← Nano Banana Pro (Gemini 3 Pro Image Preview)
Nano Banana Pro (Gemini 3 Pro Image Preview): 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/global | Healthy | 100% | 99.88% | 99.88%◆ (best) | 99.96%◆ (best) | 20.2s◆ (best) | 42.4s | 0.0 tps◆ (best) | 66K | $2.00 / $12.00 |
Google AI Studiogoogle-ai-studio/global/flex | No data | — | 99.94% | 99.83% | 99.95% | 22.1s | 33.7s◆ (best) | 0.0 tps◆ (best) | 66K | $1.00 / $6.00◆ (best) |
- Google AI Studio100%Healthy24h 99.88%
- 7d
- 99.88%◆ (best)
- 30d
- 99.96%◆ (best)
- p50
- 20.2s◆ (best)
- p99
- 42.4s
- Throughput
- 0.0 tps◆ (best)
- Context
- 66K
- $/Mtok
- $2.00 / $12.00
google-ai-studio/global - No data24h 99.94%
- 7d
- 99.83%
- 30d
- 99.95%
- p50
- 22.1s
- p99
- 33.7s◆ (best)
- Throughput
- 0.0 tps◆ (best)
- Context
- 66K
- $/Mtok
- $1.00 / $6.00◆ (best)
google-ai-studio/global/flex
Measured 4m 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.