Hub/Models/google/gemma-4-26b-a4b-it
googleimage + text + video → text

Google: Gemma 4 26B A4B

Canonical ID: google/gemma-4-26b-a4b-it

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
Strategy & Ops5.3 / 100
Finance & Accounting7.1 / 100
Legal Index6.9 / 100

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.07
Input
Completion Output (1M Tokens)
$0.22
Output
Prompt KV-Cache Read (1M Tokens)
$0.04
Cached
Context Window Capacity
256k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p