google
Google: Gemma 4 31B
google/gemma-4-31b-it
For $1, you can send approximately:
~292messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.12/M = $0.000840
Output cost per message7,000 x $0.37/M = $0.002590
Total cost per message$0.003430
Messages for $1291.55
Context window
262k
tokens
Max response
16k
tokens
Input price
$0.12
per million tokens
Output price
$0.37
per million tokens
Modalities
Input:imageInput:textInput:videoOutput:text
Description
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...