Loading...
Loading...
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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
Price/1M
$0.21
169th cheapest
64% below median
Top 31%
Context Window
262K
67th largest
Top 27%
Input
$0.14
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.21
per 1M tokens
Cheaper than 69% of models. Median price is $0.57/1M tokens.
Daily
$0.21
Monthly
$6.15
Context Window
262K
tokens
Larger than 73% of models
Max Output
131K
tokens
50% of context
Context Window Comparison
API pricing
For full methodology details, see our methodology page.