Gemini 3.5 Flash Lite: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/eu | Healthy | 100%◆ (best) | 100% | 99.97% | 99.98% | 579ms | 2.73s | 162 tps | 1.0M | $0.330 / $2.75 |
Googlegoogle-vertex/global/flex | Healthy | 100%◆ (best) | 100% | 99.98% | 99.08% | 7.02s | 8.70s | 22 tps | 1.0M | $0.150 / $1.25◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 100%◆ (best) | 99.94% | 99.97% | 99.97% | 1.10s | 2.15s | 91 tps | 1.0M | $0.540 / $4.50 |
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 99.94% | 99.91% | 99.94% | 637ms | 3.35s | 144 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.98% | 99.89% | 99.95% | 773ms | 5.10s | 195 tps◆ (best) | 1.0M | $0.150 / $1.25◆ (best) |
Googlegoogle-vertex/global | Healthy | 99.98% | 99.95% | 99.91% | 99.88% | 668ms | 3.70s | 117 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/us | No data | — | 99.84% | 99.99%◆ (best) | 99.99%◆ (best) | 1.49s | 2.72s | 182 tps | 1.0M | $0.330 / $2.75 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 99.95% | 99.95% | 99.94% | 508ms◆ (best) | 1.95s◆ (best) | 85 tps | 1.0M | $0.540 / $4.50 |
- Google100%◆ (best)Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.98%
- p50
- 579ms
- p99
- 2.73s
- Throughput
- 162 tps
- Context
- 1.0M
- $/Mtok
- $0.330 / $2.75
google-vertex/eu - Google100%◆ (best)Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.08%
- p50
- 7.02s
- p99
- 8.70s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-vertex/global/flex - Google100%◆ (best)Healthy24h 99.94%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.10s
- p99
- 2.15s
- Throughput
- 91 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - Google AI Studio100%◆ (best)Healthy24h 99.94%
- 7d
- 99.91%
- 30d
- 99.94%
- p50
- 637ms
- p99
- 3.35s
- Throughput
- 144 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-ai-studio - Google AI Studio100%◆ (best)Healthy24h 99.98%
- 7d
- 99.89%
- 30d
- 99.95%
- p50
- 773ms
- p99
- 5.10s
- Throughput
- 195 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-ai-studio/flex - Google99.98%Healthy24h 99.95%
- 7d
- 99.91%
- 30d
- 99.88%
- p50
- 668ms
- p99
- 3.70s
- Throughput
- 117 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - No data24h 99.84%
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 1.49s
- p99
- 2.72s
- Throughput
- 182 tps
- Context
- 1.0M
- $/Mtok
- $0.330 / $2.75
google-vertex/us - No data24h 99.95%
- 7d
- 99.95%
- 30d
- 99.94%
- p50
- 508ms◆ (best)
- p99
- 1.95s◆ (best)
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.