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 | 99.98% | 99.96% | 634ms | 15.7s | 77 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.98% | 99.96% | 2.43s | 5.63s | 3.0 tps | 1.0M | $0.150 / $1.25 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.98% | 99.96% | 447ms | 818ms | 60 tps | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/global | Healthy | 99.64% | 99.50% | 754ms | 6.55s | 80 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/global/priority | Healthy | 99.64% | 99.50% | 1.28s | 3.41s | 41 tps | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/eu | Healthy | 98.46% | 98.05% | 652ms | 5.17s | 79 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex | Degraded | 92.38% | 92.75% | 1.13s | 23.5s | 130 tps | 1.0M | $0.300 / $2.50 |
- Google AI Studio99.98%Healthy24h 99.96%
- p50
- 634ms
- p99
- 15.7s
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-ai-studio - Google AI Studio99.98%Healthy24h 99.96%
- p50
- 2.43s
- p99
- 5.63s
- Throughput
- 3.0 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25
google-ai-studio/flex - Google AI Studio99.98%Healthy24h 99.96%
- p50
- 447ms
- p99
- 818ms
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority - Google99.64%Healthy24h 99.50%
- p50
- 754ms
- p99
- 6.55s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google99.64%Healthy24h 99.50%
- p50
- 1.28s
- p99
- 3.41s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - Google98.46%Healthy24h 98.05%
- p50
- 652ms
- p99
- 5.17s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/eu - Google92.38%Degraded24h 92.75%
- p50
- 1.13s
- p99
- 23.5s
- Throughput
- 130 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex
Measured 3m 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, averaged over the hour.
Throughput
Median tokens per second.