opendunes

MAI-Image-2.7 Flash

New

by MicrosoftReleased 17 November 2026

MAI-Image-2.7 Flash is the lower-latency, lower-cost member of the MAI-Image-2.7 family from Microsoft AI, built for latency-sensitive, high-throughput image generation and editing at comparable quality to the precision tier. It...

TakesTextImages
GivesImages

7 shapes, square to 16:9

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperature

Other

Also accepted by this model.

max_completion_tokens

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
4 096 tokens
Max output
1 024 tokens
Reads at once
not stated
Longest reply
≈ 1 000 words
Tokenizer
Other
Released
17 Nov 2026
Full API reference

Questions about MAI-Image-2.7 Flash

Is MAI-Image-2.7 Flash still on sale?

No. Microsoft has retired it. Other Microsoft models are on sale.

What is MAI-Image-2.7 Flash best for?

The lab has not said.

Does MAI-Image-2.7 Flash work in Arabic, French or Darja?

Microsoft names no languages for MAI-Image-2.7 Flash. Arabic, French and Darja: not stated.

Can it edit my photo?

Yes. Up to 5 reference pictures in one request.

What sizes and formats does it make?

1:1, 4:3, 3:4, 16:9, 9:16, 3:2 and 2:3. Saved as: not stated.

Who makes MAI-Image-2.7 Flash, and when was it released?

Microsoft. Released 17 November 2026.

Other Microsoft models, priced in dinars

See all Microsoft models
Microsoft-Decision-1Microsoft · Oct 9, 2026

Microsoft-Decision-1 reads the content you send and returns a probability for each of a fixed set of answer options instead of writing text. Use it where a pick-one call drives your app: sorting tickets, routing requests, checking an answer, or deciding whether to act, wait or flag the case for a person. It reads about 33 pages at once. It cannot chat, translate or summarize, so pair it with a text model for those jobs.

32 pages per call
≈0,014 DAper case
View model
MAI-Voice-2Microsoft · Jun 2, 2026

#1 for realistic voice · MAI-Voice-2 turns text into speech and returns audio, with control over tone and delivery and a way to give different lines to different speakers. It covers 15 languages in 18 regional versions and offers four ready voices: US English, Mexican Spanish, French and German. Choose it for narration, tutorials and assistants where natural delivery counts more than speed.

4 voices
≈4,39 DAper paragraph read aloud
View model
MAI-Voice-2.1-FlashMicrosoft · Oct 1, 2026

MAI-Voice-2.1 Flash turns text into speech with little waiting, for voice assistants and call-centre replies that must start speaking at once. You choose from about 97 named voices across 23 languages, with natural rhythm and emotion, and get audio back.

97 voices
≈3,00 DAper paragraph read aloud
View model
MAI-Transcribe 1.5Microsoft · Jun 2, 2026

MAI-Transcribe 1.5 turns an audio file into a transcript, detecting the spoken language on its own and coping with accents and noisy recordings. You can give it a list of keywords so product names and technical terms come out right. It does not label who is speaking.

2,00 DAper minute of audio
View model