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% | 1.15s | 12.1s | 62 tps | 1.0M | $0.500 / $3.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.70% | 99.67% | 1.94s | 5.98s | 63 tps | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.70% | 99.67% | 840ms | 1.25s | 178 tps | 1.0M | $0.900 / $5.40 |
Googlegoogle-vertex/global | Healthy | 97.94% | 97.88% | 1.26s | 14.0s | 57 tps | 1.0M | $0.500 / $3.00 |
Googlegoogle-vertex/global/flex | Healthy | 97.94% | 97.88% | 13.8s | 27.5s | 5.0 tps | 1.0M | $0.250 / $1.50 |
Googlegoogle-vertex/global/priority | Healthy | 97.94% | 97.88% | 1.74s | 3.82s | 95 tps | 1.0M | $0.900 / $5.40 |
- Google AI Studio99.70%Healthy24h 99.67%
- p50
- 1.15s
- p99
- 12.1s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-ai-studio - Google AI Studio99.70%Healthy24h 99.67%
- p50
- 1.94s
- p99
- 5.98s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-ai-studio/flex - Google AI Studio99.70%Healthy24h 99.67%
- p50
- 840ms
- p99
- 1.25s
- Throughput
- 178 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-ai-studio/priority - Google97.94%Healthy24h 97.88%
- p50
- 1.26s
- p99
- 14.0s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-vertex/global - Google97.94%Healthy24h 97.88%
- p50
- 13.8s
- p99
- 27.5s
- Throughput
- 5.0 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-vertex/global/flex - Google97.94%Healthy24h 97.88%
- p50
- 1.74s
- p99
- 3.82s
- Throughput
- 95 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.
Throughput
Median tokens per second.