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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/global/priority | Healthy | 100%◆ (best) | 99.91% | 99.96% | 99.93% | 868ms | 1.47s | 66 tps | 1.0M | $0.540 / $4.50 |
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 99.91% | 99.89% | 99.92% | 1.01s | 16.6s | 78 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.98% | 99.78% | 99.94%◆ (best) | 471ms◆ (best) | 1.82s | 202 tps◆ (best) | 1.0M | $0.150 / $1.25◆ (best) |
Googlegoogle-vertex/global | Healthy | 99.87% | 99.65% | 99.69% | 99.61% | 679ms | 3.84s | 88 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/eu | Healthy | 99.44% | 99.49% | 99.41% | 99.29% | 827ms | 2.79s | 90 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex | Down | 53.85% | 94.05% | 79.05% | 78.66% | 1.65s | 14.4s | 127 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/priority | No data | — | — | 100%◆ (best) | 99.88% | 605ms | 629ms◆ (best) | 94 tps | 1.0M | $0.540 / $4.50 |
- Google100%◆ (best)Healthy24h 99.91%
- 7d
- 99.96%
- 30d
- 99.93%
- p50
- 868ms
- p99
- 1.47s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - Google AI Studio100%◆ (best)Healthy24h 99.91%
- 7d
- 99.89%
- 30d
- 99.92%
- p50
- 1.01s
- p99
- 16.6s
- Throughput
- 78 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
- 471ms◆ (best)
- p99
- 1.82s
- Throughput
- 202 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-ai-studio/flex - Google99.87%Healthy24h 99.65%
- 7d
- 99.69%
- 30d
- 99.61%
- p50
- 679ms
- p99
- 3.84s
- Throughput
- 88 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google99.44%Healthy24h 99.49%
- 7d
- 99.41%
- 30d
- 99.29%
- p50
- 827ms
- p99
- 2.79s
- Throughput
- 90 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/eu - Google53.85%Down24h 94.05%
- 7d
- 79.05%
- 30d
- 78.66%
- p50
- 1.65s
- p99
- 14.4s
- Throughput
- 127 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.88%
- p50
- 605ms
- p99
- 629ms◆ (best)
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority
Measured 1m 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.