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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.17% | 99.32% | 99.32% | 1.36s | 5.89s | 29 tps | 262K | $0.120 / $0.400 | |
| Healthy | 99.98% | 99.72% | 99.82% | 99.82% | 682ms | 2.68s | 45 tps | 262K | $0.100 / $0.400 | |
| Healthy | 99.98% | 99.81% | 99.41% | 99.41% | 357ms | 3.05s | 28 tps | 262K | $0.070 / $0.340 | |
Cloudflarecloudflare | Healthy | 99.96% | 97.07% | 94.01% | 94.01% | 468ms | 11.0s | 52 tps | 256K | $0.100 / $0.300 |
| Healthy | 99.92% | 93.33% | 95.33% | 95.33% | 880ms | 7.67s | 33 tps | 262K | $0.130 / $0.400 | |
| Healthy | 99.46% | 99.34% | 99.32% | 99.32% | 1.01s | 8.66s | 23 tps | 256K | $0.130 / $0.400 | |
Googlegoogle-vertex/global | Healthy | 99.35% | 97.47% | 98.01% | 98.01% | 588ms | 11.6s | 26 tps | 262K | $0.150 / $0.600 |
| Healthy | 99.32% | 98.34% | 98.57% | 98.57% | 598ms | 8.57s | 25 tps | 262K | $0.130 / $0.400 | |
Darkbloomdarkbloom | Degraded | 94.64% | 95.95% | 96.19% | 96.19% | 4.25s | 26.0s | 5.0 tps | 131K | $0.050 / $0.250 |
- SiliconFlow100%Healthy24h 99.17%
- 7d
- 99.32%
- 30d
- 99.32%
- p50
- 1.36s
- p99
- 5.89s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.120 / $0.400
siliconflow/fp8fp8 - NextBit99.98%Healthy24h 99.72%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 682ms
- p99
- 2.68s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.400
nextbit/bf16bf16 - DeepInfra99.98%Healthy24h 99.81%
- 7d
- 99.41%
- 30d
- 99.41%
- p50
- 357ms
- p99
- 3.05s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.340
deepinfra/fp8fp8 - Cloudflare99.96%Healthy24h 97.07%
- 7d
- 94.01%
- 30d
- 94.01%
- p50
- 468ms
- p99
- 11.0s
- Throughput
- 52 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.300
cloudflare - Novita99.92%Healthy24h 93.33%
- 7d
- 95.33%
- 30d
- 95.33%
- p50
- 880ms
- p99
- 7.67s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.400
novita/bf16bf16 - Venice99.46%Healthy24h 99.34%
- 7d
- 99.32%
- 30d
- 99.32%
- p50
- 1.01s
- p99
- 8.66s
- Throughput
- 23 tps
- Context
- 256K
- $/Mtok
- $0.130 / $0.400
venice/bf16bf16 - Google99.35%Healthy24h 97.47%
- 7d
- 98.01%
- 30d
- 98.01%
- p50
- 588ms
- p99
- 11.6s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
google-vertex/global - Parasail99.32%Healthy24h 98.34%
- 7d
- 98.57%
- 30d
- 98.57%
- p50
- 598ms
- p99
- 8.57s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.400
parasail/bf16bf16 - Darkbloom94.64%Degraded24h 95.95%
- 7d
- 96.19%
- 30d
- 96.19%
- p50
- 4.25s
- p99
- 26.0s
- Throughput
- 5.0 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
darkbloom
Measured 1m 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.