Gemma 4 31B It (free)
Google · text, image, video → text
Gemma 4 31B Instruct is a 30.7B dense multimodal model from Google DeepMind that supports both text and image inputs with text outputs. It features a massive 256K token context window, allowing it to process and analyze extensive documents and conversations. Additionally, the model offers a configurable thinking and reasoning mode along with native function support for advanced task execution.
Input$0 /M
Output$0 /M