Qwen-MT-Turbo
Retired Oct 2026The lighter of Alibaba's two Qwen-MT translation models, fine-tuned from Qwen3 with reinforcement learning, with terminology intervention, domain prompts and translation memory.
- Context
- 16K tokens
- Max output
- 8K
Capabilities
What Qwen-MT-Turbo accepts and can do, as published by Alibaba Cloud.
- Text Accepts and generates natural-language text.
Common questions
What is Qwen-MT-Turbo good for?
High-volume translation across the same 92 languages as Qwen-MT-Plus, with terminology controls, domain prompts and translation memory. It is the lighter of Alibaba's two Qwen-MT models.
When is Qwen-MT-Turbo not a good fit?
New integrations: Alibaba says the model will not be updated further and points users to a Flash variant. Closed weights, so no self-hosting.
Can I self-host Qwen-MT-Turbo?
No. Alibaba Cloud does not publish the weights; Qwen-MT-Turbo is available only through hosted APIs.
More from Alibaba Cloud
-
Qwen3-Coder-Plus
1M context
-
Qwen3.5-Flash
1M context
From $0.09 / $0.368 /1M in / out at the cheapest provider
-
Qwen3.5-Plus
1M context
From $0.36 / $2.21 /1M in / out at the cheapest provider
-
Qwen3.6-Flash
1M context
From $0.25 / $1.50 /1M in / out at the cheapest provider
-
Qwen3.6-Plus
1M context
From $0.50 / $3.00 /1M in / out at the cheapest provider
-
Qwen3.7-Flash
1M context
From $0.03 / $0.13 /1M in / out at the cheapest provider
-
Qwen3.7-Max
1M context
From $1.25 / $3.75 /1M in / out at the cheapest provider
-
Qwen3.7-Plus
1M context
From $0.276 / $1.101 /1M in / out at the cheapest provider