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 | 99.88% | 99.58% | 1.75s | 12.3s | 160 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.88% | 99.58% | 1.83s | 10.5s | 236 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.88% | 99.58% | 2.16s | 9.06s | 27 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global | Healthy | 99.25% | 98.75% | 2.45s | 17.0s | 82 tps | 1.0M | $0.375 / $1.88 |
Googlegoogle-vertex/global/flex | Healthy | 99.25% | 98.75% | 12.3s | 57.1s | 21 tps | 1.0M | $0.188 / $0.938 |
Googlegoogle-vertex/global/priority | Healthy | 99.25% | 98.75% | 2.12s | 5.54s | 127 tps | 1.0M | $0.675 / $3.38 |
- Google AI Studio99.88%Healthy24h 99.58%
- p50
- 1.75s
- p99
- 12.3s
- Throughput
- 160 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio99.88%Healthy24h 99.58%
- p50
- 1.83s
- p99
- 10.5s
- Throughput
- 236 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - Google AI Studio99.88%Healthy24h 99.58%
- p50
- 2.16s
- p99
- 9.06s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google99.25%Healthy24h 98.75%
- p50
- 2.45s
- p99
- 17.0s
- Throughput
- 82 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global - Google99.25%Healthy24h 98.75%
- p50
- 12.3s
- p99
- 57.1s
- Throughput
- 21 tps
- Context
- 1.0M
- $/Mtok
- $0.188 / $0.938
google-vertex/global/flex - Google99.25%Healthy24h 98.75%
- p50
- 2.12s
- p99
- 5.54s
- Throughput
- 127 tps
- Context
- 1.0M
- $/Mtok
- $0.675 / $3.38
google-vertex/global/priority
Measured 3m 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.