← Nano Banana (Gemini 2.5 Flash Image)
Nano Banana (Gemini 2.5 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.60% | 99.65% | 99.65% | 6.00s | 12.4s | 168 tps | 33K | $0.300 / $2.50 |
Googlegoogle-vertex/global/flex | Healthy | 100%◆ (best) | 99.60% | 99.65% | 99.65% | — | — | — | 33K | $0.150 / $1.25◆ (best) |
Google AI Studiogoogle-ai-studio | No data | — | 99.95% | 100%◆ (best) | 100%◆ (best) | 878ms | 18.7s | 212 tps◆ (best) | 33K | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | No data | — | 99.95% | 100%◆ (best) | 100%◆ (best) | 410ms◆ (best) | 5.48s◆ (best) | 206 tps | 33K | $0.150 / $1.25◆ (best) |
Google AI Studiogoogle-ai-studio/priority | No data | — | 99.95% | 100%◆ (best) | 100%◆ (best) | — | — | — | 33K | $0.540 / $4.50 |
- Google100%◆ (best)Healthy24h 99.60%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 6.00s
- p99
- 12.4s
- Throughput
- 168 tps
- Context
- 33K
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google100%◆ (best)Healthy24h 99.60%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 33K
- $/Mtok
- $0.150 / $1.25◆ (best)
google-vertex/global/flex - No data24h 99.95%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 878ms
- p99
- 18.7s
- Throughput
- 212 tps◆ (best)
- Context
- 33K
- $/Mtok
- $0.300 / $2.50
google-ai-studio - No data24h 99.95%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 410ms◆ (best)
- p99
- 5.48s◆ (best)
- Throughput
- 206 tps
- Context
- 33K
- $/Mtok
- $0.150 / $1.25◆ (best)
google-ai-studio/flex - No data24h 99.95%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 33K
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority
Measured 2m 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.