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) | 628ms | 2.15s | 124 tps | 1.0M | $0.050 / $0.200◆ (best) |
Googlegoogle-vertex/eu | Healthy | 99.99% | 99.98% | 99.96% | 99.92% | 478ms◆ (best) | 3.55s | 150 tps | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio | Healthy | 99.61% | 99.43% | 99.30% | 99.16% | 555ms | 7.50s | 151 tps◆ (best) | 1.0M | $0.100 / $0.400 |
Googlegoogle-vertex | Healthy | 99.52% | 98.77% | 98.85% | 97.39% | 1.06s | 4.58s | 101 tps | 1.0M | $0.100 / $0.400 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 100% | 99.75% | 99.92% | 732ms | 1.77s◆ (best) | 66 tps | 1.0M | $0.180 / $0.720 |
- Google AI Studio100%◆ (best)Healthy24h 100%
- 7d
- 99.99%◆ (best)
- 30d
- 99.98%◆ (best)
- p50
- 628ms
- p99
- 2.15s
- Throughput
- 124 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.200◆ (best)
google-ai-studio/flex - Google99.99%Healthy24h 99.98%
- 7d
- 99.96%
- 30d
- 99.92%
- p50
- 478ms◆ (best)
- p99
- 3.55s
- Throughput
- 150 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex/eu - Google AI Studio99.61%Healthy24h 99.43%
- 7d
- 99.30%
- 30d
- 99.16%
- p50
- 555ms
- p99
- 7.50s
- Throughput
- 151 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-ai-studio - Google99.52%Healthy24h 98.77%
- 7d
- 98.85%
- 30d
- 97.39%
- p50
- 1.06s
- p99
- 4.58s
- Throughput
- 101 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.400
google-vertex - No data24h 100%
- 7d
- 99.75%
- 30d
- 99.92%
- p50
- 732ms
- p99
- 1.77s◆ (best)
- Throughput
- 66 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.
Throughput
Median tokens per second.