Hy-MT2-1.8B is a compact, 1.8B-parameter translation model from Tencent, part of the Hy-MT2 family. It supports 33 language pairs plus five Chinese dialect and minority-language pairs, with dedicated workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.
| Developer | Tencent |
|---|---|
| Model ID | tencent/hy-mt2-1.8b |
| Release Date | August 20, 2026 |
| Context Window | 8,192 tokens |
| Max Output Tokens | 4,096 |
| Parameters | 1.8B |
| Modalities | Text (input) → Text (output) |
| Capabilities | Streaming |
33 language pairs are supported, along with five Chinese dialect and minority-language pairs not typically covered by general-purpose chat models.
Structured, delimiter-based, contextual, glossary-based, and style-guided translation modes cover use cases from raw text translation to terminology-constrained and tone-controlled output.
At 1.8B parameters, it's the smallest model in the Hy-MT2 family, suited to high-volume or latency-sensitive translation.
Low per-token cost and a compact footprint suit applications that translate large volumes of text.
Glossary-based and style-guided workflows help keep terminology and tone consistent across translated content.
Dedicated support for five Chinese dialect and minority-language pairs beyond the standard 33.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Hy-MT2-1.8B is documented as suited to multilingual translation across 33 languages, including follow-through on translation instructions in multiple languages. It is also described as useful for structured, delimiter-based, contextual, glossary-based, and style-guided translation. The model is further documented for general, real-world business, domain-specific, and instruction-following translation tasks. It is additionally presented as suitable for on-device deployment and low-resource device inference.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "tencent/hy-mt2-1.8b", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "tencent/hy-mt2-1.8b", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"tencent/hy-mt2-1.8b","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Hy-MT2-1.8B This page | High-volume translation | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Hy-MT2-1.8B has a 8,192 tokens context window and can return up to 4,096 tokens.
Hy-MT2-1.8B takes text as input and returns text.
Use tencent/hy-mt2-1.8b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Hy-MT2-1.8B became available on August 20, 2026.
Hy-MT2-1.8B is priced at input $0.0605176 / 1M tokens, output $0.2434458 / 1M tokens.
Yes, Hy-MT2-1.8B can stream responses as they are generated.
Hy-MT2-1.8B was built by Tencent.
It supports 33 language pairs plus five Chinese dialect and minority-language pairs.
