Hy-MT2-7B
Hy-MT2-7B is a large language model made by Tencent, added to the catalog on 19 Aug 2026. It has a context window of 8,192 tokens and costs $0.074 per 1M input tokens and $0.295 per 1M output tokens. It accepts text and produces text. Typical uses: text translation across supported language pairs, glossary-guided translation and context-aware translation.
Price checked ยท source: OpenRouter
What Hy-MT2-7B is
Tencent Hy-MT2-7B is a text translation model from Tencent. The provider describes it as a 7B-parameter model that supports 33 language pairs and five Chinese dialect and minority-language pairs. Its listed translation workflows include structured and delimiter-based translation, plus workflows guided by context, glossaries, or style. These options describe ways to frame translation requests; the catalog does not name the individual languages or pairs.
It accepts text and produces text. Its context window is 8,192 tokens, and its maximum output is 4,096 tokens. The context window provides room for source text and additional prompt material in the same request, while the output limit sets a cap on generated text. The model also supports structured outputs and response formats. These capabilities are relevant when translated results need to be returned in a specified format or organized around a structured workflow.
Hy-MT2-7B is suited to translation tasks where a request specifies contextual information, preferred terminology through a glossary, or a desired style. Delimiter-based workflows are also listed, as are structured workflows. Its stated coverage includes language pairs as well as Chinese dialect and minority-language pairs, but the provider description does not give a list of languages or explain the exact directions supported. A prospective use therefore depends on whether the required pair and workflow are included in the model's support.
Key features
- Supports 33 language pairs and five Chinese dialect and minority-language pairs.
- Supports structured, delimiter-based, contextual, glossary-based, and style-guided translation.
- Accepts text and produces text.
- Has an 8,192-token context window and a 4,096-token maximum output.
- Supports structured outputs and response formats.
Typical uses
- Text translation across supported language pairs
- Glossary-guided translation
- Context-aware translation
- Style-guided translation
- Structured translation outputs
Hy-MT2-7B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.074 |
| Output, per 1M tokens | $0.295 |
No price change since it was added on 19 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0028 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.012 |
Hy-MT2-7B specifications
| Model id | tencent/hy-mt2-7b |
|---|---|
| Version | hy-mt2-7b-20260521 |
| Context window | 8,192 tokensAbout 6,144 English words |
| Max output | 4,096 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 19 Aug 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | No |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Hy-MT2-7B yet.
Compare Hy-MT2-7B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.