Gemma 3 27B vs Gemma 4 31B
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareGemma 3 27BGemma 4 31B
| Gemma 3 27B | 2/5 | 99.36% | 99.44% | 99.47% | 922ms | 6.49s | 28 tps | 131K | $0.080 / $0.160 |
| Gemma 4 31B | 12/23 | 100% | 99.78% | 99.59% | 68ms | 1.12s | 122 tps | 262K | $0.070 / $0.350 |
Measured 2m ago. Each figure is the best available across that model's providers.
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest P50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.