Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
Compare with Gemma 4 31B, Gemma 4 26B A4B (free), Gemma 4 31B (free)
CompareGemma 4 26B A4B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Cloudflarecloudflare | Healthy | 99.95% | 97.09% | 93.79% | 93.79% | 596ms | 10.7s | 51 tps | 256K | $0.100 / $0.300 |
| Healthy | 99.94% | 99.79% | 99.39% | 99.39% | 392ms | 4.00s | 22 tps | 262K | $0.070 / $0.340 | |
| Healthy | 99.85% | 99.72% | 99.82% | 99.82% | 714ms | 3.58s | 41 tps | 262K | $0.100 / $0.400 | |
Googlegoogle-vertex/global | Healthy | 99.68% | 97.55% | 97.94% | 97.94% | 309ms | 8.99s | 20 tps | 262K | $0.150 / $0.600 |
| Healthy | 99.23% | 99.34% | 99.31% | 99.31% | 1.02s | 9.21s | 23 tps | 256K | $0.130 / $0.400 | |
| Healthy | 99.13% | 98.32% | 98.55% | 98.55% | 640ms | 9.66s | 26 tps | 262K | $0.130 / $0.400 | |
| Healthy | 98.86% | 99.16% | 99.30% | 99.30% | 1.31s | 7.66s | 27 tps | 262K | $0.120 / $0.400 | |
Darkbloomdarkbloom | Degraded | 94.81% | 96.22% | 96.48% | 96.48% | 3.91s | 22.9s | 6.0 tps | 131K | $0.050 / $0.250 |
| Down | 88.24% | 93.51% | 95.30% | 95.30% | 895ms | 8.92s | 28 tps | 262K | $0.130 / $0.400 |
- Cloudflare99.95%Healthy24h 97.09%
- 7d
- 93.79%
- 30d
- 93.79%
- p50
- 596ms
- p99
- 10.7s
- Throughput
- 51 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.300
cloudflare - DeepInfra99.94%Healthy24h 99.79%
- 7d
- 99.39%
- 30d
- 99.39%
- p50
- 392ms
- p99
- 4.00s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.340
deepinfra/fp8fp8 - NextBit99.85%Healthy24h 99.72%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 714ms
- p99
- 3.58s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.400
nextbit/bf16bf16 - Google99.68%Healthy24h 97.55%
- 7d
- 97.94%
- 30d
- 97.94%
- p50
- 309ms
- p99
- 8.99s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
google-vertex/global - Venice99.23%Healthy24h 99.34%
- 7d
- 99.31%
- 30d
- 99.31%
- p50
- 1.02s
- p99
- 9.21s
- Throughput
- 23 tps
- Context
- 256K
- $/Mtok
- $0.130 / $0.400
venice/bf16bf16 - Parasail99.13%Healthy24h 98.32%
- 7d
- 98.55%
- 30d
- 98.55%
- p50
- 640ms
- p99
- 9.66s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.400
parasail/bf16bf16 - SiliconFlow98.86%Healthy24h 99.16%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 1.31s
- p99
- 7.66s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.120 / $0.400
siliconflow/fp8fp8 - Darkbloom94.81%Degraded24h 96.22%
- 7d
- 96.48%
- 30d
- 96.48%
- p50
- 3.91s
- p99
- 22.9s
- Throughput
- 6.0 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
darkbloom - Novita88.24%Down24h 93.51%
- 7d
- 95.30%
- 30d
- 95.30%
- p50
- 895ms
- p99
- 8.92s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.400
novita/bf16bf16
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Gemma 4 26B A4B Darkbloomdarkbloom$0.030 / $0.165 → $0.050 / $0.2502026-08-20 20:05 UTC
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.