Gemma 3 27B
google/gemma-3-27b-it
Compare with Gemma 3 12B, Gemma 3 4B, Gemma 3n 4B
CompareGemma 3 27B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 76.88% | 85.39% | 85.39% | 582ms | 3.35s | 35 tps | 110K | $0.100 / $0.300 | |
| Healthy | 99.74% | 99.39% | 98.59% | 98.59% | 606ms | 4.18s | 25 tps | 131K | $0.080 / $0.160 | |
| Healthy | 99.54% | 99.33% | 99.30% | 99.30% | 654ms | 2.98s | 28 tps | 131K | $0.080 / $0.450 | |
Phalaphala | Degraded | 91.82% | 95.73% | 95.46% | 95.46% | 778ms | 6.05s | 39 tps | 262K | $0.150 / $0.460 |
| Down | 37.69% | 67.27% | 89.92% | 89.92% | 681ms | 64.5s | 25 tps | 98K | $0.119 / $0.200 |
- Nebius100%Healthy24h 76.88%
- 7d
- 85.39%
- 30d
- 85.39%
- p50
- 582ms
- p99
- 3.35s
- Throughput
- 35 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - DeepInfra99.74%Healthy24h 99.39%
- 7d
- 98.59%
- 30d
- 98.59%
- p50
- 606ms
- p99
- 4.18s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Parasail99.54%Healthy24h 99.33%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 654ms
- p99
- 2.98s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.450
parasail/fp8fp8 - Phala91.82%Degraded24h 95.73%
- 7d
- 95.46%
- 30d
- 95.46%
- p50
- 778ms
- p99
- 6.05s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala - Novita37.69%Down24h 67.27%
- 7d
- 89.92%
- 30d
- 89.92%
- p50
- 681ms
- p99
- 64.5s
- Throughput
- 25 tps
- Context
- 98K
- $/Mtok
- $0.119 / $0.200
novita/bf16bf16
Measured 4m 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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.