ModelWatch

Compare models

Up to 4 models side by side.

Provider
Google
Listed
Date added to OpenRouter
Apr 2, 2026
Input price
USD per 1M tokens
$0.20
Output price
USD per 1M tokens
$0.40
Workload cost
Chat reply (2K in, 500 out)
$0.0006
Context window
262K
Max output
16K
Output speed
tokens per second
36
Time to first token
seconds
0.98s
Intelligence Index
Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations.
4.4
Engineering Index
Artificial Analysis Engineering Index: engineering and technical problem solving.
11.9
Inputs
image, text, video
Open weights
Yes
Good at
visionopen-weightslow-cost
Notes
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...

Best value in each row is highlighted. Share this page's URL to share the comparison.