WeVisOne-VL
WeVisOne-VL is a vision-language model from Tencent in 2B and 4B sizes
Free
Multimodal
2B and 4B
parameters
Open weights
license
Oct 2026
released
WeVisOne-VL is a vision-language model from Tencent in 2B and 4B sizes. It handles detection, localization, counting, OCR, segmentation, and matting.
// similar models in Multimodal
Llama 5
Meta's next flagship open-weight multimodal model, built for on-device and datacenter use alike
Meta AI · Multimodal · Free
Gemini 3 Pro
Google's flagship multimodal model with a 1M-token context window
Google DeepMind · Multimodal · Paid
Gemini 3.5 Pro
Google's next-generation frontier model, announced but not yet fully released
Google DeepMind · Multimodal · Paid
GPT-4o
OpenAI's omni model, natively multimodal across text, image, and audio
OpenAI · Multimodal · Paid
Gemini Omni Flash
First model in Google's Omni family, combining reasoning with video generation
Google DeepMind · Multimodal · Paid
GPT-6.1 Terra
GPT-6.1 Terra is the fast, efficient model in OpenAI's GPT-6 family, with visual reasoning and computer use
OpenAI · Multimodal · Paid