GLM-4.1V-9B-Thinking is a 9B parameter vision-language model developed by THUDM, based on the GLM-4-9B foundation. It introduces a reasoning-centric "thinking paradigm" enhanced with reinforcement learning to improve multimodal reasoning, long-context understanding (up to 64K tokens), and complex problem solving. It achieves state-of-the-art performance among models in its class, outperforming even larger models like Qwen-2.5-VL-72B on a majority of benchmark tasks.
Modalities
Context
66K
Released
Jul 11, 2025
Knowledge Cutoff
Mar 2025
Token volume and request traffic to this model over time.
GLM-4.1V-9B-Thinking is a 9B parameter vision-language model developed by THUDM, based on the GLM-4-9B foundation. It introduces a reasoning-centric "thinking paradigm" enhanced with reinforcement learning to improve multimodal reasoning, long-context understanding (up to 64K tokens), and complex problem solving.
GLM 4.1V 9B Thinking has a 65,536 token context window.
GLM 4.1V 9B Thinking accepts images and text as input and returns text.
GLM 4.1V 9B Thinking was released on July 11, 2025. Its knowledge cutoff is March 31, 2025.