ZMIME
Comparison · 2 models · Updated Oct 4, 2026

MAI-Code-1-Flash vs MAI-Code-1.1-Flash

MAI-Code-1.1-Flash comes out ahead, 56 to 41 on our weighted score.

  1. Microsoft

    MAI-Code-1-Flash

    Released Jun 2, 2026

    41/100
    • ECI—
    • Price—
    • Context256K
    Full specs Remove MAI-Code-1-Flash
  2. Our pick

    Microsoft

    MAI-Code-1.1-Flash

    Released Aug 11, 2026

    56/100
    • ECI—
    • Price—
    • Context256K
    Full specs Remove MAI-Code-1.1-Flash

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

MAI-Code-1.1-Flash is our pick

MAI-Code-1.1-Flash is the better all-round choice, scoring 56/100 against MAI-Code-1-Flash (41). It leads on inputs & features. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Longest contextAbout the sameMAI-Code-1-Flash 256,000 · MAI-Code-1.1-Flash 256,000 tokens
  • Widest inputsMAI-Code-1.1-FlashMAI-Code-1-Flash: Text · MAI-Code-1.1-Flash: Text, Images
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightMAI-Code-1-FlashMAI-Code-1.1-Flash
Inputs & features60%4570
Context window40%3636
Overall100%41/10056/100

Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

MAI-Code-1-Flash vs MAI-Code-1.1-Flash specifications side by side
SpecificationMAI-Code-1-FlashMicrosoftMAI-Code-1.1-FlashMicrosoft
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input——
Output——
Cached input——
Blended (3:1)——
Long-context rate——
Price source——
Limits
Context window256,000 tokens256,000 tokens
Max output128,000 tokens128,000 tokens
Inputs and features
TextYesYes
ImagesNoYes
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningYesYes
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model ID——
API providers——
ReleasedJun 2, 2026Aug 11, 2026
Knowledge cutoffDec 2025—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • MAI-Code-1-Flash—
  • MAI-Code-1.1-Flash—
04 — Questions

Which should you choose?

Which is better: MAI-Code-1-Flash or MAI-Code-1.1-Flash?

MAI-Code-1.1-Flash is the better all-round choice, scoring 56/100 against MAI-Code-1-Flash (41). It leads on inputs & features. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, MAI-Code-1-Flash or MAI-Code-1.1-Flash?

None of these models has a published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. MAI-Code-1-Flash has not been scored yet and MAI-Code-1.1-Flash has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for MAI-Code-1-Flash and MAI-Code-1.1-Flash yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.

Which has the bigger context window?

MAI-Code-1-Flash and MAI-Code-1.1-Flash share the same 256,000-token context window. Maximum output per response: MAI-Code-1-Flash up to 128,000, MAI-Code-1.1-Flash up to 128,000 tokens.

Which can read images, PDFs, audio or video?

MAI-Code-1-Flash accepts text; MAI-Code-1.1-Flash accepts text and images. MAI-Code-1.1-Flash handles the widest range of inputs.

Are any of these open source?

No. MAI-Code-1-Flash and MAI-Code-1.1-Flash are proprietary and only available through APIs and apps.

Which is newer?

MAI-Code-1.1-Flash is the newest, released Aug 11, 2026. MAI-Code-1-Flash came out Jun 2, 2026. Knowledge cutoff: MAI-Code-1-Flash Dec 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons