Gemini 3 Flash Preview
google/gemini-3-flash-previewInputOutput
Compare its 6 providersIncident RSSCompare with Gemini 3.1 Flash Lite, Gemini 2.5 Flash, Gemini 3.5 Flash
CompareGemini 3 Flash Preview
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/global/flex | Healthy | 100% | 99.64% | 99.63% | 46.83% | 13.6s | 47.4s | 5.0 tps | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100% | 99.99% | 99.88% | 99.92% | 1.17s | 4.14s | 115 tps | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100% | 99.96% | 99.76% | 99.86% | 767ms | 3.15s | 85 tps | 1.0M | $0.900 / $5.40 |
Googlegoogle-vertex/global | Healthy | 99.97% | 99.76% | 99.36% | 98.27% | 1.14s | 5.93s | 91 tps | 1.0M | $0.500 / $3.00 |
Google AI Studiogoogle-ai-studio | Healthy | 99.93% | 99.95% | 99.87% | 99.89% | 1.27s | 3.74s | 84 tps | 1.0M | $0.500 / $3.00 |
Googlegoogle-vertex/global/priority | No data | — | 99.87% | 99.75% | 99.82% | 1.05s | 5.22s | 22 tps | 1.0M | $0.900 / $5.40 |
- Google100%Healthy24h 99.64%
- 7d
- 99.63%
- 30d
- 46.83%
- p50
- 13.6s
- p99
- 47.4s
- Throughput
- 5.0 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-vertex/global/flex - Google AI Studio100%Healthy24h 99.99%
- 7d
- 99.88%
- 30d
- 99.92%
- p50
- 1.17s
- p99
- 4.14s
- Throughput
- 115 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-ai-studio/flex - Google AI Studio100%Healthy24h 99.96%
- 7d
- 99.76%
- 30d
- 99.86%
- p50
- 767ms
- p99
- 3.15s
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-ai-studio/priority - Google99.97%Healthy24h 99.76%
- 7d
- 99.36%
- 30d
- 98.27%
- p50
- 1.14s
- p99
- 5.93s
- Throughput
- 91 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-vertex/global - Google AI Studio99.93%Healthy24h 99.95%
- 7d
- 99.87%
- 30d
- 99.89%
- p50
- 1.27s
- p99
- 3.74s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-ai-studio - No data24h 99.87%
- 7d
- 99.75%
- 30d
- 99.82%
- p50
- 1.05s
- p99
- 5.22s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-vertex/global/priority
Measured 4m 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, averaged over the hour.
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, 41 endpoint-days below 90%.