Context
1.1M tokens (~525 books)
Input $/1M
$1.00
Output $/1M
$5.00
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data as of
About
MAI Code 2 is Microsoft AI's coding model for complex work in real repositories · sparse MoE with vision encoder, trained from scratch · 1,050,000 token context, 922,000 max input, 128,000 max output · text and image in, text out · available in GitHub Copilot · $1 input, $5 output, $0.05 cached input per 1M tokens, 50% off until May 17, 2027.
No benchmark data available yet.
Links
Research
Documentation
Community
BenchGecko API
mai-code-2
Specifications
- Typemultimodal
- Context1.1M tokens (~525 books)
- ReleasedNov 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.007
Available On
Learn More
Share & Export
Frequently Asked Questions
MAI Code 2 is a proprietary multimodal AI model by Microsoft, released in November 2026. Context window: 1M tokens.
Related Models
ERNIE-5.5-Flash-Preview (free) · baiduQwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIBenchmarks
Key facts · as of 2026-11-18
- MAI Code 2 by Microsoft. Not enough public benchmark scores to rank yet.
- List price $1.00 input · $5.00 output per 1M tokens (as of 2026-11-18).
How to cite · data as of 2026-11-18
MAI Code 2 · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-18. https://benchgecko.ai/model/mai-code-2
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP