Gemini 3 Flash Preview vs Gemini 3.1 Flash Lite
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 3 Flash PreviewGemini 3.1 Flash Lite
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 6/6 | 99.48% Google AI Studio | 1.04s Google AI Studio | 5.49s Google | 98 tps Google | 1.0M | $0.250 / $1.50 Google |
| Gemini 3.1 Flash Lite | 6/7 | 99.50% Google AI Studio | 489ms Google AI Studio | 4.09s Google AI Studio | 141 tps Google AI Studio | 1.0M | $0.125 / $0.750 Google |
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.