RealRelay.ai
Qwen

Qwen-MT-Lite

Qwen translation model for simple, latency-sensitive scenarios such as real-time chat and live comments.

Starting at
Input
$0.12/ 1M
Output
$0.36/ 1M
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

qwen/qwen-mt-lite
Input
$0.12 USD per 1M tokens
Output
$0.36 USD per 1M tokens
Cache read
- USD per 1M tokens
Cache write
- USD per 1M tokens

Endpoints

POST/v1/chat/completionsChat Completions

Call it

Using qwen/qwen-mt-lite

1from openai import OpenAI23client = OpenAI(4    base_url="https://www.realrelay.ai/v1",5    api_key="sk-***",6)78response = client.chat.completions.create(9    model="qwen/qwen-mt-lite",10    messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)
1import OpenAI from "openai";23const client = new OpenAI({4  baseURL: "https://www.realrelay.ai/v1",5  apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9  model: "qwen/qwen-mt-lite",10  messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);
1curl https://www.realrelay.ai/v1/chat/completions \2  -H "Authorization: Bearer $REALRELAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "qwen/qwen-mt-lite",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

Qwen-MT-Lite accepts text and returns translated text. Alibaba Cloud documents it for simple scenarios where response time matters, such as real-time chat and live comment translation.

Its 16K-token context window is sized for short messages and comments, which are the inputs these scenarios produce.

Input
Text
Output
Text

Overview

Qwen-MT-Lite is a machine translation model from Alibaba Cloud's Qwen family for simple, latency-sensitive scenarios such as real-time chat and live comment translation. It takes text in one language and returns the translation as text. It has a 16K-token context window and is priced at $0.12 per 1M input tokens.

Qwen-MT-Lite has a 16K-token context window. It accepts text input and returns text.

Pricing

Qwen-MT-Lite is priced per 1M tokens at $0.12 for input and $0.36 for output.

Qwen-MT-Lite is available through RealRelay's OpenAI-compatible API.

Use cases

Use Qwen-MT-Lite to translate messages in a live chat so that two people can follow each other in different languages as the conversation happens.

It also suits live comment streams and similar short-text feeds, where each item is translated on arrival through a simple text-in, text-out call.

Frequently asked questions

What is Qwen-MT-Lite?
Qwen-MT-Lite is a machine translation model from Alibaba Cloud's Qwen family for simple, latency-sensitive scenarios such as real-time chat and live comment translation. It takes text in one language and returns the translation as text.
How much does Qwen-MT-Lite cost?
Qwen-MT-Lite costs $0.12 per 1M input tokens and $0.36 per 1M output tokens.
What is the context window of Qwen-MT-Lite?
Qwen-MT-Lite has a 16K-token context window.
What inputs and outputs does Qwen-MT-Lite support?
Qwen-MT-Lite accepts text input and returns text.
What is Qwen-MT-Lite used for?
Qwen-MT-Lite is used for simple, latency-sensitive translation such as real-time chat and live comment translation.
How do I call Qwen-MT-Lite through the API?
Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen-mt-lite.

More from Qwen

All 41 Qwen models