MAI-Code-1.1-Flash

Released
2026-08-11
Last refreshed
2026-10-08
Status
Researched today
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

MAI-Code-1.1-Flash is available now for coding, rag, and agents with 256k context; evaluate it while provider pricing coverage matures.

Microsoft AI releases · 17 in the last 12 monthsChangelog →
Specifications
Family
MAI
Released
2026-08-11
Context
256k
Parameters
138B (5B active)
Architecture
Mixture of Experts
Knowledge cutoff
2025-12
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by
Microsoft AI

Applied AI products and platforms from Microsoft

Redmond, Washington, United States
Website
Pricing

No tracked provider token pricing is available yet.

Links
Website

About

MAI-Code-1.1-Flash is Microsoft AI's successor to MAI-Code-1-Flash: a sparse Mixture-of-Experts coding model (138B total / 5B active per the model card) with a 256K context window, text and image input, and text output. It launched in GitHub Copilot on 2026-08-11 with native vision, stronger coding and tool use, and a lower list price than 1-Flash. Microsoft reports SWE-Bench Verified 72.6% and Terminal-Bench 2.1 62.9% in the Copilot harness, ~25% better token efficiency, and about one quarter the cost of the June 1.0 Flash launch. GitHub Copilot models-and-pricing (per 1M tokens): $0.20 input, $0.02 cached input, $1.20 output.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

VisionMultimodalReasoningJSON / Tool usePrompt Caching

Benchmark peer barsfor Coding

SWE-bench VerifiedRank 55 of 90
Claude Fable 5
96.0
Claude Opus 5
96.0
Claude Mythos Preview
93.9
Claude Opus 4.8
88.6
MAI-Code-1.1-Flashcurrent
72.6

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
SWE-bench Verified72.6—Observed 2026-10-08—Source
Terminal-Bench 2.162.9—Observed 2026-10-08—Source

Migration checks

No linked migration route is available for this model yet.

API versions

MAI-Code-1.1-Flashmai-code-1.1-flashmai-code-1-1-flashMAI Code 1.1 Flash