Gemini 3 Flash Preview
google/gemini-3-flash-preview
Compare with Gemini 2.5 Flash, Gemini 3.1 Flash Lite, Gemini 3.5 Flash
CompareGemini 3 Flash Preview
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.70% | 99.67% | 1.04s | 12.6s | 66 tps | 1.0M | $0.500 / $3.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.70% | 99.67% | 2.05s | 6.23s | 50 tps | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.70% | 99.67% | — | — | — | 1.0M | $0.900 / $5.40 |
Googlegoogle-vertex/global | Healthy | 99.02% | 97.94% | 1.24s | 13.4s | 60 tps | 1.0M | $0.500 / $3.00 |
Googlegoogle-vertex/global/flex | Healthy | 99.02% | 97.94% | 14.9s | 171s | 9.0 tps | 1.0M | $0.250 / $1.50 |
Googlegoogle-vertex/global/priority | Healthy | 99.02% | 97.94% | 2.15s | 5.18s | 102 tps | 1.0M | $0.900 / $5.40 |
- Google AI Studio99.70%Healthy24h 99.67%
- p50
- 1.04s
- p99
- 12.6s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-ai-studio - Google AI Studio99.70%Healthy24h 99.67%
- p50
- 2.05s
- p99
- 6.23s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-ai-studio/flex - Google AI Studio99.70%Healthy24h 99.67%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-ai-studio/priority - Google99.02%Healthy24h 97.94%
- p50
- 1.24s
- p99
- 13.4s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-vertex/global - Google99.02%Healthy24h 97.94%
- p50
- 14.9s
- p99
- 171s
- Throughput
- 9.0 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-vertex/global/flex - Google99.02%Healthy24h 97.94%
- p50
- 2.15s
- p99
- 5.18s
- Throughput
- 102 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-vertex/global/priority
Measured 1m 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.