MAI-Image-2-Efficient 发布：旗舰级质量，成本降低 41%

Apr 14, 2026 Models MAI Superintelligence Team

A collage featuring a beige knitted sweater against a blue sky, close-up texture shots, and a person wearing the sweater, all set on a brown background with curved white lines.

Available now in Microsoft Foundry and MAI Playground

We built MAI-Image-2 to be our best text-to-image model — photorealistic, expressive, with reliable in-image text.

Today we’re making all that faster and cheaper.

Meet MAI-Image-2-Efficient.

Production-ready quality. Built for speed and scale. 22% faster and 4x more efficient¹. And priced nearly 41% lower — $5 per 1M text input tokens, $19.50 per 1M image output tokens.

That’s not just faster than our own flagship. It’s 40% faster on average than other leading text-to-image models².

Two models, two jobs

MAI-Image-2-Efficient is your production workhorse. Use it when you need volume, speed, and tight cost control — product shots, marketing creatives, UI mockups, branded assets, batch pipelines. It handles short-form text like headlines and labels cleanly, and it’s built to run in real-time, interactive workflows without breaking a sweat.

MAI-Image-2 is your precision tool. Reach for it when the brief demands the highest fidelity — portraits, photorealistic scenes, stylized looks like anime or illustration, and longer or more complex in-image text. This is the model for final deliverables where every detail matters.

Start building now

MAI-Image-2-Efficient is available today in Microsoft Foundry and MAI Playground³. No waitlist, no preview — just plug it in and go. It’s also rolling out across Copilot and Bing, with more surfaces like PowerPoint coming soon.

Partners like Shutterstock are already testing with promising results:

“MAI-Image-2-Efficient shows strong progress in prompt fidelity and creative usability across a range of workflows. In our evaluation work, we look closely at how well models translate intent into consistent, production-ready outputs, and this model is trending in the right direction. That level of reliability is what ultimately matters when teams move from experimentation into real-world use.” – Vanessa Salvo, Principal Product Manager, Shutterstock

This is just the beginning. More models ahead — stay tuned.

A collage of six sections: clothing labels, orange slices with bottles, close-up tomatoes, skin care products with sky background, bottles with figs, and abstract orange and white graphic with the words "THE FUTURE CAN WAIT.

Download Model Card

As tested on April 13, 2026. Compared to MAI-Image-2 when normalized by latency and GPU usage. Throughput per GPU vs MAI-Image-2 on NVIDIA H100 at 1024×1024; measured with optimized batch sizes and matched latency targets. Results vary with batch size, concurrency, and latency constraints.
As tested on April 13, 2026. Compared to Gemini 3.1 Flash (high reasoning), Gemini 3.1 Flash Image and Gemini 3 Pro Image: Measured at p50 latency via AI Studio API (1:1, 1K images; minimal reasoning unless noted; web search disabled). MAI-Image-2, MAI-Image-2e, GPT-Image-1.5-High: Measured at p50 latency via Foundry API.
MAI Playground is available in select markets including the US. Coming soon to EU countries.

MAI-Image-2-Efficient 发布：旗舰级质量，成本降低 41%

Two models, two jobs

Start building now

Related Stories

Two in-house models in support of our mission

Announcing 3 new world class MAI models, available in Foundry

Health Check: How People Use Copilot for Health