Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Hy-MT2-7B

Tencent· released 19 Aug 2026

tencent/hy-mt2-7b
Input / 1M tokens
$0.074
Output / 1M tokens
$0.295
Context window8K tokens

Longest answer: 4K tokens

reads textopen weights
See it on openrouter.ai

About

Hy-MT2-7B is Tencent's 7B-parameter translation model for text input and output. It supports 33 language pairs and five Chinese dialect and minority-language pairs. Listed translation workflows include structured, delimiter-based, contextual, glossary-based, and style-guided approaches. The model has open weights, an 8,192-token context window, and a maximum output of 4,096 tokens. Input costs $0.074 per 1M tokens and output costs $0.295 per 1M tokens. Its model ID is tencent/hy-mt2-7b, and its listed Hugging Face ID is tencent/Hy-MT2-7B. The release date is August 19, 2026. For teams selecting a translation model, the supported language-pair coverage, workflow types, context size, and output cap are practical points to check against their needs.

Who it is for

It suits teams building text translation workflows for its listed language pairs and workflow styles. Its 8,192-token context window and 4,096-token output limit are relevant when matching it to translation tasks.

What is good

  • Supports 33 language pairs
  • Includes five Chinese dialect and minority-language pairs
  • Open weights are available
  • Offers glossary-based and style-guided workflows

What to know first

  • Context window is 8,192 tokens
  • Maximum output is 4,096 tokens

Verdict

Hy-MT2-7B is focused on translation, with several workflow styles and open weights. Check its language coverage and output limit against the texts your stack needs to process.

Details

Lab
Tencentopenrouter.ai · 3 Oct 2026
Context
8Kopenrouter.ai · 3 Oct 2026
Input price
$0.074 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.295 / 1Mopenrouter.ai · 3 Oct 2026
Max output
4,096 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources