Gemini 3.5 Flash
google/gemini-3.5-flash
Compare with Gemini 3.6 Flash, Gemini 3.7 Flash, Gemini 3.5 Flash Lite
CompareGemini 3.5 Flash
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 100% | 99.76% | 1.72s | 18.0s | 159 tps | 1.0M | $1.50 / $9.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100% | 99.76% | 1.59s | 5.12s | 234 tps | 1.0M | $0.750 / $4.50 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100% | 99.76% | 921ms | 921ms | 34 tps | 1.0M | $2.70 / $16.20 |
Googlegoogle-vertex/global | Healthy | 98.97% | 99.30% | 1.62s | 10.6s | 129 tps | 1.0M | $1.50 / $9.00 |
Googlegoogle-vertex/global/flex | Healthy | 98.97% | 99.30% | 12.9s | 14.4s | 4.0 tps | 1.0M | $0.750 / $4.50 |
Googlegoogle-vertex/global/priority | Healthy | 98.97% | 99.30% | 1.39s | 2.92s | 80 tps | 1.0M | $2.70 / $16.20 |
Googlegoogle-vertex/us | No data | — | — | — | — | — | 1.0M | $1.65 / $9.90 |
- Google AI Studio100%Healthy24h 99.76%
- p50
- 1.72s
- p99
- 18.0s
- Throughput
- 159 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $9.00
google-ai-studio - Google AI Studio100%Healthy24h 99.76%
- p50
- 1.59s
- p99
- 5.12s
- Throughput
- 234 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $4.50
google-ai-studio/flex - Google AI Studio100%Healthy24h 99.76%
- p50
- 921ms
- p99
- 921ms
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $2.70 / $16.20
google-ai-studio/priority - Google98.97%Healthy24h 99.30%
- p50
- 1.62s
- p99
- 10.6s
- Throughput
- 129 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $9.00
google-vertex/global - Google98.97%Healthy24h 99.30%
- p50
- 12.9s
- p99
- 14.4s
- Throughput
- 4.0 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $4.50
google-vertex/global/flex - Google98.97%Healthy24h 99.30%
- p50
- 1.39s
- p99
- 2.92s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $2.70 / $16.20
google-vertex/global/priority - Google—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.65 / $9.90
google-vertex/us
Measured 53s 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.