Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3.1 Pro and GLM 5.3-Flash from Synthetic
Novita AI logo

Model details

Qwen MT Plus

Qwen MT Plus is a specialized large language model built upon the foundation of the Tongyi Qianwen architecture, specifically engineered to excel in machine translation tasks. Designed to facilitate seamless multilingual communication, the model supports a broad range of 92 languages, including Chinese, English, Japanese, Korean, Thai, and various European and Middle Eastern tongues. Its design intent focuses on delivering high-fidelity translations, making it a robust tool for complex requirements such as document translation, website localization, content globalization, and academic research.

The model benefits from a fine-tuned lineage that emphasizes translation quality, incorporating advanced features like term intervention and translation memory to ensure consistency and precision. By leveraging its specialized training, Qwen MT Plus provides strong performance in cross-lingual tasks, with particular expertise in Chinese-English translation. Its architecture is well-suited for professional workflows that demand reliable, context-aware language processing, positioning it as a practical solution for developers and organizations looking to integrate high-quality, scalable translation capabilities into their applications.

Novita AIqwen/qwen-mt-plusqwen

Quick Info

Powered by
Provider
Novita AI
Model key
qwen/qwen-mt-plus
Release date
Jul 24, 2025
Last updated
Jul 24, 2025
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.25
Output token cost
$0.75

Limits

Output tokens
8,192 tokens
Context window
16,384 tokens

Transparent token rates

Compare Qwen MT Plus pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Qwen MT Plus

Novita AI

CoverageDocumentation

Qwen-MT-Plus is the Qwen series' flagship translation model, now fully upgraded to the Qwen3 architecture and supporting 92 languages for highly accurate, natural-sounding translations. The Alibaba Cloud Model Studio documentation confirms strong contextual understanding, terminology control, and format preservation suited to specialized domains. The model is text-in and text-out only, with an 8,192-token max input, 8,192-token max output, and a 16,384-token context window. Function calling, structured outputs, web search, prefix completion, context caching, batch inference, and fine-tuning are all unsupported, while rate limits sit at 60 RPM with 25,000 or 100,000 TPM depending on region.

Sulat also reports on AI and tech beyond the catalog.Read news.sulat.com

Videos about Qwen MT Plus

More models around Qwen MT Plus