Gemma 3 27B
google/gemma-3-27b-it
Compare with Gemma 3 12B, Gemma 3 4B, Gemma 3n 4B
CompareGemma 3 27B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Parasailparasail/fp8fp8 | Healthy | 100% | 99.51% | 630ms | 5.82s | 19 tps | 131K | $0.080 / $0.450 |
Novitanovita/bf16bf16 | Healthy | 98.39% | 94.81% | 673ms | 4.93s | 25 tps | 98K | $0.119 / $0.200 |
DeepInfradeepinfra/fp8fp8 | Healthy | 98.29% | 98.31% | 913ms | 7.09s | 19 tps | 131K | $0.080 / $0.160 |
Nebiusnebius/fp8fp8 | Down | 32.58% | 85.93% | 1.29s | 7.04s | 10 tps | 110K | $0.100 / $0.300 |
Phalaphala | No data | — | 91.08% | 3.18s | 9.42s | 10 tps | 262K | $0.150 / $0.460 |
- Parasail100%Healthy24h 99.51%
- p50
- 630ms
- p99
- 5.82s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.450
parasail/fp8fp8 - Novita98.39%Healthy24h 94.81%
- p50
- 673ms
- p99
- 4.93s
- Throughput
- 25 tps
- Context
- 98K
- $/Mtok
- $0.119 / $0.200
novita/bf16bf16 - DeepInfra98.29%Healthy24h 98.31%
- p50
- 913ms
- p99
- 7.09s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Nebius32.58%Down24h 85.93%
- p50
- 1.29s
- p99
- 7.04s
- Throughput
- 10 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - Phala—No data24h 91.08%
- p50
- 3.18s
- p99
- 9.42s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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.
Throughput
Median tokens per second.