Qwen-VL-OCR
Qwen-VL-OCR is a vision-language OCR model for recognizing, parsing and processing text in images. This model ID identifies the November 20, 2025 snapshot. Alibaba's release page lists it under…
MODEL DIRECTORY
New releases, in one place. Explore models by their publication date.
Qwen-VL-OCR is a vision-language OCR model for recognizing, parsing and processing text in images. This model ID identifies the November 20, 2025 snapshot. Alibaba's release page lists it under…
Qwen-MT-Lite is a basic-tier, text-to-text multilingual translation model based on Qwen3. It is positioned for low-cost, low-latency translation, including real-time chat and live comments. Alibaba…
CosyVoice-v3-Flash is a Tongyi Lab speech synthesis and voice-cloning model. It converts text to audio, including through real-time streaming, and can create a custom voice from 5–20 seconds of…
Qwen3-ASR-Flash-Filetrans is the large-file transcription variant of Qwen3-ASR-Flash, an LLM-based multilingual automatic speech recognition model. It accepts audio and produces text, automatically…
ERNIE 5.0 Preview is the preview of Baidu’s natively omni-modal ERNIE 5.0 foundation model, unveiled on November 13, 2025 at Baidu World 2025. At launch, Baidu said the preview was available to the…
WebVIA-Agent is a vision-language web exploration model in the WebVIA framework, built on GLM-4.1V-9B-Base. It navigates websites and collects screenshots of multiple UI states to support interactive…
GUI-Plus is a graphical-user-interface interaction foundation model for understanding and interacting with mobile and desktop interfaces. Alibaba lists its release date as November 12, 2025.…
UI2Code^N is a vision-language model for interactive UI-to-code generation, built on GLM-4.1V-9B-Base. Its model card lists approximately 10 billion parameters, BF16 weights and an MIT license. The…
An introduction in this language is coming soon.
An introduction in this language is coming soon.