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% | 99.31% | 98.56% | 98.56% | 637ms | 4.66s | 23 tps | 131K | $0.080 / $0.160 | |
| Healthy | 100% | 76.88% | 85.27% | 85.27% | 685ms | 2.57s | 24 tps | 110K | $0.100 / $0.300 | |
| Healthy | 99.68% | 99.31% | 99.29% | 99.29% | 570ms | 2.72s | 34 tps | 131K | $0.080 / $0.450 | |
Phalaphala | Degraded | 97.94% | 95.94% | 95.72% | 95.72% | 457ms | 2.94s | 80 tps | 262K | $0.150 / $0.460 |
| Down | 32.82% | 68.82% | 90.01% | 90.01% | 752ms | 61.7s | 23 tps | 98K | $0.119 / $0.200 |
- DeepInfra100%Healthy24h 99.31%
- 7d
- 98.56%
- 30d
- 98.56%
- p50
- 637ms
- p99
- 4.66s
- Throughput
- 23 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Nebius100%Healthy24h 76.88%
- 7d
- 85.27%
- 30d
- 85.27%
- p50
- 685ms
- p99
- 2.57s
- Throughput
- 24 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - Parasail99.68%Healthy24h 99.31%
- 7d
- 99.29%
- 30d
- 99.29%
- p50
- 570ms
- p99
- 2.72s
- Throughput
- 34 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.450
parasail/fp8fp8 - Phala97.94%Degraded24h 95.94%
- 7d
- 95.72%
- 30d
- 95.72%
- p50
- 457ms
- p99
- 2.94s
- Throughput
- 80 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala - Novita32.82%Down24h 68.82%
- 7d
- 90.01%
- 30d
- 90.01%
- p50
- 752ms
- p99
- 61.7s
- Throughput
- 23 tps
- Context
- 98K
- $/Mtok
- $0.119 / $0.200
novita/bf16bf16
Measured 1m 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.