Qwen-MT: Where Speed Meets Smart Translation
Qwen
Alibaba released Qwen-MT (qwen-mt-turbo), a multilingual translation model based on Qwen3 that supports 92 languages and dialects. The model was trained on trillions of multilingual and translation tokens and uses reinforcement learning to improve translation accuracy and fluency. This expansion enables high-quality translation coverage for over 95% of the global population.
Why it matters
DEMO API DISCORD Introduction Here we introduce the latest update of Qwen-MT (qwen-mt-turbo) via Qwen API. This update builds upon the powerful Qwen3, leveraging trillions multilingual and translation tokens to comprehensively enhance the model’s multilingual understanding and translation capabilities. By integrating reinforcement learning techniques, the model achieves significant improvements in translation accuracy and linguistic fluency. Key Features: Multilingual Support for 92 Languages: Qwen-MT enables high-quality translation across 92 major official languages and prominent dialects, covering over 95% of the global population to meet diverse cross-lingual communication needs.