AI Hub
All models
MultimodalOpen weights

Gemma 4 31B

Google

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
Multimodal
Access
Open weights
Released
April 2, 2026
Context window
262,144 tokens
Output speed
36 tok/s
Latency (TTFT)
0.79s
Input
Image, Text, Video
Output
Text
API pricing
$0.12 in · $0.37 out / 1M tokens
Capabilities
Function callingStructured output

Benchmarks

Reasoning

Compare Gemma 4 31B with

See all Gemma 4 31B alternatives →