Megatron MarketsWholesale
Sign inContact Us
Models Model details

Google

Google: Gemma 4 31B

google/gemma-4-31b-it

Enquire about this model Request a quote

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.

Input
$0.2

/ 1M tokens

Output
$0.4

/ 1M tokens

Context window
262.14K

tokens

Limits

Context

262,144

tokens

Max output

16,384

6.3% of the context window

Parameters

31,273,088,876

Model facts

Author

Google

Tokenizer

Gemma

Modality

Text + Image + Video -> Text

License

Apache-2.0

Created

Apr 2, 2026

Hugging Face

google/gemma-4-31B-it

Default generation parameters

temperature

1

top_k

64

top_p

0.95

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · ImageInput · TextInput · VideoOutput · Text

Generation controls

Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin pPresence penaltyReasoningRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p

Capability scores

4.2
Agentic index

Better than 28% of models compared

43.4
Coding index

Better than 38% of models compared

14.7
Intelligence index

Better than 37% of models compared