MAI-Image-2e
Last refreshed 2026-05-19. Next refresh: weekly.
MAI-Image-2e is worth evaluating for vision when its provider route and context window match the workload.
Decision context: Vision task fit, 1 tracked provider route, and research from 2026-05-19.
Use it for
- Teams evaluating vision
- Workloads that can use a 33k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Strict JSON or tool-calling flows
Cheapest output
-
Microsoft Foundry per 1M tokens
Provider routes
1
Tracked API hosts
Quality / dollar
Unknown
No task benchmark coverage yet
Freshness
2026-05-19
Researched 14d ago
Top use-case fit
Vision
Included by capability and metadata signals in the decision map.
Provider price ladder
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Microsoft Foundry | - | - | ServerlessPartial |
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
About
Microsoft AI image generation model optimized for efficiency — the 'e' stands for Efficient. Delivers flagship MAI-Image-2 quality at 41% lower cost, ~22% faster generation, and 4x better efficiency (normalized by latency and GPU usage). Generates photorealistic images up to 1024×1024 pixels with strong in-image text rendering and complex scene handling. Available in Microsoft Foundry and MAI Playground; rolling out to Copilot, Bing Image Creator, and PowerPoint. Pricing: $5/1M text input tokens, $19.50/1M image output tokens.
MAI-Image-2e is a proprietary model in the MAI family. The structured metadata tracks a 33k-token context window and multimodal input. This page tracks provider routes through Microsoft Foundry. No headline benchmark score is tracked for MAI-Image-2e yet.