The AI arena is free today

Open Superagent
MicrosoftReleased on Aug 11, 2026

MAI-Code-1.1-Flash: API Pricing, Context Window & Benchmarks

MAI-Code-1.1-Flash is a language model from Microsoft, released in August 2026, with multimodal input, a 256K-token context window, and pricing from $0.200/M input, $0.020/M cached input, $1.20/M output.

MAI-Code-1.1-Flash is a Microsoft text-to-text and image-to-text coding model built for fast, efficient assistance in everyday developer workflows, including agentic coding in real repositories, repository Q&A, refactoring, and tool-using

Input
TextImage
Output
Text

MAI-Code-1.1-Flash benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for MAI-Code-1.1-Flash across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How MAI-Code-1.1-Flash holds up as conversations get longer.

Quality Tracker

MAI-Code-1.1-Flash Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Mon Sep 07 2026
Notice missing or incorrect data?

MAI-Code-1.1-Flash pricing

Providers

MAI-Code-1.1-Flash starts at $0.200 per million input tokens and $1.20 per million output tokens via GitHub Copilot. Reused prompt prefixes cost $0.0200 per million cached input tokens.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
GitHub Copilot logoGitHub Copilot
$0.200$0.0200$1.20256.0K/
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

MAI-Code-1.1-Flash context window

Input and output token limits for MAI-Code-1.1-Flash, plus how it ranks on long-context understanding.

Input
256Ktokens
385 pages of text
256K
8K128K1M

MAI-Code-1.1-Flash API

Available from the model provider

MAI-Code-1.1-Flash is available from GitHub Copilot. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

MAI-Code-1.1-Flash latency

MAI-Code-1.1-Flash time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

MAI-Code-1.1-Flash examples

Recent arena outputs from MAI-Code-1.1-Flash, picked from the highest-ranked matchups.

MAI-Code-1.1-Flash license

MAI-Code-1.1-Flash is a proprietary model available under its provider's product and API terms, has 138.0B parameters.

License
Proprietary
Hosted access
Parameters
138.0B

Proprietary license - usage restrictions apply

MAI-Code-1.1-Flash resources

Official sources for MAI-Code-1.1-Flash: api documentation, official playground, paper or system card, official launch post, source repository.

MAI-Code-1.1-Flash vs other models

The most-compared alternatives to MAI-Code-1.1-Flash are Solar Pro 4, Claude Sonnet 4, Nemotron 3 Ultra (550B A55B). Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like MAI-Code-1.1-Flash

Models ranked just above and below MAI-Code-1.1-Flash by LLM Stats score.

 

Solar Pro 4

Score pending
 

Claude Sonnet 4

Score pending
 

Nemotron 3 Ultra (550B A55B)

Score pending
 

Claude Opus 4

Score pending
 

Qwen3.5-27B

Score pending
 

DeepSeek-V3.2

Score pending

FAQ

Common questions about MAI-Code-1.1-Flash.

When was MAI-Code-1.1-Flash released?

MAI-Code-1.1-Flash was released on August 11, 2026 by Microsoft. This is the official MAI-Code-1.1-Flash release date tracked on LLM Stats.

How much does MAI-Code-1.1-Flash cost?

MAI-Code-1.1-Flash pricing starts at $0.20 per million input tokens, $0.02 per million cached input tokens, $1.20 per million output tokens via GitHub Copilot, the lowest price among tracked providers.

Is MAI-Code-1.1-Flash available via API?

Yes, MAI-Code-1.1-Flash is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is MAI-Code-1.1-Flash?

MAI-Code-1.1-Flash has 138 billion parameters.

Who created MAI-Code-1.1-Flash?

MAI-Code-1.1-Flash was created by Microsoft.

What is the license for MAI-Code-1.1-Flash?

MAI-Code-1.1-Flash is released under the Proprietary license.

Is MAI-Code-1.1-Flash multimodal?

Yes, MAI-Code-1.1-Flash is multimodal and can accept both text and images as input.

Where can I use MAI-Code-1.1-Flash?

MAI-Code-1.1-Flash is available through 1 provider including GitHub Copilot.

Where is the MAI-Code-1.1-Flash paper or technical report?

MAI-Code-1.1-Flash has a paper or technical report available at https://microsoft.ai/pdf/MAI-Code-1.1-Flash-Model-Card.PDF. Use that source for architecture, training, release and evaluation details.

What models should I compare MAI-Code-1.1-Flash against?

Common MAI-Code-1.1-Flash comparisons include MAI-Code-1.1-Flash vs Solar Pro 4, MAI-Code-1.1-Flash vs Claude Sonnet 4, MAI-Code-1.1-Flash vs Nemotron 3 Ultra (550B A55B). Compare them side by side for benchmark scores, pricing, context window, latency and API availability.