brazil Southbrazilsouth | $0.20 | $0.75 | $0.02 | $0.25 | |
| Canada Eastcanadaeast | $0.20 | $0.75 | $0.02 | $0.25 | |
| Central UScentralus | $0.20 | $0.75 | $0.02 | $0.25 | |
| East USeastus | $0.20 | $0.75 | $0.02 | $0.25 | |
| East US 2eastus2 | $0.20 | $0.75 | $0.02 | $0.25 | |
| France Centralfrancecentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| Germany West Centralgermanywestcentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| Indonesia Centralindonesiacentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| Japan Eastjapaneast | $0.20 | $0.75 | $0.02 | $0.25 | |
| Korea Centralkoreacentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| Malaysia Westmalaysiawest | $0.20 | $0.75 | $0.02 | $0.25 | |
| North Central USnorthcentralus | $0.20 | $0.75 | $0.02 | $0.25 | |
| Norway Eastnorwayeast | $0.20 | $0.75 | $0.02 | $0.25 | |
| Poland Centralpolandcentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| South Africa Northsouthafricanorth | $0.20 | $0.75 | $0.02 | $0.25 | |
| South Central USsouthcentralus | $0.20 | $0.75 | $0.02 | $0.25 | |
| South Indiasouthindia | $0.20 | $0.75 | $0.02 | $0.25 | |
| Spain Centralspaincentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| Sweden Centralswedencentral | $0.20 | $0.75 | $0.02 | $0.25 | |
| Switzerland Northswitzerlandnorth | $0.20 | $0.75 | $0.02 | $0.25 | |
| UAE Northuaenorth | $0.20 | $0.75 | $0.02 | $0.25 | |
| UK Southuksouth | $0.20 | $0.75 | $0.02 | $0.25 | |
| West Europewesteurope | $0.20 | $0.75 | $0.02 | $0.25 | |
| West USwestus | $0.20 | $0.75 | $0.02 | $0.25 | |
| West US 3westus3 | $0.20 | $0.75 | $0.02 | $0.25 |
Model information and limits
OpenAI's most efficient model for focused, high-volume tasks
- Metadata model ID
- gpt-6-luna
- 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.
Similar models
Models from the same family or provider, and similarly priced models from other providers.
- GPT-5.6 Luna (OpenAI) pricingCompare GPT-6 Luna vs GPT-5.6 Luna
- GPT-6 Sol (OpenAI) pricingCompare GPT-6 Luna vs GPT-6 Sol
- GPT-6 Astra (OpenAI) pricingCompare GPT-6 Luna vs GPT-6 Astra
- DeepSeek V4 Flash (DeepSeek) pricingCompare GPT-6 Luna vs DeepSeek V4 Flash
- Grok 4 Fast (xAI) pricingCompare GPT-6 Luna vs Grok 4 Fast
- GPT-5.6 Sol (OpenAI) pricingCompare GPT-6 Luna vs GPT-5.6 Sol
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.
- 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.
- Azure Retail Prices API
See the Microsoft API documentation for the retail meter data used here.