Gemini 3.1 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/global/flex | Healthy | 100%◆ (best) | 99.95% | 99.95% | 56.77% | 16.1s | 32.8s | 8.0 tps | 1.0M | $0.125 / $0.750◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 100%◆ (best) | 100% | 99.99%◆ (best) | 99.96% | 1.11s | 2.00s | 108 tps | 1.0M | $0.450 / $2.70 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.99% | 99.93% | 99.95% | 488ms◆ (best) | 1.78s | 104 tps | 1.0M | $0.125 / $0.750◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.96% | 99.94% | 99.93% | 890ms | 2.89s | 166 tps | 1.0M | $0.450 / $2.70 |
Googlegoogle-vertex/global | Healthy | 99.98% | 99.96% | 99.50% | 99.71% | 908ms | 4.14s | 111 tps | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio | Healthy | 99.97% | 99.93% | 99.82% | 99.81% | 698ms | 2.74s | 116 tps | 1.0M | $0.250 / $1.50 |
Googlegoogle-vertex/eu | No data | — | 100% | 99.98% | 99.97%◆ (best) | — | — | — | 1.0M | $0.275 / $1.65 |
Googlegoogle-vertex/us | No data | — | 100% | 99.99% | 99.96% | 685ms | 1.65s◆ (best) | 195 tps◆ (best) | 1.0M | $0.275 / $1.65 |
- Google100%◆ (best)Healthy24h 99.95%
- 7d
- 99.95%
- 30d
- 56.77%
- p50
- 16.1s
- p99
- 32.8s
- Throughput
- 8.0 tps
- Context
- 1.0M
- $/Mtok
- $0.125 / $0.750◆ (best)
google-vertex/global/flex - Google100%◆ (best)Healthy24h 100%
- 7d
- 99.99%◆ (best)
- 30d
- 99.96%
- p50
- 1.11s
- p99
- 2.00s
- Throughput
- 108 tps
- Context
- 1.0M
- $/Mtok
- $0.450 / $2.70
google-vertex/global/priority - Google AI Studio100%◆ (best)Healthy24h 99.99%
- 7d
- 99.93%
- 30d
- 99.95%
- p50
- 488ms◆ (best)
- p99
- 1.78s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $0.125 / $0.750◆ (best)
google-ai-studio/flex - Google AI Studio100%◆ (best)Healthy24h 99.96%
- 7d
- 99.94%
- 30d
- 99.93%
- p50
- 890ms
- p99
- 2.89s
- Throughput
- 166 tps
- Context
- 1.0M
- $/Mtok
- $0.450 / $2.70
google-ai-studio/priority - Google99.98%Healthy24h 99.96%
- 7d
- 99.50%
- 30d
- 99.71%
- p50
- 908ms
- p99
- 4.14s
- Throughput
- 111 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-vertex/global - Google AI Studio99.97%Healthy24h 99.93%
- 7d
- 99.82%
- 30d
- 99.81%
- p50
- 698ms
- p99
- 2.74s
- Throughput
- 116 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-ai-studio - No data24h 100%
- 7d
- 99.98%
- 30d
- 99.97%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.275 / $1.65
google-vertex/eu - No data24h 100%
- 7d
- 99.99%
- 30d
- 99.96%
- p50
- 685ms
- p99
- 1.65s◆ (best)
- Throughput
- 195 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.275 / $1.65
google-vertex/us
Measured 4m 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.