Hub/Models/google/gemma-4-31b-it
googleimage + text + video → text

Google: Gemma 4 31B

Canonical ID: google/gemma-4-31b-it

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
Intelligence Index4.4 / 100
Engineering Index11.9 / 100
Strategy & Ops6.9 / 100
Finance & Accounting8.2 / 100
Legal Index7.3 / 100

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.20
Input
Completion Output (1M Tokens)
$0.40
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
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