Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-image
Compare with Gemini 3.5 Flash, Gemini 3.1 Flash Lite, Gemini 3.6 Flash
CompareNano Banana 2 (Gemini 3.1 Flash Image)
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.65% | 99.21% | 8.00s | 19.3s | 175 tps | 66K | $0.500 / $3.00 |
Googlegoogle-vertex/global | Healthy | 99.21% | 99.44% | 10.9s | 35.6s | 88 tps | 131K | $0.500 / $3.00 |
- Google AI Studio99.65%Healthy24h 99.21%
- p50
- 8.00s
- p99
- 19.3s
- Throughput
- 175 tps
- Context
- 66K
- $/Mtok
- $0.500 / $3.00
google-ai-studio - Google99.21%Healthy24h 99.44%
- p50
- 10.9s
- p99
- 35.6s
- Throughput
- 88 tps
- Context
- 131K
- $/Mtok
- $0.500 / $3.00
google-vertex/global
Measured 52s 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.