Alibaba Cloud: Qwen-MT Plus

Translation model for multilingual conversion, localization, and cross-language workflows

qwen-mt-plus

AvailableAlibaba CloudChat

Input / Output: $2.46 / $7.37
Context: 8K
Max output: 8K
Modalities: Chat

About Qwen-MT Plus

Qwen-MT Plus is the highest-quality model in Alibaba's Qwen-MT translation family, fine-tuned from Qwen3 and covering 92 languages. Alibaba directs it at professional fields: formal documents, academic papers and technical reports. It is slower and costs more than Flash, and it does not stream output incrementally, so it fits batch work more than live chat.

Where it works well

Alibaba rates it highest in the family for professional domains and formal text.
It covers 92 languages, including less common ones such as Pangasinan and Maithili.
Term intervention, translation memory and domain prompting help hold legal or technical terminology steady.

When to choose another model

It does not support incremental streaming, so text arrives all at once.
It is slower and more expensive than Flash, which is enough for everyday messages.
Each request takes one user message with a limited input length, so long files need splitting.

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 textMessages API

POST/v1/messages

API format:

curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "qwen-mt-plus",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "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.

Default

per 1M tokens

Official price: Input $2.46 / Output $7.37 / Text Input $2.46 / Text Output $7.37
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default	Input $2.46 / Output $7.37 / Text Input $2.46 / Text Output $7.37	—	—

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

Model performance

Last updated Nov 1, 2026, 8:36 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Qwen-MT Plus in Console with a prompt ready to edit or send.

Help me try qwen-mt-plus with a short message at /v1/messages. Show the reply, latency, and cost.

Use cases

Technical documentation
Translate API guides and manuals with a glossary so product terms stay fixed.
Academic and legal text
Handle papers and agreements where precise wording matters more than latency, with a domain hint for the field.
Localization with translation memory
Reuse approved sentence pairs as translation memory so new pages match the wording of earlier translated ones.

Prompt examples

Translate this abstract into Chinese using academic register; keep 'transformer' as 'Transformer'.

Domain: legal. Translate the clause below into German and keep defined terms capitalized.

Translate the product manual section into Portuguese, using these glossary pairs.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

When is Qwen-MT Plus worth choosing?

When the text is formal or technical and an error costs more than extra seconds: contracts, papers, documentation. For chat and short strings, Flash is the cheaper recommended default.

How many languages does it support?

Ninety-two, the same as Flash, including rarer languages. The Lite tier covers only 31, so Plus and Flash are the choice when the language pair is uncommon.

Does it support streaming?

Not incrementally. Alibaba's documentation lists no incremental streaming for Plus, unlike Flash and Lite, so the full translation arrives only once it is complete and ready.

How do I keep terminology consistent?

Use term intervention for glossary mappings, translation memory for reference sentence pairs, and domain prompting for field-specific style. Domain prompts currently work with English targets only.

Is it a chat model?

No. It is a translation model; give it a single user message holding the text, and set source and target languages through translation options rather than a system prompt.

How much does Qwen-MT Plus cost?

On TokenLab, Qwen-MT Plus costs Input $2.46 / Output $7.37 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Qwen-MT Plus?

Qwen-MT Plus accepts up to 8,192 tokens of context and returns up to 8,192 tokens in one response.

Which endpoint should Qwen-MT Plus use?

Use https://api.tokenlab.sh/v1/messages for Qwen-MT Plus. The request example below shows the matching code shape.

Which operations does Qwen-MT Plus support?

Qwen-MT Plus supports Text to text. Select an operation above to see its endpoint and request example.