Skip to content
ModelCap

Head-to-head comparison

Hy-MT2-1.8B vs Hy-MT2-30B-A3B

Hy-MT2-1.8B (Tencent) and Hy-MT2-30B-A3B (Tencent) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 20 August 2026

As of 20 August 2026, Hy-MT2-1.8B holds the stronger ModelCap Index position (#76 vs #77); and Hy-MT2-1.8B is 1.7× cheaper per output token ($0.177/1M vs $0.295/1M).

Which should you choose?

Choose Hy-MT2-1.8B if…

  • you want the stronger overall ModelCap Index position — #76 against #77 (36.9 vs 36.9 points).
  • API cost matters — $0.177/1M output tokens against $0.295/1M, about 1.7× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.044/1M against $0.074/1M.
  • you want the more recently listed model — Hy-MT2-1.8B was listed 20 August 2026, Hy-MT2-30B-A3B 20 August 2026.

Choose Hy-MT2-30B-A3B if…

  • ModelCap publishes no field on which Hy-MT2-30B-A3B leads Hy-MT2-1.8B for this pair.

Hy-MT2-1.8B vs Hy-MT2-30B-A3B: specs, pricing and context

Specification comparison of Hy-MT2-1.8B and Hy-MT2-30B-A3B
FieldHy-MT2-1.8BTencentHy-MT2-30B-A3BTencent
ModelCap Index position#76#77
Index score36.936.9
EvidenceEstimatedEstimated
Input price / 1M tokens$0.044$0.074
Output price / 1M tokens$0.177$0.295
Context window8K tokens8K tokens
Max output tokens4K4K
API providers listed11
Weight accessOpen weightsOpen weights
Input modalitiesTextText
First listed20 August 202620 August 2026
PublisherTencentTencent

Evidence: publisher corpus prior · leave-one-anchor-out calibrated · publisher corpus prior · leave-one-anchor-out calibrated. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Hy-MT2-1.8B vs Hy-MT2-30B-A3B

Neither model has a published result on a public benchmark board ModelCap tracks yet.

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Hy-MT2-1.8B vs Hy-MT2-30B-A3B: common questions

Is Hy-MT2-1.8B better than Hy-MT2-30B-A3B?

Hy-MT2-1.8B ranks higher on the ModelCap Index as of 20 August 2026: #76 against #77. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it.

Is Hy-MT2-1.8B cheaper than Hy-MT2-30B-A3B?

Hy-MT2-1.8B is cheaper on output tokens: $0.177/1M against $0.295/1M. Input tokens are $0.044/1M for Hy-MT2-1.8B and $0.074/1M for Hy-MT2-30B-A3B. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens.

Which has the bigger context window, Hy-MT2-1.8B or Hy-MT2-30B-A3B?

Both publish a 8K-token context window.

Which is better for coding, Hy-MT2-1.8B or Hy-MT2-30B-A3B?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are Hy-MT2-1.8B and Hy-MT2-30B-A3B open-weight models?

Hy-MT2-1.8B: Open weights. Hy-MT2-30B-A3B: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Hy-MT2-1.8B and Hy-MT2-30B-A3B?

ModelCap currently lists 1 API provider for Hy-MT2-1.8B and 1 for Hy-MT2-30B-A3B, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Hy-MT2-1.8B vs Hy-MT2-30B-A3B comparison?

Every figure comes from the sealed ModelCap dataset published 20 August 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further