ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Macaron V1 Venti vs Viv Fast vs Hy4 preview

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. Mindlab

    Macaron V1 Venti

    Released Jul 21, 2026

    45/100
    • ECI—
    • Price$0.825 / $2.48
    • Context1.05M
  2. Vivgrid

    Viv Fast

    Released Sep 21, 2026New

    74/100
    • ECI—
    • Price$0.13 / $0.40
    • Context1M
  3. Tencent

    Hy4 preview

    Released Aug 28, 2026

    45/100
    • ECI—
    • Price$0.834 / $2.50
    • Context1.02M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Viv Fast 74/100, 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 priceViv FastViv Fast $0.198 · Macaron V1 Venti $1.24 · Hy4 preview $1.25 per 1M tokens (3:1 blend)
  • Longest contextMacaron V1 VentiMacaron V1 Venti 1,048,576 · Hy4 preview 1,024,000 · Viv Fast 1,000,000 tokens
  • Widest inputsViv FastMacaron V1 Venti: Text · Viv Fast: Text, Images · Hy4 preview: Text
  • Self-hostingMacaron V1 Venti and Hy4 previewPublishes downloadable weights (MIT)
How the score is built
MeasureWeightMacaron V1 VentiViv FastHy4 preview
Price50%448043
Inputs & features30%357035
Context window20%656465
Specs & price only100%45/10074/10045/100

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.

Macaron V1 Venti vs Viv Fast vs Hy4 preview specifications side by side
SpecificationMacaron V1 VentiMindlabViv FastVivgridHy4 previewTencent
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.825$0.13 (best)$0.834
Output$2.48$0.40 (best)$2.50
Cached input—$0.05$0.042 (best)
Blended (3:1)$1.24$0.198 (best)$1.25
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Vivgrid APIOfficial Tencent TokenHub API
Limits
Context window1,048,576 tokens (best)1,000,000 tokens1,024,000 tokens
Max output131,072 tokens256,000 tokens (best)64,000 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYeslow · high · maxYeshigh
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenMITProprietaryOpen
API model ID—viv-fasthy4-preview
API providers1118 (best)
ReleasedJul 21, 2026Sep 21, 2026Aug 28, 2026
Knowledge cutoff—Sep 2026—
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.

  • Macaron V1 Venti$13.20
  • Viv Fast$2.10
  • Hy4 preview$13.34
04 — Questions

Which should you choose?

Which is better: Macaron V1 Venti, Viv Fast or Hy4 preview?

There is not enough shared capability evidence to name an overall winner. The scores (Viv Fast 74/100, 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, Macaron V1 Venti, Viv Fast or Hy4 preview?

Viv Fast is cheaper at $0.13 input / $0.40 output per million tokens (official Vivgrid 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 $0.198 per million tokens for Viv Fast versus $1.24 for Macaron V1 Venti (6.3× as much) and $1.25 for Hy4 preview (6.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Macaron V1 Venti has not been scored yet, Viv Fast has not been scored yet and Hy4 preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Macaron V1 Venti, Viv Fast and Hy4 preview 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?

Macaron V1 Venti has the largest context window at 1,048,576 tokens, against 1,024,000 for Hy4 preview and 1,000,000 for Viv Fast. Maximum output per response: Macaron V1 Venti up to 131,072, Viv Fast up to 256,000, Hy4 preview up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Macaron V1 Venti accepts text; Viv Fast accepts text and images; Hy4 preview accepts text. Viv Fast handles the widest range of inputs.

Are any of these open source?

Macaron V1 Venti and Hy4 preview publishes its weights (MIT) and can be self-hosted; Viv Fast is proprietary.

Which is newer?

Viv Fast is the newest, released Sep 21, 2026. Hy4 preview came out Aug 28, 2026; Macaron V1 Venti came out Jul 21, 2026. Knowledge cutoff: Viv Fast Sep 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.