Google
Google: Gemma 4 31B
google/gemma-4-31b-it
Score61
Add to CompareInput / M
Output / M
Context
Max Output
262K
Usage
#28 · 0.71%
Quality
41.6 / 100
Providers
11
Best Uptime 30m
100.00%
Released
Apr 2, 2026
Modalities
image, text, video
About
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...
Capabilities
Vision
Tools
Reasoning
Streaming
JSON Mode
Providers
Per-provider pricing, uptime, latency
No provider data yet — will populate on next endpoints sync.
Benchmarks
Quality index 41.6 / 100
Artificial Analysis
intelligence index
29.4 / 100
coding index
43.4 / 100
agentic index
14.4 / 100
Performance History
53 snapshots
Price History
0 recorded changes
No price changes recorded yet.
Usage (OpenRouter)
Rank #28 of the market
0.71% share
Activity Timeline
- No events yet.
Versus
Nearest peers by price, context, and capabilities. One click to compare.
No comparable models found.
First seen 3d ago · Last verified 19m ago