Hy-MT2-30B-A3B
Hy-MT2-30B-A3B is a large language model made by Tencent, added to the catalog on 20 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: translating text across supported language pairs, translating Chinese dialect or minority-language pairs and contextual translation.
Price checked · source: OpenRouter
What Hy-MT2-30B-A3B is
Tencent: Hy-MT2-30B-A3B is a text-in, text-out translation model in Tencent’s Hy-MT2 family. The provider says it supports 33 language pairs and five Chinese dialect and minority-language pairs. Its listed workflows include structured, delimiter-based, contextual, and glossary-based translation. These capabilities describe a model intended for translation requests that may include formatting, delimiters, context, or terminology. The available facts do not name the individual language pairs or specify which dialects and minority languages are included.
The model accepts text and produces text, with an 8,192-token context window and a maximum output of 4,096 tokens. The context window sets the amount of input and contextual material the model can process in a request, while the output limit caps the generated response. These limits make it possible to submit translation material together with additional context, as long as the request remains within the stated context size. The facts do not specify separate limits for each language or workflow.
Structured outputs and response-format controls are also supported. They are relevant when a translation request calls for a particular output format, alongside the model’s listed structured and delimiter-based workflows. Contextual translation can incorporate supplied context, and glossary-based translation can use terminology supplied as part of a request; the provider does not describe implementation details. The known capabilities make the model relevant to translation tasks involving the listed language-pair coverage, context, glossaries, or formatting requirements. The model accepts text as its listed input modality.
Key features
- Supports 33 language pairs and five Chinese dialect and minority-language pairs
- Accepts text and produces text
- Has an 8,192-token context window and a 4,096-token maximum output
- Supports structured outputs and response-format controls
- Lists structured, delimiter-based, contextual, and glossary-based workflows
Typical uses
- Translating text across supported language pairs
- Translating Chinese dialect or minority-language pairs
- Contextual translation
- Glossary-based translation
- Formatting translation results as structured output
Hy-MT2-30B-A3B 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 20 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-MT2-30B-A3B specifications
| Model id | tencent/hy-mt2-30b-a3b |
|---|---|
| Version | hy-mt2-30b-a3b-20260521 |
| Context window | 8,192 tokensAbout 6,144 English words |
| Max output | 4,096 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 20 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-MT2-30B-A3B yet.
Compare Hy-MT2-30B-A3B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.