mai-thinking-1 · Microsoft
MAI-Thinking-1 is Microsoft’s first inference model in the MAI series, built for enterprise-scale workloads. With excellent reasoning, mathematical, and general intelligence capabilities, combined with superior cost-effectiveness, it makes high-throughput, 24/7 AI workloads economically viable.
MAI-Thinking-1 is Microsoft’s first inference model in the MAI series, built for enterprise-scale workloads. With excellent reasoning, mathematical, and general intelligence capabilities, combined with superior cost-effectiveness, it makes high-throughput, 24/7 AI workloads economically viable.
Mai Thinking 1 has a 256,000 token context window. It supports up to 64,000 output tokens.
On AIHubMix, Mai Thinking 1 costs $2 per million input tokens and $8 per million output tokens.
Mai Thinking 1 accepts text input.
Mai Thinking 1 supports thinking and structured outputs. Per-protocol parameter support is listed in the capability table on this page.
Mai Thinking 1 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to mai-thinking-1 — no other code changes needed.
Mai Thinking 1 is developed by Microsoft. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…
MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…
MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…
Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical…
Microsoft's latest model
Microsoft's latest model
Use Mai Thinking 1 via the AIHubMix unified API — one interface for every major LLM.