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 | 99.76% | 99.68% | 1.16s | 12.8s | 74 tps | 1.0M | $0.500 / $3.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.76% | 99.68% | 2.28s | 9.65s | 60 tps | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.76% | 99.68% | 1.18s | 1.18s | 135 tps | 1.0M | $0.900 / $5.40 |
Googlegoogle-vertex/global | Degraded | 95.65% | 96.98% | 1.56s | 16.6s | 50 tps | 1.0M | $0.500 / $3.00 |
Googlegoogle-vertex/global/flex | Degraded | 95.65% | 96.98% | 16.0s | 140s | 7.0 tps | 1.0M | $0.250 / $1.50 |
Googlegoogle-vertex/global/priority | Degraded | 95.65% | 96.98% | 1.95s | 4.49s | 94 tps | 1.0M | $0.900 / $5.40 |
- Google AI Studio99.76%Healthy24h 99.68%
- p50
- 1.16s
- p99
- 12.8s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-ai-studio - Google AI Studio99.76%Healthy24h 99.68%
- p50
- 2.28s
- p99
- 9.65s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-ai-studio/flex - Google AI Studio99.76%Healthy24h 99.68%
- p50
- 1.18s
- p99
- 1.18s
- Throughput
- 135 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-ai-studio/priority - Google95.65%Degraded24h 96.98%
- p50
- 1.56s
- p99
- 16.6s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-vertex/global - Google95.65%Degraded24h 96.98%
- p50
- 16.0s
- p99
- 140s
- Throughput
- 7.0 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-vertex/global/flex - Google95.65%Degraded24h 96.98%
- p50
- 1.95s
- p99
- 4.49s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-vertex/global/priority
Measured 5m 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.