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% | 99.40% | 98.61% | 98.61% | 582ms | 5.08s | 23 tps | 131K | $0.080 / $0.160 | |
| Down | 100% | 76.74% | 85.60% | 85.60% | 1.00s | 7.29s | 13 tps | 110K | $0.100 / $0.300 | |
| Down | 100% | 67.09% | 89.82% | 89.82% | 813ms | 63.4s | 21 tps | 98K | $0.119 / $0.200 | |
| Healthy | 99.87% | 99.35% | 99.31% | 99.31% | 652ms | 2.61s | 28 tps | 131K | $0.080 / $0.450 | |
Phalaphala | Degraded | 96.94% | 95.31% | 95.32% | 95.32% | 567ms | 2.83s | 75 tps | 262K | $0.150 / $0.460 |
- DeepInfra100%Healthy24h 99.40%
- 7d
- 98.61%
- 30d
- 98.61%
- p50
- 582ms
- p99
- 5.08s
- Throughput
- 23 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Nebius100%Down24h 76.74%
- 7d
- 85.60%
- 30d
- 85.60%
- p50
- 1.00s
- p99
- 7.29s
- Throughput
- 13 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - Novita100%Down24h 67.09%
- 7d
- 89.82%
- 30d
- 89.82%
- p50
- 813ms
- p99
- 63.4s
- Throughput
- 21 tps
- Context
- 98K
- $/Mtok
- $0.119 / $0.200
novita/bf16bf16 - Parasail99.87%Healthy24h 99.35%
- 7d
- 99.31%
- 30d
- 99.31%
- p50
- 652ms
- p99
- 2.61s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.450
parasail/fp8fp8 - Phala96.94%Degraded24h 95.31%
- 7d
- 95.32%
- 30d
- 95.32%
- p50
- 567ms
- p99
- 2.83s
- Throughput
- 75 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala
Measured 2m 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.