Gemma 4 31B reasoning
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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
Capabilities
Context Window 262k tokens
Max Output 131k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.14
Output $0.40
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p