ZMIME
Comparison · 2 models · Updated Nov 18, 2026

Hy4 vs Hy4 preview

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

Price in rating: Excluded · Include price

  1. Tencent

    Hy4

    Released Nov 4, 2026New

    62/100
    • ECI—
    • Price$0.834 / $2.50
    • Context1.05M
  2. Tencent

    Hy4 preview

    Released Aug 28, 2026

    47/100
    • ECI—
    • Price$0.834 / $2.50
    • Context1.02M
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Hy4 62/100, Hy4 preview 47/100) compare the available specifications only. 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
  • Lowest priceSame priceHy4 $1.25 · Hy4 preview $1.25 per 1M tokens (3:1 blend)
  • Longest contextHy4Hy4 1,048,576 · Hy4 preview 1,024,000 tokens
  • Widest inputsHy4Hy4: Text, Images · Hy4 preview: Text
  • Self-hostingHy4 previewPublishes downloadable weights
How the score is built
MeasureWeightHy4Hy4 preview
Inputs & features60%6035
Context window40%6565
Specs only100%62/10047/100

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 vs Hy4 preview specifications side by side
SpecificationHy4TencentHy4 previewTencent
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input$0.834$0.834
Output$2.50$2.50
Cached input$0.042$0.042
Blended (3:1)$1.25$1.25
Long-context rateSame rateSame rate
Price sourceOfficial Tencent TokenHub APIOfficial Tencent TokenHub API
Limits
Context window1,048,576 tokens (best)1,024,000 tokens
Max output65,536 tokens (best)64,000 tokens
Inputs and features
TextYesYes
ImagesYesNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningYeshighYeshigh
Tool callingYesYes
Structured outputNoNo
Availability
WeightsProprietaryOpen
API model IDhy4hy4-preview
API providers1218 (best)
ReleasedNov 4, 2026Aug 28, 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$13.34
  • Hy4 preview$13.34
04 — Questions

Which should you choose?

Which is better: Hy4 or Hy4 preview?

There is not enough shared capability evidence to name an overall winner. The scores (Hy4 62/100, Hy4 preview 47/100) compare the available specifications only. 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, Hy4 or Hy4 preview?

Hy4 and Hy4 preview cost the same: $0.834 input / $2.50 output per million tokens.

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Hy4 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 Hy4 and Hy4 preview 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?

Hy4 has the largest context window at 1,048,576 tokens, against 1,024,000 for Hy4 preview. Maximum output per response: Hy4 up to 65,536, Hy4 preview up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Hy4 accepts text and images; Hy4 preview accepts text. Hy4 handles the widest range of inputs.

Are any of these open source?

Hy4 preview publishes its weights and can be self-hosted; Hy4 is proprietary.

Which is newer?

Hy4 is the newest, released Nov 4, 2026. Hy4 preview came out Aug 28, 2026.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.