← Nano Banana 2 (Gemini 3.1 Flash Image)
Nano Banana 2 (Gemini 3.1 Flash Image): providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.02%◆ (best) | 99.20% | 99.37% | 99.37% | 9.86s◆ (best) | 19.3s◆ (best) | 146 tps◆ (best) | 66K | $0.500 / $3.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 96.76% | 99.49% | 99.42%◆ (best) | 99.42%◆ (best) | 11.5s | 19.7s | 91 tps | 131K | $0.500 / $3.00◆ (best) |
- Google AI Studio99.02%◆ (best)Healthy24h 99.20%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 9.86s◆ (best)
- p99
- 19.3s◆ (best)
- Throughput
- 146 tps◆ (best)
- Context
- 66K
- $/Mtok
- $0.500 / $3.00◆ (best)
google-ai-studio - Google96.76%Healthy24h 99.49%
- 7d
- 99.42%◆ (best)
- 30d
- 99.42%◆ (best)
- p50
- 11.5s
- p99
- 19.7s
- Throughput
- 91 tps
- Context
- 131K
- $/Mtok
- $0.500 / $3.00◆ (best)
google-vertex/global
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.