Gemini 3.7 Flash
google/gemini-3.7-flashInputOutput
Compare its 6 providersIncident RSSCompare with Gemini 3.8 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash
CompareGemini 3.7 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.92% | 99.80% | 99.60% | 99.51% | 2.12s | 7.94s | 205 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global | Healthy | 99.90% | 99.37% | 99.08% | 99.39% | 2.35s | 9.02s | 100 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.87% | 99.94% | 99.88% | 99.68% | 1.49s | 5.77s | 177 tps | 1.0M | $0.375 / $1.88 |
Googlegoogle-vertex/global/flex | No data | — | 98.66% | 99.57% | 80.98% | 12.6s | 85.1s | 19 tps | 1.0M | $0.375 / $1.88 |
Googlegoogle-vertex/global/priority | No data | — | 99.76% | 99.80% | 99.75% | 1.80s | 3.50s | 129 tps | 1.0M | $1.35 / $6.75 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 99.94% | 99.86% | 99.61% | 1.58s | 4.56s | 79 tps | 1.0M | $1.35 / $6.75 |
- Google AI Studio99.92%Healthy24h 99.80%
- 7d
- 99.60%
- 30d
- 99.51%
- p50
- 2.12s
- p99
- 7.94s
- Throughput
- 205 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google99.90%Healthy24h 99.37%
- 7d
- 99.08%
- 30d
- 99.39%
- p50
- 2.35s
- p99
- 9.02s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Google AI Studio99.87%Healthy24h 99.94%
- 7d
- 99.88%
- 30d
- 99.68%
- p50
- 1.49s
- p99
- 5.77s
- Throughput
- 177 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - No data24h 98.66%
- 7d
- 99.57%
- 30d
- 80.98%
- p50
- 12.6s
- p99
- 85.1s
- Throughput
- 19 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global/flex - No data24h 99.76%
- 7d
- 99.80%
- 30d
- 99.75%
- p50
- 1.80s
- p99
- 3.50s
- Throughput
- 129 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority - No data24h 99.94%
- 7d
- 99.86%
- 30d
- 99.61%
- p50
- 1.58s
- p99
- 4.56s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 6 endpoints · 46 days with data, 33 endpoint-days below 90%.
Price changes
- Gemini 3.7 FlashGooglegoogle-vertex/global$0.375 → $0.750 / $1.88 → $3.75cache read $0.037 → $0.075cache write $0.021 → $0.042reasoning $1.88 → $3.752026-08-28 18:10 UTC
- Gemini 3.7 FlashGooglegoogle-vertex/global/flex$0.188 → $0.375 / $0.938 → $1.88cache read $0.019 → $0.037cache write $0.010 → $0.021reasoning $0.938 → $1.882026-08-28 18:10 UTC
- Gemini 3.7 FlashGooglegoogle-vertex/global/priority$0.675 → $1.35 / $3.38 → $6.75cache read $0.068 → $0.135cache write $0.037 → $0.075reasoning $3.38 → $6.752026-08-28 18:10 UTC