Gemini 3.7 Flash
google/gemini-3.7-flash
Compare with Gemini 3.6 Flash, Gemini 3.5 Flash, Gemini 3.5 Flash Lite
CompareGemini 3.7 Flash
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.96% | 99.60% | 1.86s | 12.8s | 139 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.96% | 99.60% | 1.66s | 16.1s | 415 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.96% | 99.60% | 1.18s | 1.88s | 57 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global | Healthy | 99.13% | 98.78% | 2.44s | 15.9s | 84 tps | 1.0M | $0.375 / $1.88 |
Googlegoogle-vertex/global/flex | Healthy | 99.13% | 98.78% | 17.6s | 132s | 28 tps | 1.0M | $0.188 / $0.938 |
Googlegoogle-vertex/global/priority | Healthy | 99.13% | 98.78% | 2.05s | 3.79s | 103 tps | 1.0M | $0.675 / $3.38 |
- Google AI Studio99.96%Healthy24h 99.60%
- p50
- 1.86s
- p99
- 12.8s
- Throughput
- 139 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio99.96%Healthy24h 99.60%
- p50
- 1.66s
- p99
- 16.1s
- Throughput
- 415 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - Google AI Studio99.96%Healthy24h 99.60%
- p50
- 1.18s
- p99
- 1.88s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google99.13%Healthy24h 98.78%
- p50
- 2.44s
- p99
- 15.9s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global - Google99.13%Healthy24h 98.78%
- p50
- 17.6s
- p99
- 132s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.188 / $0.938
google-vertex/global/flex - Google99.13%Healthy24h 98.78%
- p50
- 2.05s
- p99
- 3.79s
- Throughput
- 103 tps
- Context
- 1.0M
- $/Mtok
- $0.675 / $3.38
google-vertex/global/priority
Measured 47s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.