ThePromptBuddy logoThePromptBuddy

Google

Google: Gemma 4 26B A4B

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Specifications
ProviderGoogle
Input pricing$0.12/M tokens
Output pricing$0.35/M tokens
Context length262K tokens
Max output262K tokens
Input modalities
imagetextvideo
Output modalities
text
TokenizerGemma
Content moderatedNo
HuggingFacegoogle/gemma-4-26B-A4B-it

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p