Hy MT2 7B
Neural Network
Hy MT2 7B is a Tencent translation model with 7B parameters: 33 language pairs, context awareness, and glossary-based translation.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Hy MT2 7B?
Hy MT2 7B is a specialized machine translation model from Tencent with 7B parameters. It covers 33 language pairs, plus five pairs involving Chinese dialects and minority languages. It supports multiple modes: translating structured documents, delimited texts, context-aware translation, glossary-based translation, and style-specific translation. In BotHub, Hy MT2 7B is accessible without a VPN or foreign card; payment is made in rubles via Russian cards based on actual usage, and unused tokens do not expire. Over 250 models are available in the same window, and a unified OpenAI-compatible API allows you to integrate translation into your services and switch models later without rewriting the integration. It is useful for localizers and translation agencies with a unified glossary, product teams for translating interfaces and documentation, support teams for client correspondence, and editors or researchers working with Chinese and its dialects. For companies, we offer contracts, invoices, electronic document management (EDO), and an admin panel with limits.Frequently asked questions about Hy MT2 7B
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
hy-mt2-7b is a Tencent text model from the Hunyuan family, focused on translation and precise wording. It accepts text and documents as input, with an 8192-token context window. It is suitable for translation, rewriting, summarizing, and parsing small files.
Up to 4096 tokens per response, which is several pages of text. Note that the total window is 8192 tokens, which includes your prompt and the attached document. It is better to process long material in parts using sequential requests.
A dedicated reasoning mode is not noted in our data; we won't deny it, but we cannot promise it. If you need step-by-step logic, ask for it directly in the prompt: break down the task, compare options, or explain the choice of wording.
Support for function calling and strict JSON is not noted in our data for hy-mt2-7b. For scenarios where the response schema is critical, it is more convenient to use another model: BotHub has a unified OpenAI-compatible API, so switching will not require rewriting the integration.
Images, audio, and video as input are not noted in our data: hy-mt2-7b works with text and documents. Upload text files and ask to translate, summarize, or format them. For media, BotHub has multimodal models—switching is available in the same window.
The set of languages for hy-mt2-7b is not specified in our data, so we cannot promise specific quality in Russian—please test it with your own text. In BotHub, it's easy: pay per token, no subscription, no VPN, and no foreign card required.