tencent
Tencent: Hy-MT2-7B
tencent/hy-mt2-7b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
tencent/hy-mt2-7b is the 7B-parameter member of Tencent's Hy-MT2 multilingual translation family, released as an open-source Apache-2.0 text-to-text model. Tencent describes coverage across 33 languages plus Chinese dialect and minority-language pairs, with prompt workflows for terminology, style, personalization, delimiters, context, and structured data. The OpenRouter catalog lists an 8192-token context and structured-output support. Vendor-reported evaluations describe strong translation quality, but this pack contains no independent scores, so teams should validate it on their own workloads.[1][2]
Strengths
- Tencent reports translation among 33 languages, plus five Chinese dialect and minority-language pairs.[1][2]
- Documented prompt patterns cover terminology, style-guided, contextual, delimiter-preserving, and structured-data translation.[1][2]
- OpenRouter lists text input and output, an 8192-token context, and parameters including max_tokens, temperature, stop, response_format, and structured_outputs.[1]
Limitations
- The evidence is limited to Tencent documentation and the OpenRouter catalog; no independent evaluation was supplied.[1][2]
- Quality claims are vendor-reported and detailed scores are not included here, so real workload validation is still needed.[2]
- Hardware requirements, safety behavior, and knowledge cutoff are not specified; OpenRouter lists text as the only input and output modality.[1][2]
Where to use it
- Consider evaluating it for localization workflows that need terminology, style, or personalization constraints.[2]
- It may fit structured-content translation where tags, keys, placeholders, or delimiters must be preserved.[2]
- It could be tested for multilingual customer or content workflows within its documented language coverage.[1][2]
Sources
- [1] OpenRouter catalog · Tencent: Hy-MT2-7BSources checked: Nov 13, 2026
- [2] Model documentation · Tencent: Hy-MT2-7BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.
Specifications
- Model ID
- tencent/hy-mt2-7b
- Canonical ID
- tencent/hy-mt2-7b-20260521
- Creator
- tencent
- Added to OpenRouter
- 19.08.2026
- Context length
- 8,192
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.074 / out $0.295
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Tencentfp8 | 8,192 | $0.074 | $0.295 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.