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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/eu | Healthy | 99.86%◆ (best) | 99.87% | 99.89%◆ (best) | 99.89%◆ (best) | 474ms | 3.90s | 80 tps | 1.0M | $0.100 / $0.400 |
Googlegoogle-vertex | Healthy | 99.83% | 99.78% | 99.77% | 99.77% | 522ms | 3.77s | 73 tps | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio | Healthy | 99.25% | 99.38% | 99.44% | 99.44% | 489ms | 12.2s | 113 tps◆ (best) | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.25% | 99.38% | 99.44% | 99.44% | 742ms | 4.18s | 64 tps | 1.0M | $0.050 / $0.200◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.25% | 99.38% | 99.44% | 99.44% | 284ms◆ (best) | 313ms◆ (best) | 18 tps | 1.0M | $0.180 / $0.720 |
- Google99.86%◆ (best)Healthy24h 99.87%
- 7d
- 99.89%◆ (best)
- 30d
- 99.89%◆ (best)
- p50
- 474ms
- p99
- 3.90s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex/eu - Google99.83%Healthy24h 99.78%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 522ms
- p99
- 3.77s
- Throughput
- 73 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex - Google AI Studio99.25%Healthy24h 99.38%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 489ms
- p99
- 12.2s
- Throughput
- 113 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-ai-studio - Google AI Studio99.25%Healthy24h 99.38%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 742ms
- p99
- 4.18s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.200◆ (best)
google-ai-studio/flex - Google AI Studio99.25%Healthy24h 99.38%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 284ms◆ (best)
- p99
- 313ms◆ (best)
- Throughput
- 18 tps
- Context
- 1.0M
- $/Mtok
- $0.180 / $0.720
google-ai-studio/priority
Measured 3m 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.