Hy-MT2-1.8B
Hy-MT2-1.8B 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 $0.044 per 1M input tokens and $0.177 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 · source: OpenRouter
What Hy-MT2-1.8B is
Tencent Hy-MT2-1.8B is a text-to-text translation model from Tencent. It accepts text and produces text. The catalog says it supports 33 language pairs and five Chinese dialect and minority-language pairs, though it does not identify the languages or specify the translation directions. Its stated role is translation, and its listed workflows cover ways of providing structure, context, terminology, or style guidance. The supplied details do not describe image or audio input.
Hy-MT2-1.8B has an 8,192-token context length and a maximum output of 4,096 tokens. The context limit indicates how much text can be considered in a request, while the output limit bounds the amount of generated text. These limits can help assess whether source material and relevant context fit a translation task, although the facts do not specify how tokens correspond to words or how text beyond the limit is handled. The model lists structured and delimiter-based workflows alongside contextual, glossary-based, and style-guided translation. The catalog does not explain how those workflows are configured or how they affect the output.
The model may suit translation tasks that involve supported language pairs and benefit from contextual information, glossary guidance, or a specified style. Its structured and delimiter-based options are relevant when translation content is organized using those approaches. The available facts establish the model’s text interface, context and output limits, supported pair counts, and workflow types, but do not provide further detail about particular languages or task performance.
Key features
- Accepts text and produces text
- Supports 33 language pairs and five Chinese dialect and minority-language pairs
- Provides structured and delimiter-based translation workflows
- Includes contextual, glossary-based, and style-guided workflows
- Has an 8,192-token context length and a 4,096-token maximum output
Typical uses
- Text translation across supported language pairs
- Glossary-guided translation
- Context-aware translation
- Style-guided translation
- Structured and delimiter-based translation
Hy-MT2-1.8B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.044 |
| Output, per 1M tokens | $0.177 |
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 | $0.0012 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0017 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0069 |
Hy-MT2-1.8B specifications
| Model id | tencent/hy-mt2-1.8b |
|---|---|
| Version | hy-mt2-1.8b-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 | No |
| 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-MT2-1.8B yet.
Compare Hy-MT2-1.8B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.