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 |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp8fp8 | Healthy | 99.53% | 98.31% | 924ms | 7.09s | 16 tps | 131K | $0.080 / $0.160 |
Novitanovita/bf16bf16 | Degraded | 99.44% | 95.18% | 966ms | 10.3s | 15 tps | 98K | $0.119 / $0.200 |
Parasailparasail/fp8fp8 | Healthy | 98.22% | 99.53% | 721ms | 5.63s | 24 tps | 131K | $0.080 / $0.450 |
Nebiusnebius/fp8fp8 | Degraded | 96.38% | 86.58% | 386ms | 5.46s | 38 tps | 110K | $0.100 / $0.300 |
Phalaphala | No data | — | 91.24% | 3.81s | 7.27s | 10 tps | 262K | $0.150 / $0.460 |
- DeepInfra99.53%Healthy24h 98.31%
- p50
- 924ms
- p99
- 7.09s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Novita99.44%Degraded24h 95.18%
- p50
- 966ms
- p99
- 10.3s
- Throughput
- 15 tps
- Context
- 98K
- $/Mtok
- $0.119 / $0.200
novita/bf16bf16 - Parasail98.22%Healthy24h 99.53%
- p50
- 721ms
- p99
- 5.63s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.450
parasail/fp8fp8 - Nebius96.38%Degraded24h 86.58%
- p50
- 386ms
- p99
- 5.46s
- Throughput
- 38 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - Phala—No data24h 91.24%
- p50
- 3.81s
- p99
- 7.27s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala
Measured 2m 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, averaged over the hour.
Throughput
Median tokens per second.