Compare Azure AI Models and Prices
Compare up to 3 Microsoft Foundry models by price, token limits, modalities, capabilities, and lifecycle. Search or replace a model directly in its comparison column.
Every change updates the URL, so this exact comparison can be bookmarked or shared.
Global Standard profile details
Inference data may be processed in any Azure region. Input and output usage is billed by token. Standard deployments provide best-effort throughput; reserved PTU pricing is separate.
Official deployment type guidanceCompare selected models
Prices use the same Global Standard profile in All Azure Public price regions. Ranges reflect different matching meters. Model specifications come from Models.dev's Azure catalog.
7 differing rows and 19 matching rows.
| Attribute |
|
|
|
|---|---|---|---|
| Identity | |||
| Provider | OpenAI | OpenAI | OpenAI |
| Azure product family | Azure OpenAI GPT5 | Azure OpenAI GPT5 | Azure OpenAI GPT5 |
| Model specifications | |||
| Models.dev Azure model ID | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna |
| Description | Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows | Balanced GPT-5.6 model for capable, cost-efficient everyday work | Cost-efficient GPT-5.6 model for fast, high-volume workloads |
| Model family | gpt-sol | gpt-terra | gpt-luna |
| Input modalities | Text, Image, Pdf | Text, Image, Pdf | Text, Image, Pdf |
| Output modalities | Text | Text | Text |
| Context window | 1,050,000 | 1,050,000 | 1,050,000 |
| Maximum input tokens | 922,000 | 922,000 | 922,000 |
| Maximum output tokens | 128,000 | 128,000 | 128,000 |
| Capabilities | |||
| Reasoning support | Yes | Yes | Yes |
| Reasoning options | Effort: none, low, medium, high, xhigh, max | Effort: none, low, medium, high, xhigh, max | Effort: none, low, medium, high, xhigh, max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| File attachments | Yes | Yes | Yes |
| Temperature control | No | No | No |
| Open weights | No | No | No |
| Lifecycle | |||
| Knowledge cutoff | Feb 16, 2026 | Feb 16, 2026 | Feb 16, 2026 |
| Release date | Jul 9, 2026 | Jul 9, 2026 | Jul 9, 2026 |
| Metadata last updated | Jul 9, 2026 | Jul 9, 2026 | Jul 9, 2026 |
| Global Standard pricing | |||
| Input / 1M tokens | $5.00 | $2.50 | $1.00 |
| Output / 1M tokens | $30.00 | $15.00 | $6.00 |
| Cached input / 1M tokens | $0.50 | $0.25 | $0.10 |
| Cache write / 1M tokens | $6.25 | $3.125 | $1.25 |
| Matching price regions | 24 | 24 | 24 |
| Latest meter effective date | Jul 1, 2026 | Jul 1, 2026 | Jul 1, 2026 |
Global Standard pricing
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $30.00
- Cached input / 1M tokens
- $0.50
- Cache write / 1M tokens
- $6.25
- Matching price regions
- 24
- Latest meter effective date
- Jul 1, 2026
Capabilities
- Reasoning support
- Yes
- Reasoning options
- Effort: none, low, medium, high, xhigh, max
- Tool calling
- Yes
- Structured output
- Yes
- File attachments
- Yes
- Temperature control
- No
- Open weights
- No
More model details
Identity
- Provider
- OpenAI
- Azure product family
- Azure OpenAI GPT5
Model specifications
- Models.dev Azure model ID
- gpt-5.6-sol
- Description
- Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
- Model family
- gpt-sol
- Input modalities
- Text, Image, Pdf
- Output modalities
- Text
- Context window
- 1,050,000
- Maximum input tokens
- 922,000
- Maximum output tokens
- 128,000
Lifecycle
- Knowledge cutoff
- Feb 16, 2026
- Release date
- Jul 9, 2026
- Metadata last updated
- Jul 9, 2026
Global Standard pricing
- Input / 1M tokens
- $2.50
- Output / 1M tokens
- $15.00
- Cached input / 1M tokens
- $0.25
- Cache write / 1M tokens
- $3.125
- Matching price regions
- 24
- Latest meter effective date
- Jul 1, 2026
Capabilities
- Reasoning support
- Yes
- Reasoning options
- Effort: none, low, medium, high, xhigh, max
- Tool calling
- Yes
- Structured output
- Yes
- File attachments
- Yes
- Temperature control
- No
- Open weights
- No
More model details
Identity
- Provider
- OpenAI
- Azure product family
- Azure OpenAI GPT5
Model specifications
- Models.dev Azure model ID
- gpt-5.6-terra
- Description
- Balanced GPT-5.6 model for capable, cost-efficient everyday work
- Model family
- gpt-terra
- Input modalities
- Text, Image, Pdf
- Output modalities
- Text
- Context window
- 1,050,000
- Maximum input tokens
- 922,000
- Maximum output tokens
- 128,000
Lifecycle
- Knowledge cutoff
- Feb 16, 2026
- Release date
- Jul 9, 2026
- Metadata last updated
- Jul 9, 2026
Global Standard pricing
- Input / 1M tokens
- $1.00
- Output / 1M tokens
- $6.00
- Cached input / 1M tokens
- $0.10
- Cache write / 1M tokens
- $1.25
- Matching price regions
- 24
- Latest meter effective date
- Jul 1, 2026
Capabilities
- Reasoning support
- Yes
- Reasoning options
- Effort: none, low, medium, high, xhigh, max
- Tool calling
- Yes
- Structured output
- Yes
- File attachments
- Yes
- Temperature control
- No
- Open weights
- No
More model details
Identity
- Provider
- OpenAI
- Azure product family
- Azure OpenAI GPT5
Model specifications
- Models.dev Azure model ID
- gpt-5.6-luna
- Description
- Cost-efficient GPT-5.6 model for fast, high-volume workloads
- Model family
- gpt-luna
- Input modalities
- Text, Image, Pdf
- Output modalities
- Text
- Context window
- 1,050,000
- Maximum input tokens
- 922,000
- Maximum output tokens
- 128,000
Lifecycle
- Knowledge cutoff
- Feb 16, 2026
- Release date
- Jul 9, 2026
- Metadata last updated
- Jul 9, 2026
In pricing rows, N/A means the Azure Retail Prices API has not published a matching meter for the current Azure Public profile and region. In model metadata rows, N/A means Models.dev has no reliable Azure model match or does not report that field for the exact model snapshot. Lifecycle fields from a family-level record are not applied to a date-pinned price entry; metadata rows unavailable for every selected model are hidden. Public list prices and catalog metadata do not guarantee availability, quota, capacity, or subscription eligibility. Prices exclude taxes and negotiated discounts; cost estimates also exclude request-based, hosting, and other non-token charges.
Estimate request and monthly token costs from each matching regional price point. Cached input and cache writes use their dedicated meters when published.
GPT-5.6 Sol
OpenAI
- Cost / request
- $0.045
- Estimated monthly
- $450.00
- Difference vs. lowest
- +400%
24 matching price regions
GPT-5.6 Terra
OpenAI
- Cost / request
- $0.0225
- Estimated monthly
- $225.00
- Difference vs. lowest
- +150%
24 matching price regions
GPT-5.6 Luna
OpenAI
- Cost / request
- $0.009
- Estimated monthly
- $90.00
- Difference vs. lowest
- Lowest selected cost
24 matching price regions
Popular comparisons
Switch to another useful comparison generated from models priced in this deployment profile and region.