Back to all models
google
googleGoogle: Gemma 4 31B
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...
google/gemma-4-31b-it
Context Size
262.144K
Input Price
18,000 pts/M
Output Price
55,500 pts/M
Architecture
Image
Text
Video
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerGemma
Max Completion16,384 tokens
Provider Context262.144K tokens
ModeratedNo
CreatedApr 2, 2026