Gemini 3.6 Flash
google/gemini-3.6-flash
Compare with Gemini 3.5 Flash, Gemini 3.7 Flash, Gemini 3.5 Flash Lite
CompareGemini 3.6 Flash
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.65% | 98.50% | 1.63s | 13.8s | 125 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.65% | 98.50% | 1.80s | 22.6s | 154 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.65% | 98.50% | 800ms | 980ms | 61 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global | Healthy | 97.31% | 98.78% | 1.88s | 15.1s | 80 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/flex | Healthy | 97.31% | 98.78% | 7.64s | 38.3s | 103 tps | 1.0M | $0.375 / $1.88 |
Googlegoogle-vertex/global/priority | Healthy | 97.31% | 98.78% | — | — | — | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/us | No data | — | 100% | — | — | — | 1.0M | $0.825 / $4.13 |
- Google AI Studio99.65%Healthy24h 98.50%
- p50
- 1.63s
- p99
- 13.8s
- Throughput
- 125 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio99.65%Healthy24h 98.50%
- p50
- 1.80s
- p99
- 22.6s
- Throughput
- 154 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - Google AI Studio99.65%Healthy24h 98.50%
- p50
- 800ms
- p99
- 980ms
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google97.31%Healthy24h 98.78%
- p50
- 1.88s
- p99
- 15.1s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Google97.31%Healthy24h 98.78%
- p50
- 7.64s
- p99
- 38.3s
- Throughput
- 103 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global/flex - Google97.31%Healthy24h 98.78%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority - Google—No data24h 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.825 / $4.13
google-vertex/us
Measured 51s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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.