--- title: "MAI-Image-2.6 AI model: facts and benchmarks | Kendr" canonical: "https://kendr.org/models/microsoft-mai-image-2-6" date_modified: "2026-09-06" profile_kind: "reference" --- # MAI-Image-2.6 model profile MAI-Image-2.6 is a Microsoft model profile with a 4,096-token context window. The dated catalog snapshot records text, image modalities and interfaces for image generation, vision. Microsoft's MAI-Image-2.6 is an image generation and editing model available via Azure AI Foundry. It creates images from text prompts and supports image-guided editing across multiple aspect ratios. MAI-Image-2.6 is a reference profile: Microsoft publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. MAI-Image-2.6 is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt. MAI-Image-2.6 accepts text and image and returns image. The snapshot records image generation and vision as capabilities or interfaces. The dated unit-price records list $5 per 1M tokens for input_text, $8 per 1M tokens for input_image, and $38 per 1M tokens for output_image. Each figure retains its billable dimension, variant, provider, source, and evidence date. The 2026-09-06 snapshot includes 2 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated. ## Profile facts - **Profile type:** Model research profile - **Provider or publisher:** Microsoft - **Context window:** 4,096 tokens - **Snapshot date:** 2026-09-06 - **Knowledge cutoff:** Not disclosed - **Reference catalog ID:** microsoft/mai-image-2.6 ## When to pick MAI-Image-2.6 MAI-Image-2.6 is a reference profile: Microsoft publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field. - Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. - Reach for it when the output is image. This route produces image rather than only text, and those units are priced separately from tokens. - Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. - Look elsewhere when the prompt is long. The 4K-token context window is in the bottom quarter of the 163 models publishing a limit. Long documents need chunking or a wider-context route. - Look elsewhere when you are building an agent. No tool-calling capability is recorded for this model in the snapshot. Agent loops need a route that can call functions. ## Context, modalities, and identity MAI-Image-2.6 accepts text and image and returns image. The snapshot records image generation and vision as capabilities or interfaces. - **Provider or publisher:** Microsoft - **Context window:** 4,096 tokens - **Maximum output:** 1,024 tokens - **Input modalities:** text and image - **Output modalities:** image - **Knowledge cutoff:** Not disclosed ## Model overview Microsoft's MAI-Image-2.6 is an image generation and editing model available via Azure AI Foundry. It creates images from text prompts and supports image-guided editing across multiple aspect ratios. - **Reference model ID:** microsoft/mai-image-2.6 - **Canonical version:** microsoft/mai-image-2.6-20260904 - **Hugging Face ID:** Not separately documented ## Capabilities and supported controls Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route. - **Supported parameters:** max_completion_tokens, max_tokens, temperature - image generation - vision ## Dated pricing snapshot The dated unit-price records list $5 per 1M tokens for input_text, $8 per 1M tokens for input_image, and $38 per 1M tokens for output_image. Each figure retains its billable dimension, variant, provider, source, and evidence date. These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price. - **Price date:** 2026-09-06 - **Input:** No verified rate - **Cached input:** No verified rate - **Output:** No verified rate | Billable | Variant | Cost | Unit | Provider | As of | | --- | --- | --- | --- | --- | --- | | input_text | Default | $5 | per 1M tokens | Azure | 2026-09-06 | | input_image | Default | $8 | per 1M tokens | Azure | 2026-09-06 | | output_image | Default | $38 | per 1M tokens | Azure | 2026-09-06 | ## Provider routes, performance, and uptime The snapshot retains 1 provider endpoint. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees. - **Active provider endpoints:** 1 - **Best p50 latency:** No recent metric - **Best p50 throughput:** No recent metric - **Availability with routing:** No recent metric - **Availability without routing:** No recent metric - **Performance date:** 2026-09-06 | Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | | Azure | unknown | $5 / 1M | $0 / 1M | No verified rate | 4,096 tokens | No recent p50 | No recent p50 | 100.00% | ## Benchmark evidence and limitations The 2026-09-06 snapshot includes 2 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source. | Design Arena category | Elo | Win rate | Rank | | --- | --- | --- | --- | | image | 1335 | 67.6% | #2 | | logo | 1320 | 67% | #1 | ## Popularity and market context No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. - **Third-party catalog rank:** No verified rank - **Global market share:** Not inferred - **Observation date:** 2026-09-06 ## Frequently asked questions ### When should I use MAI-Image-2.6? MAI-Image-2.6 is a reference profile: Microsoft publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the output is image: This route produces image rather than only text, and those units are priced separately from tokens. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when the prompt is long: The 4K-token context window is in the bottom quarter of the 163 models publishing a limit. Long documents need chunking or a wider-context route. Look elsewhere when you are building an agent: No tool-calling capability is recorded for this model in the snapshot. Agent loops need a route that can call functions. ### What is MAI-Image-2.6? MAI-Image-2.6 is a Microsoft model profile with a 4,096-token context window. The dated catalog snapshot records text, image modalities and interfaces for image generation, vision. ### What context window does MAI-Image-2.6 have? The dated profile lists 4,096 tokens of context and up to 1,024 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits. ### What benchmark evidence is available for MAI-Image-2.6? The 2026-09-06 snapshot includes 2 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source. ### Is MAI-Image-2.6 available through Kendr? This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases. ### Does the popularity rank represent MAI-Image-2.6's global market share? No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. No global market-share percentage is inferred when the source does not publish one. ## Sources and evidence dates - [MAI-Image-2.6 third-party catalog record](https://openrouter.ai/microsoft/mai-image-2.6) — catalog, checked 2026-09-06 - [Third-party model catalog methodology](https://openrouter.ai/docs/guides/overview/models) — methodology, checked 2026-09-06 - [Microsoft official model documentation](https://learn.microsoft.com/azure/ai-foundry/models/) — primary, checked 2026-09-06 - [Design Arena leaderboard and methodology](https://www.designarena.ai/leaderboard) — benchmark, checked 2026-09-06 - [MAI-Image-2.6 third-party catalog record](https://openrouter.ai/microsoft/mai-image-2.6) — catalog, checked 2026-09-06 Live Kendr operational availability is published separately at https://api.kendr.org/api/public/models.