Gemini 2.5 Flash: 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 | 100%◆ (best) | 99.90% | 99.89% | 99.92% | 1.55s | 14.4s | 127 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.98% | 99.78% | 99.94%◆ (best) | 469ms◆ (best) | 1.72s | 195 tps◆ (best) | 1.0M | $0.150 / $1.25◆ (best) |
Googlegoogle-vertex/global | Healthy | 99.80% | 99.65% | 99.69% | 99.61% | 730ms | 5.23s | 91 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/eu | Healthy | 99.68% | 99.49% | 99.41% | 99.30% | 851ms | 2.86s | 88 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex | Down | 63.79% | 93.99% | 78.98% | 78.65% | 2.31s | 29.4s | 149 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/global/priority | No data | — | 99.90% | 99.96% | 99.93% | 857ms | 1.49s◆ (best) | 64 tps | 1.0M | $0.540 / $4.50 |
Google AI Studiogoogle-ai-studio/priority | No data | — | — | 100%◆ (best) | 99.88% | — | — | — | 1.0M | $0.540 / $4.50 |
- Google AI Studio100%◆ (best)Healthy24h 99.90%
- 7d
- 99.89%
- 30d
- 99.92%
- p50
- 1.55s
- p99
- 14.4s
- Throughput
- 127 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-ai-studio - Google AI Studio100%◆ (best)Healthy24h 99.98%
- 7d
- 99.78%
- 30d
- 99.94%◆ (best)
- p50
- 469ms◆ (best)
- p99
- 1.72s
- Throughput
- 195 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-ai-studio/flex - Google99.80%Healthy24h 99.65%
- 7d
- 99.69%
- 30d
- 99.61%
- p50
- 730ms
- p99
- 5.23s
- Throughput
- 91 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google99.68%Healthy24h 99.49%
- 7d
- 99.41%
- 30d
- 99.30%
- p50
- 851ms
- p99
- 2.86s
- Throughput
- 88 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/eu - Google63.79%Down24h 93.99%
- 7d
- 78.98%
- 30d
- 78.65%
- p50
- 2.31s
- p99
- 29.4s
- Throughput
- 149 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex - No data24h 99.90%
- 7d
- 99.96%
- 30d
- 99.93%
- p50
- 857ms
- p99
- 1.49s◆ (best)
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority
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.