← Nano Banana Pro (Gemini 3 Pro Image)
Nano Banana Pro (Gemini 3 Pro 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 | 97.64% | 85.84% | 99.21% | 99.48% | 21.6s◆ (best) | 45.5s◆ (best) | 0.0 tps◆ (best) | 66K | $2.00 / $12.00◆ (best) |
Google AI Studiogoogle-ai-studio/global | No data | — | 99.98% | 99.93%◆ (best) | 99.97%◆ (best) | 24.7s | 63.3s | 0.0 tps◆ (best) | 131K | $2.00 / $12.00◆ (best) |
- Google97.64%Healthy24h 85.84%
- 7d
- 99.21%
- 30d
- 99.48%
- p50
- 21.6s◆ (best)
- p99
- 45.5s◆ (best)
- Throughput
- 0.0 tps◆ (best)
- Context
- 66K
- $/Mtok
- $2.00 / $12.00◆ (best)
google-vertex/global - No data24h 99.98%
- 7d
- 99.93%◆ (best)
- 30d
- 99.97%◆ (best)
- p50
- 24.7s
- p99
- 63.3s
- Throughput
- 0.0 tps◆ (best)
- Context
- 131K
- $/Mtok
- $2.00 / $12.00◆ (best)
google-ai-studio/global
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, averaged over the hour.
Throughput
Median tokens per second.