Gemma 4 26B A4B (free)
google/gemma-4-26b-a4b-it:free
Compare with Gemma 4 31B, Gemma 4 26B A4B , Gemma 4 31B (free)
CompareGemma 4 26B A4B (free)
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 100% | 99.26% | 1.07s | 20.8s | 41 tps | 262K | free / free |
Darkbloomdarkbloom | Degraded | 94.77% | 95.20% | 5.57s | 63.4s | 11 tps | 131K | free / free |
- Google AI Studio100%Healthy24h 99.26%
- p50
- 1.07s
- p99
- 20.8s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- free / free
google-ai-studio - Darkbloom94.77%Degraded24h 95.20%
- p50
- 5.57s
- p99
- 63.4s
- Throughput
- 11 tps
- Context
- 131K
- $/Mtok
- free / free
darkbloom
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. p50 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.