Google: Gemma 4 31B
google/gemma-4-31b-it
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...
Modalities
In / Out Price
$0.09 / $0.34 per 1M
Context
262K
Released
Apr 2, 2026
Knowledge Cutoff
—
Uptime
Share of successful requests per carrier, measured over the last 5 minutes, 30 minutes and day. When one carrier dips, the router fails over to the next.
Carriers
13
Best carrier, 30m
100.00%
Healthy now
9 / 13
| Provider | Status | Last 5m | Last 30m | Last day |
|---|---|---|---|---|
 DeepInfra | Operational | 100.00% | 100.00% | 99.93% |
 CoreWeave | Operational | 100.00% | 100.00% | 100.00% |
 Venice | Operational | 100.00% | 100.00% | 99.72% |
 Chutes | Degraded | 100.00% | 100.00% | 63.33% |
 Crusoe | Degraded | 100.00% | 76.67% | 98.29% |
 Friendli | Operational | 100.00% | 100.00% | 96.25% |
 Novita | Degraded | 80.00% | 93.33% | 59.86% |
 Parasail | Operational | 100.00% | 100.00% | 99.86% |
| DeepInfra | Operational | 100.00% | 100.00% | 100.00% |
 Io Net | Operational | 100.00% | 100.00% | 92.76% |
 SambaNova | Degraded | 100.00% | 81.25% | 89.39% |
 ModelRun | Operational | 100.00% | 100.00% | 98.96% |
 SiliconFlow | Operational | 100.00% | 96.67% | 90.36% |