Google: Gemma 4 31B
TextImageTextgoogle/gemma-4-31b-it
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
by GoogleApr 2, 2026256K context$0.225/M in$0.625/M out
2 of 32 models
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.
Prices are in USD per 1 million tokens and are what you pay. Credit purchases carry a separate platform fee; see pricing.