Tencent: Hy-MT2 Pro
hy-mt2-pro- Input / Output
- $0.074 / $0.295
- Context
- 4K
- Max output
- 4K
- Modalities
- Chat
About Hy-MT2 Pro
Hy-MT2 Pro is a translation model from Tencent Hunyuan's Hy-MT2 family, which covers 33 languages. It is built for translating whole passages rather than isolated sentences: product copy, correspondence, and localized content. The Hy-MT2 family supports terminology references, style instructions, background context, and preserving JSON or XML structure while only visible text is translated.
Where it works well
- Terminology control: you can supply reference translations so product names and domain terms stay consistent.
- Structured text: the Hy-MT2 family keeps JSON and XML formatting intact and translates only the user-visible content.
- Context awareness: background information in the prompt informs word choice across a passage.
- Style adaptation: instructions can steer output toward a requested tone or register.
- Instructions can be written in several languages, as Tencent states for the family.
When to choose another model
- The context window is small, so long documents must be split into sections before sending.
- It is a translation specialist, so it suits translation jobs rather than open-ended questions or code.
- Rare language pairs may need a short test, since quality is not equal across all 33 languages.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses APIPOST/v1/responsesAPI format:curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "hy-mt2-pro", "input": "Hello!" }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Pricing
per 1M tokens- Verified price
- —
- Official price
- Input$0.074per 1M tokensOutput$0.295per 1M tokens
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Input | $0.074 | — | — |
| Output | $0.295 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Hy-MT2 Pro in Console with a prompt ready to edit or send.
Help me try hy-mt2-pro with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Product copy localization
Translate item titles and descriptions into many markets with a glossary that pins brand names and technical terms.
Customer correspondence
Translate emails and support replies while preserving politeness and tone the sender intended.
App string files
Send JSON or XML resource files and receive translated values with keys and markup left untouched.
Cross-language review
Check how a translated contract paragraph reads back in the source language.
Prompt examples
Translate this product description into Japanese. Keep 'TrailPro' untranslated and use the glossary below for all technical terms.
Translate the values in this JSON file into Spanish and leave keys, placeholders like {name}, and HTML tags unchanged.
Translate this apology email into formal German; the customer is a long-standing enterprise client.
Cost calculator
FAQ
What is Hy-MT2 Pro?
It is a Tencent Hunyuan translation model from the Hy-MT2 family, which translates among 33 languages and is designed for complex real-world text instead of short sentences.
Which languages does it support?
Tencent states that the Hy-MT2 family translates among 33 languages, including Chinese, English, French, Spanish, Japanese, Korean, and Arabic. Rare language pairs deserve a short sample test first.
Can it keep my terminology consistent?
Yes. Tencent documents terminology support: give reference translations for key terms in the prompt, and the model follows them. Pair this with background context for domain-specific text.
Does it preserve JSON and XML?
Tencent states that Hy-MT2 preserves structured formats such as JSON and XML and translates only the visible content. Still validate the output programmatically, since a model can occasionally alter markup.
Can I translate a long document in one call?
Probably not. The family has a short context window, so split long documents by section and carry a glossary and a short background note in every request.
How much does Hy-MT2 Pro cost?
On TokenLab, Hy-MT2 Pro costs Input $0.074 / Output $0.295 per 1M tokens. The pricing table above shows the full breakdown.
What are the context window and output limit of Hy-MT2 Pro?
Hy-MT2 Pro accepts up to 4,096 tokens of context and returns up to 4,096 tokens in one response.
Which endpoint should Hy-MT2 Pro use?
Use https://api.tokenlab.sh/v1/responses for Hy-MT2 Pro. The request example below shows the matching code shape.
Which operations does Hy-MT2 Pro support?
Hy-MT2 Pro supports Text to text. Select an operation above to see its endpoint and request example.
Compare Hy-MT2 Pro
Sources
Reviewed Oct 2, 2026
