whichllm — Browse and compare AI model specs and pricing

Nvidia

Gemma-4-31B-IT

gemma

Model ID google/gemma-4-31b-it
Provider Nvidia
Family gemma
Status -
Knowledge Cutoff 2025-01
Release Date 2026-04-02
Input Modalities text, image, video
Output Modalities text
Context Window 256000
Input Limit -
Output Limit 16384
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens -
Output Cost / 1M tokens -
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -