---
type: "post"
stable_id: "post:microsoft-builds-its-own-fast-code-and-reasoning-model-stack"
slug: "microsoft-builds-its-own-fast-code-and-reasoning-model-stack"
title: "Microsoft Builds Its Own Fast-Code and Reasoning Model Stack"
description: "Microsoft released MAI-Code-1.1-Flash and MAI-Thinking-1, pairing a fast coding model with a separate reasoning model."
retrieval_nugget: "The release points to a portfolio strategy for agent workloads: use different models for interactive code loops and deeper reasoning, then make routing and evaluation part of the product rather than forcing one model into every task."
published_at: "2026-08-14"
updated_at: "2026-08-15"
record_date: "2026-08-14"
date_kind: "discovered_at"
topics: ["new-models","coding-agents","routing"]
entities: ["Microsoft AI","MAI-Code","MAI-Thinking"]
source_urls: ["https://microsoft.ai/news/mai-code-1-1-flash-br-better-faster-at-a-quarter-of-the-cost","https://microsoft.ai/news/introducing-mai-thinking-1"]
source_format: "article"
editorial_timing: {"lane":"regular_hourly","scheduled_at":"2026-08-18T17:00:00+03:00","real_news_delta":"owner-selected verified story"}
origin: {"basket_id":"5854f7b2-5954-4d2a-8997-81596a49da74","basket_revision":1,"target_kind":"story_cluster","target_id":"54eba6a5-b39a-412d-ad69-1e4d19118197","owner_selection":"6","route":"openclaw"}
visual_decision: {"outcome":"text_only","status":"not_applicable","reason_code":"concise_text_sufficient","owner_reviewed":true,"reviewed_by":"owner-and-codex"}
schema_version: "newruntime-agent-readable-v0.2"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/posts/microsoft-builds-its-own-fast-code-and-reasoning-model-stack/","markdown":"https://newruntime.com/posts/microsoft-builds-its-own-fast-code-and-reasoning-model-stack.md","json":"https://newruntime.com/posts/microsoft-builds-its-own-fast-code-and-reasoning-model-stack.json"}
---

# Microsoft Builds Its Own Fast-Code and Reasoning Model Stack

## Retrieval answer

The release points to a portfolio strategy for agent workloads: use different models for interactive code loops and deeper reasoning, then make routing and evaluation part of the product rather than forcing one model into every task.

Microsoft released MAI-Code-1.1-Flash and MAI-Thinking-1, pairing a fast coding model with a separate reasoning model.

New Runtime reading: The release points to a portfolio strategy for agent workloads: use different models for interactive code loops and deeper reasoning, then make routing and evaluation part of the product rather than forcing one model into every task.

Evidence boundary: this item uses the listed public sources and keeps vendor, author, or reporter claims attributed. The queued page is an editorial synthesis, not an independent validation of every reported metric.