Skip to content
RankShark

Hy-MT2-1.8B

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.

ModelOpen sourceby Tencentsince 2026
28.7

SharkScore

#331 in Models

Why it scores 28.7

Hy-MT2-1.8B has a SharkScore of 28.7/100, ranked #331 of 608 in Models (updated 2026-11-19).

Each part compares Hy-MT2-1.8B with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
5 · 30%
User reviews
no data · 25%
Maintenance
15 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of Hy-MT2-1.8B

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, Hy-MT2-1.8B is Tencent’s translation model; OpenRouter lists an 8,192-token context and charges $0.044/$0.177 per million input/output tokens. [E1, E2]

A 1.8B-parameter text-to-text model from Tencent for multilingual translation. Its model page describes translation instructions for real-world tasks and provides inference and fine-tuning guidance. [E1, E2]

Best for

  • People building multilingual translation workflows, including glossary, style, contextual, or structured-text translation. · model card, OpenRouter
  • Teams seeking a model they can run with Transformers, vLLM, or SGLang. · model card

Not for

  • People seeking a general-purpose model rather than one described specifically for translation. · model card, OpenRouter

Key features

  • Multilingual translation. The vendor says the Hy-MT2 family supports translation among 33 languages and follows translation instructions in multiple languages. · model card
  • Instruction-guided translation. The vendor gives examples for terminology, style, personalization, delimiters, structured data, and contextual information. · model card
  • Inference options. The vendor documents running the model with Transformers, vLLM, and SGLang. · model card
  • Fine-tuning. The vendor says its training pipeline supports full-parameter and LoRA fine-tuning. · model card
  • Open-source license. The model page lists the Apache-2.0 license. · model card

Pros

  • The vendor documents translation controls for style, terminology, formatting, and contextual information. · model card
  • The vendor provides instructions for local inference with several frameworks and documents fine-tuning options. · model card
  • The model page lists an Apache-2.0 license. · model card

Cons

  • The vendor says the model has no default system prompt, so deployments need to supply task instructions where required. · model card
  • OpenRouter lists a maximum completion of 4,096 tokens and a context window of 8,192 tokens. · OpenRouter
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

PlanPriceLimits
OpenRouter inference$0.044 per million input tokens; $0.177 per million output tokens8,192-token context window; maximum completion of 4,096 tokens

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Hy-MT2-1.8B · model card, OpenRouter
API
OpenRouter lists chat completions, completions, messages, and responses endpoints. · OpenRouter
SDKs
Not stated (checked 18 Nov 2026)
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
The vendor documents inference with Transformers, vLLM, and SGLang. · model card
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
8,192 tokens
Price per million tokens (OpenRouter listing) · now
$0.044 in, $0.177 out
Package downloads · 30 days
21,628
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to Hy-MT2-1.8B

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source