Gemini 2.5 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/flex | Healthy | 100%◆ (best) | 100% | 99.99%◆ (best) | 99.98%◆ (best) | 425ms | 2.12s | 131 tps | 1.0M | $0.050 / $0.200◆ (best) |
Googlegoogle-vertex/eu | Healthy | 99.96% | 99.98% | 99.96% | 99.92% | 443ms | 3.83s | 166 tps | 1.0M | $0.100 / $0.400 |
Googlegoogle-vertex | Healthy | 99.58% | 98.77% | 98.86% | 97.39% | 1.09s | 4.98s | 98 tps | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio | Healthy | 99.31% | 99.43% | 99.30% | 99.16% | 528ms | 8.78s | 179 tps◆ (best) | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 100% | 99.76% | 99.92% | 297ms◆ (best) | 305ms◆ (best) | 149 tps | 1.0M | $0.180 / $0.720 |
- Google AI Studio100%◆ (best)Healthy24h 100%
- 7d
- 99.99%◆ (best)
- 30d
- 99.98%◆ (best)
- p50
- 425ms
- p99
- 2.12s
- Throughput
- 131 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.200◆ (best)
google-ai-studio/flex - Google99.96%Healthy24h 99.98%
- 7d
- 99.96%
- 30d
- 99.92%
- p50
- 443ms
- p99
- 3.83s
- Throughput
- 166 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex/eu - Google99.58%Healthy24h 98.77%
- 7d
- 98.86%
- 30d
- 97.39%
- p50
- 1.09s
- p99
- 4.98s
- Throughput
- 98 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex - Google AI Studio99.31%Healthy24h 99.43%
- 7d
- 99.30%
- 30d
- 99.16%
- p50
- 528ms
- p99
- 8.78s
- Throughput
- 179 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-ai-studio - No data24h 100%
- 7d
- 99.76%
- 30d
- 99.92%
- p50
- 297ms◆ (best)
- p99
- 305ms◆ (best)
- Throughput
- 149 tps
- Context
- 1.0M
- $/Mtok
- $0.180 / $0.720
google-ai-studio/priority
Measured 2m 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.