MAI-Image-2.5 Pro
Microsoft's quality-focused image generation and editing model for Azure teams that want enterprise deployment controls inside Microsoft Foundry.
Microsoft's quality-focused image generation and editing model for Azure teams that want enterprise deployment controls inside Microsoft Foundry.
Plain-English overview
MAI-Image-2.5 Pro creates images from text and can make targeted changes to an uploaded image. Microsoft positions it for visually rich concepts, production design, realistic scenes, readable text, and edits that preserve the rest of a composition.
The main reason to choose it is the Azure route: identity, regional deployment, quotas, and data governance live in Microsoft Foundry. It is still a preview model, so teams should test feature availability and limits in the exact Azure region they plan to use.
Category comparison
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
Pricing & comparisons
Set your usage. Your estimate updates as you type.
Example output: square 1,024 × 1,024 images. Prices depend on supported resolution and quality; edits and retries can cost extra.
MAI-Image-2.5 Pro
Microsoft
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Availability
Available in preview as a deployable Microsoft Foundry Model sold by Azure.
Global Standard deployment is listed in West Central US, East US, West US, West Europe, Sweden Central, South India, and UAE North.
Check live availabilityData and training
Microsoft says Foundry Model prompts and outputs are not used to train foundation models without permission. Preview features may not support every storage or customer-managed-key control, so verify the deployed feature set.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Microsoft's quality-focused image generation and editing model for Azure teams that want enterprise deployment controls inside Microsoft Foundry. MAI-Image-2.5 Pro creates images from text and can make targeted changes to an uploaded image. Microsoft positions it for visually rich concepts, production design, realistic scenes, readable text, and edits that preserve the rest of a composition.
MAI-Image-2.5 Pro was released on June 19, 2026 according to the cited provider materials.
Available in preview as a deployable Microsoft Foundry Model sold by Azure. The access routes listed in this guide are Microsoft Foundry and Microsoft Azure.
Azure account pricing. Microsoft lists the model on its Foundry pricing page, but the public table does not expose a universal dollar rate. Use the Azure pricing calculator for your agreement and region.
Available in preview as a deployable Microsoft Foundry Model sold by Azure. Global Standard deployment is listed in West Central US, East US, West US, West Europe, Sweden Central, South India, and UAE North.
Microsoft says Foundry Model prompts and outputs are not used to train foundation models without permission. Preview features may not support every storage or customer-managed-key control, so verify the deployed feature set. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
OpenAI's quality-first GPT Image 2.5 model for demanding generation, precise edits, subject preservation, typography, and high-resolution creative work.
Open full comparisonOpenAI's speed-first GPT Image 2.5 model for everyday generation and editing, positioned at GPT Image 2-level image quality with lower latency.
Open full comparisonOpenAI's current image model for detailed generation and editing, especially complex prompts, text-heavy visuals, and high-fidelity source images.
Open full comparisonGoogle's versatile image workhorse for fast generation, conversational edits, multiple references, grounded imagery, and outputs up to 4K.
Open full comparisonBlack Forest Labs' production-focused image model for scalable generation and editing, precise composition, and multi-reference creative workflows.
Open full comparisonA design-oriented image model with open weights, multilingual typography, structured layout control, editable elements, and simple per-image API tiers.
Open full comparisonSpaceXAI's current image model for creating and editing practical visuals, with an emphasis on following detailed instructions, typography, and consistent references.
Open full comparisonMidjourney's current default image model for highly polished, style-led creative work, with stronger personalization and a new reference-based Edit Model.
Open full comparisonA typography-aware image model for creating and editing polished visuals, now available through Reve's creative product rather than its discontinued direct API.
Open full comparison