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 | 99.85%◆ (best) | 99.85% | 99.89%◆ (best) | 99.89%◆ (best) | 422ms | 3.43s | 118 tps | 1.0M | $0.100 / $0.400 |
Googlegoogle-vertex | Healthy | 99.79% | 99.76% | 99.77% | 99.77% | 496ms | 3.17s | 94 tps | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio | Healthy | 99.10% | 99.39% | 99.44% | 99.44% | 463ms | 10.9s | 119 tps◆ (best) | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.10% | 99.39% | 99.44% | 99.44% | 722ms | 5.00s | 67 tps | 1.0M | $0.050 / $0.200◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.10% | 99.39% | 99.44% | 99.44% | 314ms◆ (best) | 331ms◆ (best) | 16 tps | 1.0M | $0.180 / $0.720 |
- Google99.85%◆ (best)Healthy24h 99.85%
- 7d
- 99.89%◆ (best)
- 30d
- 99.89%◆ (best)
- p50
- 422ms
- p99
- 3.43s
- Throughput
- 118 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex/eu - Google99.79%Healthy24h 99.76%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 496ms
- p99
- 3.17s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex - Google AI Studio99.10%Healthy24h 99.39%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 463ms
- p99
- 10.9s
- Throughput
- 119 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-ai-studio - Google AI Studio99.10%Healthy24h 99.39%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 722ms
- p99
- 5.00s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.200◆ (best)
google-ai-studio/flex - Google AI Studio99.10%Healthy24h 99.39%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 314ms◆ (best)
- p99
- 331ms◆ (best)
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $0.180 / $0.720
google-ai-studio/priority
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.