ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Hy4 preview vs MiMo-V2.6-Flash vs Macaron V1 Venti

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Tencent

    Hy4 preview

    Released Aug 28, 2026

    45/100
    • ECI—
    • Price$0.834 / $2.50
    • Context1.02M
  2. Xiaomi

    MiMo-V2.6-Flash

    Released Sep 22, 2026New

    81/100
    • ECI—
    • Price$0.14 / $0.28
    • Context1.05M
  3. Mindlab

    Macaron V1 Venti

    Released Jul 21, 2026

    45/100
    • ECI—
    • Price$0.825 / $2.48
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.6-Flash 81/100, Macaron V1 Venti 45/100, Hy4 preview 45/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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
  • Lowest priceMiMo-V2.6-FlashMiMo-V2.6-Flash $0.175 · Macaron V1 Venti $1.24 · Hy4 preview $1.25 per 1M tokens (3:1 blend)
  • Longest contextMiMo-V2.6-Flash and Macaron V1 VentiMiMo-V2.6-Flash 1,048,576 · Macaron V1 Venti 1,048,576 · Hy4 preview 1,024,000 tokens
  • Widest inputsMiMo-V2.6-FlashHy4 preview: Text · MiMo-V2.6-Flash: Text, Images, Audio, Video · Macaron V1 Venti: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightHy4 previewMiMo-V2.6-FlashMacaron V1 Venti
Price50%438244
Inputs & features30%359035
Context window20%656565
Specs & price only100%45/10081/10045/100

Left out because at least one model lacks the data: capability. 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.

Hy4 preview vs MiMo-V2.6-Flash vs Macaron V1 Venti specifications side by side
SpecificationHy4 previewTencentMiMo-V2.6-FlashXiaomiMacaron V1 VentiMindlab
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.834$0.14 (best)$0.825
Output$2.50$0.28 (best)$2.48
Cached input$0.042$0.0028 (best)—
Blended (3:1)$1.25$0.175 (best)$1.24
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Tencent TokenHub APIOfficial Xiaomi APIMedian of 1 providers
Limits
Context window1,024,000 tokens1,048,576 tokens (best)1,048,576 tokens (best)
Max output64,000 tokens131,072 tokens (best)131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoYesNo
VideoNoYesNo
ReasoningYeshighYesYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenOpenOpenMIT
API model IDhy4-previewmimo-v2.6-flash—
API providers1826 (best)1
ReleasedAug 28, 2026Sep 22, 2026Jul 21, 2026
Knowledge cutoff———
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.

  • Hy4 preview$13.34
  • MiMo-V2.6-Flash$1.96
  • Macaron V1 Venti$13.20
04 — Questions

Which should you choose?

Which is better: Hy4 preview, MiMo-V2.6-Flash or Macaron V1 Venti?

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.6-Flash 81/100, Macaron V1 Venti 45/100, Hy4 preview 45/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Hy4 preview, MiMo-V2.6-Flash or Macaron V1 Venti?

MiMo-V2.6-Flash is cheaper at $0.14 input / $0.28 output per million tokens (official Xiaomi API price). Macaron V1 Venti costs $0.825 input / $2.48 output per million tokens (median across 1 API provider); Hy4 preview costs $0.834 input / $2.50 output per million tokens (official Tencent TokenHub API price). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for MiMo-V2.6-Flash versus $1.24 for Macaron V1 Venti (7.1× as much) and $1.25 for Hy4 preview (7.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Hy4 preview has not been scored yet, MiMo-V2.6-Flash has not been scored yet and Macaron V1 Venti has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Hy4 preview, MiMo-V2.6-Flash and Macaron V1 Venti yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

MiMo-V2.6-Flash and Macaron V1 Venti have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,024,000 for Hy4 preview. Maximum output per response: Hy4 preview up to 64,000, MiMo-V2.6-Flash up to 131,072, Macaron V1 Venti up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Hy4 preview accepts text; MiMo-V2.6-Flash accepts text, images, audio and video; Macaron V1 Venti accepts text. MiMo-V2.6-Flash handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (MIT), so you can self-host them.

Which is newer?

MiMo-V2.6-Flash is the newest, released Sep 22, 2026. Hy4 preview came out Aug 28, 2026; Macaron V1 Venti came out Jul 21, 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 Nov 18, 2026.