Gemini 2.5 Pro Preview 05-06 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.
CompareGemini 2.5 Pro Preview 05-06Gemma 4 31B
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Gemini 2.5 Pro Preview 05-06 | 6/8 | 100% Google AI Studio | 1.94s Google | 2.81s Google | 90 tps Google | 1.0M | $0.625 / $5.00 Google |
| Gemma 4 31B | 11/17 | 100% Cerebras | 165ms ModelRun | 3.68s DeepInfra | 108 tps Cerebras | 262K | $0.080 / $0.350 OpenInference |
Measured 1m 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.