Kimi K2.5 thinking Azure Pricing
Moonshot AI prices for Azure Kimi in Microsoft Foundry. Published rates cover 2 deployment profiles across 35 Azure Public price regions.
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 | $0.66 | $3.30 | $0.11 | Not published | 19 |
| Global Standard | $0.60 | $3.00 | $0.10 | Not published | 35 |
The tables contain only this Moonshot AI 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.
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
Estimate unavailable
Published input prices are missing for this workload in one or more matching price regions. Select a region with complete prices.
Customize workload or price region for Data Zone Standard, No cached input50% cached input
Estimate unavailable
Published input prices are missing for this workload in one or more matching price regions. Select a region with complete prices.
Customize workload or price region for Data Zone Standard, 50% cached inputView 19 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 | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| East USeastus | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| East US 2eastus2 | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| France Centralfrancecentral | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| Germany West Centralgermanywestcentral | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| Italy Northitalynorth | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| North Europenortheurope | Not published | $3.30 | $0.11 | Not published | |
| Norway Eastnorwayeast | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| Poland Centralpolandcentral | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| South Central USsouthcentralus | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| Spain Centralspaincentral | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| Sweden Centralswedencentral | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| Switzerland Northswitzerlandnorth | Not published | $3.30 | $0.11 | Not published | |
| Switzerland Westswitzerlandwest | Not published | $3.30 | $0.11 | Not published | |
| West Central USwestcentralus | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| West Europewesteurope | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| West USwestus | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| West US 2westus2 | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
| West US 3westus3 | $0.66 | $3.30 | $0.11 | Not published | input and output: cached input: |
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
- $0.0048
- Per month
- $48.00
Across 35 published price regions.
Customize workload or price region for Global Standard, No cached input50% cached input
- Per request
- $0.00405
- Per month
- $40.50
Across 35 published price regions.
Customize workload or price region for Global Standard, 50% cached inputView 35 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 | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Brazil Southbrazilsouth | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Canada Centralcanadacentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Canada Eastcanadaeast | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Central UScentralus | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| East USeastus | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| East US 2eastus2 | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| France Centralfrancecentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Germany West Centralgermanywestcentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Italy Northitalynorth | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Japan Eastjapaneast | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Japan Westjapanwest | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Korea Centralkoreacentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Malaysia Westmalaysiawest | $0.60 | $3.00 | $0.10 | Not published | |
| North Central USnorthcentralus | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| North Europenortheurope | $0.60 | $3.00 | $0.10 | Not published | |
| Norway Eastnorwayeast | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Poland Centralpolandcentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Qatar Centralqatarcentral | $0.60 | $3.00 | $0.10 | Not published | |
| South Africa Northsouthafricanorth | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| South Central USsouthcentralus | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| South Indiasouthindia | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Southeast Asiasoutheastasia | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Spain Centralspaincentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Sweden Centralswedencentral | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Switzerland Northswitzerlandnorth | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| Switzerland Westswitzerlandwest | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| UAE Northuaenorth | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| UK Southuksouth | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| UK Westukwest | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| West Central USwestcentralus | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| West Europewesteurope | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| West USwestus | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| West US 2westus2 | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
| West US 3westus3 | $0.60 | $3.00 | $0.10 | Not published | input and output: cached input: |
Model information and limits
Kimi multimodal agent model for visual understanding, coding, and planning
- Metadata model ID
- kimi-k2.5
- Metadata match
- model
- Input modalities
- text, image
- Output modalities
- text
- Context window (tokens)
- 262,144
- Maximum input tokens
- Not published
- Maximum output tokens
- 262,144
- 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.
Related Azure model listings
Check the provider, Azure product and deployment type for each listing; their prices are independent.
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.