Hy-MT2-7B API

Hy-MT2-7B is a 7B-parameter translation model from Tencent supporting 33 language pairs plus five Chinese dialect and minority-language pairs.

Modalities: TextText
In / Out price: $0.0783/$0.3121per 1M
Context window: 8K tokens
Released: Aug 19, 2026

Hy-MT2-7B overview

Hy-MT2-7B by Tencent

Meet Hy-MT2-7B, Tencent's 7B-parameter translation model supporting 33 language pairs and five Chinese dialects.

Hy-MT2-7B specs

Model ID: tencent/hy-mt2-7b
Developer: Tencent
Context window: 8,192 tokens
Max output: 4,096 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is Hy-MT2-7B API?

Hy-MT2-7B is a 7B-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 workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

Technical Reference

Developer	Tencent
Model ID	tencent/hy-mt2-7b
Release Date	August 19, 2026
Context Window	8,192 tokens
Max Output Tokens	4,096
Parameters	7B
Modalities	Text (input) → Text (output)
Capabilities	Streaming

Balanced size and language coverage

Sitting between the 1.8B and 30B-A3B models in the Hy-MT2 family, it targets a middle ground of translation quality and cost across 33 language pairs plus five Chinese dialect and minority-language pairs.

Multiple translation workflows

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.

Streaming output

Responses can be streamed token-by-token for lower perceived latency in interactive translation flows.

General-purpose translation

A balanced default for translation workloads that don't need the largest model in the family.

Use cases

Multi-dimensional evaluations show Hy-MT2-7B is suited to general translation tasks. It is also documented as suitable for real-world business translation tasks. The model is described as effective for domain-specific translation tasks. It is further documented as suited to instruction-following translation tasks.

Capabilities

Streaming

Hy-MT2-7B API pricing

Hy-MT2-7B pricing in US dollars
Usage	Price	Unit
Input	$0.0783	1M tokens
Output	$0.3121	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Hy-MT2-7B vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Hy-MT2-7B	$0.0783	$0.3121
Hy-MT2-1.8B	$0.0466	$0.1873
Hy-MT2-30B-A3B	$0.0783	$0.3121
Hy3	$0.2116	$0.8464
Hy4 Preview	$0.8824	$2.65

How to use the Hy-MT2-7B API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "tencent/hy-mt2-7b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "tencent/hy-mt2-7b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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-mt2-7b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Hy-MT2-7B FAQ

What is the context window of Hy-MT2-7B?

Hy-MT2-7B has a 8,192 tokens context window and can return up to 4,096 tokens.

What inputs and outputs does Hy-MT2-7B support?

Hy-MT2-7B takes text as input and returns text.

What is the model ID for Hy-MT2-7B?

Use tencent/hy-mt2-7b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Hy-MT2-7B released?

Hy-MT2-7B became available on August 19, 2026.

How much does Hy-MT2-7B cost?

Hy-MT2-7B costs $0.0783 input and $0.3121 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Hy-MT2-7B support streaming?

Yes, Hy-MT2-7B can stream responses as they are generated.

Who created Hy-MT2-7B?

Hy-MT2-7B was built by Tencent.

How many language pairs does Hy-MT2-7B support?

Hy-MT2-7B supports 33 language pairs plus five Chinese dialect and minority-language pairs.

Start building with Hy-MT2-7B

Get API key

Hy-MT2-7B API

tencent/hy-mt2-7b

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "tencent/hy-mt2-7b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "tencent/hy-mt2-7b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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-mt2-7b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Hy-MT2-7B API

Hy-MT2-7B overview

Hy-MT2-7B by Tencent

Hy-MT2-7B specs

What Is Hy-MT2-7B API?

Technical Reference

Balanced size and language coverage

Multiple translation workflows

Streaming output

General-purpose translation

Use cases

Capabilities

Hy-MT2-7B API pricing

Hy-MT2-7B vs other models: token prices

How to use the Hy-MT2-7B API

Build with your agent

1Get your API key

2Make your first request

Related articles

Hy-MT2-7B FAQ

Start building with Hy-MT2-7B

Hy-MT2-7B API

Build with your agent

1Get your API key

2Make your first request

Hy-MT2-7B API

Hy-MT2-7B overview

Hy-MT2-7B by Tencent

Hy-MT2-7B specs

What Is Hy-MT2-7B API?

Technical Reference

Balanced size and language coverage

Multiple translation workflows

Streaming output

General-purpose translation

Use cases

Capabilities

Hy-MT2-7B API pricing

Hy-MT2-7B vs other models: token prices

How to use the Hy-MT2-7B API

Build with your agent

1Get your API key

2Make your first request

Models similar to Hy-MT2-7B

Hy4 Preview

Hy-MT2-1.8B

Hy-MT2-30B-A3B

Ling-3.0-flash

Ternary Bonsai 2 27B

Seed 1.6 Flash

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Hy-MT2-7B FAQ

Start building with Hy-MT2-7B