Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Modalities
In / Out Price
$0.0765 / $0.255 per 1M
Context
262K
Released
Apr 3, 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
13 / 13
| Provider | Status | Last 5m | Last 30m | Last day |
|---|---|---|---|---|
 Darkbloom | Operational | 100.00% | 100.00% | 100.00% |
 Io Net | Operational | 100.00% | 100.00% | 100.00% |
 DekaLLM | Operational | 100.00% | 100.00% | 99.93% |
 DeepInfra | Operational | 100.00% | 100.00% | 100.00% |
 NextBit | Operational | 100.00% | 100.00% | 100.00% |
 Makora | Operational | 100.00% | 100.00% | 99.79% |
 CoreWeave | Operational | 100.00% | 100.00% | 99.65% |
 Cloudflare | Operational | 100.00% | 100.00% | 99.24% |
 Venice | Operational | 100.00% | 100.00% | 99.44% |
 Parasail | Operational | 100.00% | 100.00% | 99.58% |
 Novita | Operational | 100.00% | 100.00% | 100.00% |
 SiliconFlow | Operational | 100.00% | 100.00% | 90.90% |
 Google | Operational | 100.00% | 100.00% | 96.88% |