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 | Healthy | 99.63%◆ (best) | 99.76% | 99.76%◆ (best) | 99.76%◆ (best) | 2.21s | 13.9s | 141 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.63%◆ (best) | 99.76% | 99.76%◆ (best) | 99.76%◆ (best) | 2.08s | 14.9s | 130 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.63%◆ (best) | 99.76% | 99.76%◆ (best) | 99.76%◆ (best) | 2.04s◆ (best) | 9.96s◆ (best) | 187 tps◆ (best) | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global | Healthy | 99.31% | 98.54% | 98.45% | 98.45% | 2.33s | 16.7s | 83 tps | 1.0M | $0.375 / $1.88 |
Googlegoogle-vertex/global/flex | Healthy | 99.31% | 98.54% | 98.45% | 98.45% | 13.4s | 135s | 17 tps | 1.0M | $0.188 / $0.938◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 99.31% | 98.54% | 98.45% | 98.45% | 2.20s | 42.7s | 137 tps | 1.0M | $0.675 / $3.38 |
- Google AI Studio99.63%◆ (best)Healthy24h 99.76%
- 7d
- 99.76%◆ (best)
- 30d
- 99.76%◆ (best)
- p50
- 2.21s
- p99
- 13.9s
- Throughput
- 141 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio99.63%◆ (best)Healthy24h 99.76%
- 7d
- 99.76%◆ (best)
- 30d
- 99.76%◆ (best)
- p50
- 2.08s
- p99
- 14.9s
- Throughput
- 130 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - Google AI Studio99.63%◆ (best)Healthy24h 99.76%
- 7d
- 99.76%◆ (best)
- 30d
- 99.76%◆ (best)
- p50
- 2.04s◆ (best)
- p99
- 9.96s◆ (best)
- Throughput
- 187 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google99.31%Healthy24h 98.54%
- 7d
- 98.45%
- 30d
- 98.45%
- p50
- 2.33s
- p99
- 16.7s
- Throughput
- 83 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global - Google99.31%Healthy24h 98.54%
- 7d
- 98.45%
- 30d
- 98.45%
- p50
- 13.4s
- p99
- 135s
- Throughput
- 17 tps
- Context
- 1.0M
- $/Mtok
- $0.188 / $0.938◆ (best)
google-vertex/global/flex - Google99.31%Healthy24h 98.54%
- 7d
- 98.45%
- 30d
- 98.45%
- p50
- 2.20s
- p99
- 42.7s
- Throughput
- 137 tps
- Context
- 1.0M
- $/Mtok
- $0.675 / $3.38
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, averaged over the hour.
Throughput
Median tokens per second.