LLM Reference
Microsoft Foundry

Using MAI-Thinking-1 on Microsoft Foundry

Implementation guide · MAI · Microsoft AI

Serverless

Microsoft Foundry exposes MAI-Thinking-1 through model ID MAI-Thinking-1. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-08-24. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Microsoft Foundry and generate an API key.
  2. 2
    Use the Microsoft Foundry SDK or REST API to call MAI-Thinking-1 — see the documentation for request format.

Code Examples

See Microsoft Foundry documentation for integration details.

Pricing on Microsoft Foundry

Capabilities

ReasoningJSON / Tool use

About MAI-Thinking-1

MAI-Thinking-1 is Microsoft AI's flagship reasoning model, built from scratch on enterprise-grade commercially licensed data without third-party distillation. The sparse mixture-of-experts model activates about 35B parameters from roughly 1T total parameters, supports a 256K-token context window, and targets frontier reasoning and software engineering work at a mid-weight price point. Microsoft reports 97% on AIME 2025, 94.5% on AIME 2026, 84.2% on GPQA Diamond, 87.7% on LiveCodeBench v6, 73.5% on SWE-bench Verified, and 52.8% on SWE-bench Pro. In a 1,276-task Surge blind side-by-side evaluation, it narrowly beat Claude Sonnet 4.6 but trailed Claude Opus 4.6.

Model Specs

Released2026-06-02
Parameters1T total / 35B active
Context256k
ArchitectureMixture of Experts

Provider

Microsoft Foundry
Microsoft Foundry

Microsoft

Redmond, Washington, United States