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 | 99.73% | 99.57% | 838ms | 5.60s | 21 tps | 131K | $0.080 / $0.450 |
DeepInfradeepinfra/fp8fp8 | Healthy | 99.72% | 98.29% | 1.50s | 11.9s | 11 tps | 131K | $0.080 / $0.160 |
Novitanovita/bf16bf16 | Down | 60.07% | 94.30% | 1.74s | 33.4s | 12 tps | 98K | $0.119 / $0.200 |
Nebiusnebius/fp8fp8 | Down | 33.23% | 88.75% | 2.23s | 10.4s | 5.0 tps | 110K | $0.100 / $0.300 |
Phalaphala | No data | — | 90.72% | 1.87s | 8.26s | 12 tps | 262K | $0.150 / $0.460 |
- Parasail99.73%Healthy24h 99.57%
- p50
- 838ms
- p99
- 5.60s
- Throughput
- 21 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.450
parasail/fp8fp8 - DeepInfra99.72%Healthy24h 98.29%
- p50
- 1.50s
- p99
- 11.9s
- Throughput
- 11 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Novita60.07%Down24h 94.30%
- p50
- 1.74s
- p99
- 33.4s
- Throughput
- 12 tps
- Context
- 98K
- $/Mtok
- $0.119 / $0.200
novita/bf16bf16 - Nebius33.23%Down24h 88.75%
- p50
- 2.23s
- p99
- 10.4s
- Throughput
- 5.0 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - Phala—No data24h 90.72%
- p50
- 1.87s
- p99
- 8.26s
- Throughput
- 12 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.
Throughput
Median tokens per second.