Gemini 2.5 Flash
google/gemini-2.5-flash
Compare with Gemini 2.5 Flash Lite, Gemini 2.5 Flash (batch), Gemini 2.5 Pro
CompareGemini 2.5 Flash
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.93% | 99.96% | 635ms | 8.07s | 75 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.93% | 99.96% | 2.53s | 7.72s | 3.0 tps | 1.0M | $0.150 / $1.25 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.93% | 99.96% | — | — | — | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/global | Healthy | 99.44% | 99.50% | 741ms | 7.94s | 76 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/global/priority | Healthy | 99.44% | 99.50% | 1.29s | 2.19s | 40 tps | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/eu | Healthy | 98.46% | 97.95% | 685ms | 10.9s | 77 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex | Degraded | 91.35% | 92.75% | 1.17s | 11.5s | 127 tps | 1.0M | $0.300 / $2.50 |
- Google AI Studio99.93%Healthy24h 99.96%
- p50
- 635ms
- p99
- 8.07s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-ai-studio - Google AI Studio99.93%Healthy24h 99.96%
- p50
- 2.53s
- p99
- 7.72s
- Throughput
- 3.0 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25
google-ai-studio/flex - Google AI Studio99.93%Healthy24h 99.96%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority - Google99.44%Healthy24h 99.50%
- p50
- 741ms
- p99
- 7.94s
- Throughput
- 76 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google99.44%Healthy24h 99.50%
- p50
- 1.29s
- p99
- 2.19s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - Google98.46%Healthy24h 97.95%
- p50
- 685ms
- p99
- 10.9s
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/eu - Google91.35%Degraded24h 92.75%
- p50
- 1.17s
- p99
- 11.5s
- Throughput
- 127 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.