← Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Nano Banana 2 Lite (Gemini 3.1 Flash Lite 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/global | Healthy | 100% | 99.94% | 99.92% | 99.89% | 8.08s | 20.0s | 0.0 tps◆ (best) | 66K | $0.250 / $1.50◆ (best) |
Google AI Studiogoogle-ai-studio | No data | — | 99.91% | 100%◆ (best) | 100%◆ (best) | 6.42s◆ (best) | 14.7s◆ (best) | 0.0 tps◆ (best) | 66K | $0.250 / $1.50◆ (best) |
- Google100%Healthy24h 99.94%
- 7d
- 99.92%
- 30d
- 99.89%
- p50
- 8.08s
- p99
- 20.0s
- Throughput
- 0.0 tps◆ (best)
- Context
- 66K
- $/Mtok
- $0.250 / $1.50◆ (best)
google-vertex/global - No data24h 99.91%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 6.42s◆ (best)
- p99
- 14.7s◆ (best)
- Throughput
- 0.0 tps◆ (best)
- Context
- 66K
- $/Mtok
- $0.250 / $1.50◆ (best)
google-ai-studio
Measured 5m 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.