Back to all models
google
googleGoogle: Gemma 4 31B (free)
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:free
Context Size
262.144K
Input Price
Free
Output Price
Free
Architecture
Image
Text
Video
Supported Parameters
include_reasoningmax_tokensmin_preasoningresponse_formatseedstoptemperaturetool_choicetoolstop_atop_ktop_p
Details
TokenizerGemma
Max Completion8,192 tokens
Provider Context262.144K tokens
ModeratedYes
CreatedApr 2, 2026