Gemini 3.7 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/flex | Healthy | 100%◆ (best) | 99.95% | 99.91%◆ (best) | 99.77% | 2.23s | 9.78s | 159 tps | 1.0M | $0.375 / $1.88◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.99% | 99.90% | 99.65% | 2.02s◆ (best) | 6.98s | 170 tps◆ (best) | 1.0M | $1.35 / $6.75 |
Google AI Studiogoogle-ai-studio | Healthy | 99.97% | 99.86% | 99.63% | 99.60% | 2.80s | 12.8s | 169 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global | Healthy | 99.46% | 99.10% | 98.95% | 99.36% | 3.22s | 14.4s | 80 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/flex | Down | — | 99.14% | 99.49% | 84.68% | 89.0s | 284s | 31 tps | 1.0M | $0.375 / $1.88◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.57% | 99.84% | 99.78%◆ (best) | 2.26s | 6.36s◆ (best) | 144 tps | 1.0M | $1.35 / $6.75 |
- Google AI Studio100%◆ (best)Healthy24h 99.95%
- 7d
- 99.91%◆ (best)
- 30d
- 99.77%
- p50
- 2.23s
- p99
- 9.78s
- Throughput
- 159 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-ai-studio/flex - Google AI Studio100%◆ (best)Healthy24h 99.99%
- 7d
- 99.90%
- 30d
- 99.65%
- p50
- 2.02s◆ (best)
- p99
- 6.98s
- Throughput
- 170 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google AI Studio99.97%Healthy24h 99.86%
- 7d
- 99.63%
- 30d
- 99.60%
- p50
- 2.80s
- p99
- 12.8s
- Throughput
- 169 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google99.46%Healthy24h 99.10%
- 7d
- 98.95%
- 30d
- 99.36%
- p50
- 3.22s
- p99
- 14.4s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Down24h 99.14%
- 7d
- 99.49%
- 30d
- 84.68%
- p50
- 89.0s
- p99
- 284s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-vertex/global/flex - No data24h 99.57%
- 7d
- 99.84%
- 30d
- 99.78%◆ (best)
- p50
- 2.26s
- p99
- 6.36s◆ (best)
- Throughput
- 144 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/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.
Throughput
Median tokens per second.