Vision-Language Model with thinking paradigm and reinforcement learning. Achieves state-of-the-art performance among 10B-parameter VLMs. Supports 64k context length, handles arbitrary aspect ratios and up to 4K image resolution. Bilingual Chinese/English.
Added Jul 9, 2025
Context Window
64.0K
Max Output
8.2K
Input Price (Auto)
$0.30/1M
Output Price (Auto)
$0.30/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
No benchmark data is available yet for this model.
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
