MAI-Image-2.7 Preview
Preview of Microsoft AI’s next image model, editing only for now.
MAI-Image-2.7 is the next version of Microsoft AI’s in-house image model, launched as a preview that edits existing images from text instructions; Microsoft says text-to-image generation will follow. It can be tried in MAI Playground; no API or price has been announced.
- Provider
- Microsoft AI
- Type
- Image model
- Released
- Oct 27, 2026
- Input
- text, image
- Output
- image
- Open weights
- No
Best for
- Image generation
Strengths
- Image editing
- Improves on MAI-Image-2.6 (vendor-reported)
More from Microsoft AI
- Microsoft-Decision-1 — Microsoft AI. Microsoft’s small decision-scoring model: calibrated probabilities over fixed options.
- MAI-Image-2.6 — Microsoft AI. Microsoft AI’s in-house image model.
- MAI-Voice-2.1 — Microsoft AI. Microsoft AI’s most expressive multilingual text-to-speech model.
- MAI-Voice-2.1-Flash — Microsoft AI. Low-latency MAI-Voice for real-time, high-volume speech.
- MAI-Transcribe-2 — Microsoft AI. Microsoft AI’s in-house speech-to-text model.
- MAI-Transcribe-2-Streaming — Microsoft AI. Microsoft AI’s first streaming speech-to-text model, in 60 languages.