GPT-4 8K Azure pricing
Read model rates and estimates
Compare models using the same deployment type, price region, and workload. Input, output, cache-read, and cache-write prices are separate categories.
Missing rates do not mean free usage. A listed price does not guarantee deployment availability or quota.
GPT-4 8K costs $30.00 input and $60.00 output per 1M tokens on Azure (Global Standard). Compare 4 deployment types across 22 price regions.
OpenAIText generationUSD / 1M tokens
Estimate token costPrices 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
- $30.00
- Output / 1M
- $60.00
Cache rates and 1 price regions
- Cached input / 1M
- Not published
- Cache write / 1M
- Not published
Regional Standard
- Input / 1M
- $30.00 - $36.30
- Output / 1M
- $60.00 - $72.60
Cache rates and 22 price regions
- Cached input / 1M
- Not published
- Cache write / 1M
- Not published
Global Batch
- Input / 1M
- $15.00
- Output / 1M
- $30.00
Cache rates and 4 price regions
- Cached input / 1M
- Not published
- Cache write / 1M
- Not published
Regional Batch
- Input / 1M
- $15.00
- Output / 1M
- $30.00
Cache rates and 1 price regions
- Cached input / 1M
- Not published
- Cache write / 1M
- Not published
Model information and limits
Input, output, and context limits are not published for this model.
Microsoft Foundry model catalogCost examples
Customize workloadMonthly 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
- $1,500.00
- 50% cached input / month
- Published cached input prices are missing for this workload.
Regional Standard
- No cached input / month
- $1,500.00 - $1,815.00
- 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
- $750.00
- 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.
Regional Batch
- No cached input / month
- $750.00
- 50% cached input / month
- Published cached input prices are missing for this workload.
Per-request costs
| Deployment type | No cached input | 50% cached input |
|---|---|---|
| Global Standard | $0.15 | Unavailable |
| Regional Standard | $0.15 - $0.1815 | Unavailable |
| Global Batch | $0.075 | Unavailable |
| Regional Batch | $0.075 | 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 1 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.
| Price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M |
|---|---|---|---|---|
| Spain Centralspaincentral | $30.00 | $60.00 | Not published | Not published |
Regional Standard 22 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.
| Price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M |
|---|---|---|---|---|
| Australia Eastaustraliaeast | $30.00 | $60.00 | Not published | Not published |
| Brazil Southbrazilsouth | $30.00 | $60.00 | Not published | Not published |
| Canada Centralcanadacentral | $30.00 | $60.00 | Not published | Not published |
| Canada Eastcanadaeast | $30.00 | $60.00 | Not published | Not published |
| East USeastus | $30.00 | $60.00 | Not published | Not published |
| East US 2eastus2 | $30.00 | $60.00 | Not published | Not published |
| France Centralfrancecentral | $30.00 | $60.00 | Not published | Not published |
| Germany West Centralgermanywestcentral | $30.00 | $60.00 | Not published | Not published |
| Japan Eastjapaneast | $30.00 | $60.00 | Not published | Not published |
| North Central USnorthcentralus | $30.00 | $60.00 | Not published | Not published |
| North Europenortheurope | $30.00 | $60.00 | Not published | Not published |
| Norway Eastnorwayeast | $30.00 | $60.00 | Not published | Not published |
| Poland Centralpolandcentral | $30.00 | $60.00 | Not published | Not published |
| South Central USsouthcentralus | $30.00 | $60.00 | Not published | Not published |
| South Indiasouthindia | $30.00 | $60.00 | Not published | Not published |
| Spain Centralspaincentral | $36.30 | $72.60 | Not published | Not published |
| Sweden Centralswedencentral | $30.00 | $60.00 | Not published | Not published |
| Switzerland Northswitzerlandnorth | $30.00 | $60.00 | Not published | Not published |
| UK Southuksouth | $30.00 | $60.00 | Not published | Not published |
| West Europewesteurope | $30.00 | $60.00 | Not published | Not published |
| West USwestus | $30.00 | $60.00 | Not published | Not published |
| West US 3westus3 | $30.00 | $60.00 | Not published | Not published |
Global Batch 4 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.
| Price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M |
|---|---|---|---|---|
| East USeastus | $15.00 | $30.00 | Not published | Not published |
| South Indiasouthindia | $15.00 | $30.00 | Not published | Not published |
| Sweden Centralswedencentral | $15.00 | $30.00 | Not published | Not published |
| West USwestus | $15.00 | $30.00 | Not published | Not published |
Regional Batch 1 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.
- 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.
| Price region | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M |
|---|---|---|---|---|
| Canada Centralcanadacentral | $15.00 | $30.00 | 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.
- GPT-4 8K
OpenAI · Current model · Global Standard
- Input
- $30.00
- Output
- $60.00
- GPT-6.1 Sol
OpenAI · Same provider · Global Standard
- Input
- $2.00
- Output
- $10.00
- GPT-6 Luna
OpenAI · Same provider · Global Standard
- Input
- $0.10
- Output
- $0.50
- Grok 3
xAI · Similar price · Global Standard
- Input
- $3.00
- Output
- $15.00
- Grok 4
xAI · Similar price · Global Standard
- Input
- $3.00
- Output
- $15.00
- GPT-6 Sol
OpenAI · Same provider · Global Standard
- Input
- $2.00
- Output
- $10.00
- GPT-6 Astra
OpenAI · Same provider · Global Standard
- Input
- $10.00
- Output
- $50.00
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.