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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.93%◆ (best) | 99.87% | 99.85%◆ (best) | 99.85%◆ (best) | 564ms | 3.20s | 60 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.93%◆ (best) | 99.87% | 99.85%◆ (best) | 99.85%◆ (best) | 1.61s | 4.17s | 212 tps◆ (best) | 1.0M | $0.150 / $1.25◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.93%◆ (best) | 99.87% | 99.85%◆ (best) | 99.85%◆ (best) | 404ms◆ (best) | 446ms◆ (best) | 92 tps | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/global | Healthy | 99.89% | 99.70% | 99.73% | 99.73% | 652ms | 6.21s | 59 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/global/flex | Healthy | 99.89% | 99.70% | 99.73% | 99.73% | 6.71s | 7.25s | 5.0 tps | 1.0M | $0.150 / $1.25◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 99.89% | 99.70% | 99.73% | 99.73% | 1.22s | 2.98s | 27 tps | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/us | No data | — | — | — | — | 539ms | 557ms | 2.5 tps | 1.0M | $0.330 / $2.75 |
- Google AI Studio99.93%◆ (best)Healthy24h 99.87%
- 7d
- 99.85%◆ (best)
- 30d
- 99.85%◆ (best)
- p50
- 564ms
- p99
- 3.20s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-ai-studio - Google AI Studio99.93%◆ (best)Healthy24h 99.87%
- 7d
- 99.85%◆ (best)
- 30d
- 99.85%◆ (best)
- p50
- 1.61s
- p99
- 4.17s
- Throughput
- 212 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-ai-studio/flex - Google AI Studio99.93%◆ (best)Healthy24h 99.87%
- 7d
- 99.85%◆ (best)
- 30d
- 99.85%◆ (best)
- p50
- 404ms◆ (best)
- p99
- 446ms◆ (best)
- Throughput
- 92 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority - Google99.89%Healthy24h 99.70%
- 7d
- 99.73%
- 30d
- 99.73%
- p50
- 652ms
- p99
- 6.21s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google99.89%Healthy24h 99.70%
- 7d
- 99.73%
- 30d
- 99.73%
- p50
- 6.71s
- p99
- 7.25s
- Throughput
- 5.0 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-vertex/global/flex - Google99.89%Healthy24h 99.70%
- 7d
- 99.73%
- 30d
- 99.73%
- p50
- 1.22s
- p99
- 2.98s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - No data24h —
- 7d
- —
- 30d
- —
- p50
- 539ms
- p99
- 557ms
- Throughput
- 2.5 tps
- Context
- 1.0M
- $/Mtok
- $0.330 / $2.75
google-vertex/us
Measured 53s 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.
Throughput
Median tokens per second.