← 模型广场
Google: Gemma 4 31B (free)
google/gemma-4-31b-it:free
图像理解工具调用JSON推理流式
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
参数
上下文
262,144 tokens
输入模态
image, text, video
输出模态
text
发布：2026-04
支持参数
include_reasoningmax_tokensreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_p