Gemma 4 31B (free) vs Gemma 4 26B A4B (free)
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 4 31B (free)Gemma 4 26B A4B (free)
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Gemma 4 31B (free) | 1/1 | 100% Google AI Studio | 1.11s Google AI Studio | 10.3s Google AI Studio | 29 tps Google AI Studio | 262K | free / free Google AI Studio |
| Gemma 4 26B A4B (free) | 2/2 | 100% Google AI Studio | 1.05s Google AI Studio | 20.5s Google AI Studio | 41 tps Google AI Studio | 262K | free / free Darkbloom |
Measured 4m 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.