← 模型广场
Google: Gemma 4 31B
google/gemma-4-31b-it
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...
价格
输入
$0.12 / 1M
输出
$0.37 / 1M
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
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p