← Gemini 2.5 Pro Preview 06-05
Gemini 2.5 Pro Preview 06-05: 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/global | Healthy | 99.86%◆ (best) | 99.21% | 99.25%◆ (best) | 99.25%◆ (best) | 2.56s | 7.74s | 74 tps | 1.0M | $1.25 / $10.00 |
Googlegoogle-vertex/global/flex | Healthy | 99.86%◆ (best) | 99.21% | 99.25%◆ (best) | 99.25%◆ (best) | — | — | — | 1.0M | $0.625 / $5.00◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 99.86%◆ (best) | 99.21% | 99.25%◆ (best) | 99.25%◆ (best) | 2.23s◆ (best) | 2.85s◆ (best) | 96 tps◆ (best) | 1.0M | $2.25 / $18.00 |
Google AI Studiogoogle-ai-studio | Healthy | 98.48% | 82.83% | 94.53% | 94.53% | 4.14s | 23.1s | 66 tps | 1.0M | $1.25 / $10.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 98.48% | 82.83% | 94.53% | 94.53% | 4.66s | 6.51s | 22 tps | 1.0M | $0.625 / $5.00◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 98.48% | 82.83% | 94.53% | 94.53% | — | — | — | 1.0M | $2.25 / $18.00 |
Googlegoogle-vertex/eu | No data | — | 92.01% | 86.54% | 86.54% | 20.0s | 26.7s | 86 tps | 1.0M | $1.25 / $10.00 |
Googlegoogle-vertex/us | Degraded | — | 93.48% | 74.28% | 74.28% | 3.60s | 23.4s | 63 tps | 1.0M | $1.25 / $10.00 |
- Google99.86%◆ (best)Healthy24h 99.21%
- 7d
- 99.25%◆ (best)
- 30d
- 99.25%◆ (best)
- p50
- 2.56s
- p99
- 7.74s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/global - Google99.86%◆ (best)Healthy24h 99.21%
- 7d
- 99.25%◆ (best)
- 30d
- 99.25%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.625 / $5.00◆ (best)
google-vertex/global/flex - Google99.86%◆ (best)Healthy24h 99.21%
- 7d
- 99.25%◆ (best)
- 30d
- 99.25%◆ (best)
- p50
- 2.23s◆ (best)
- p99
- 2.85s◆ (best)
- Throughput
- 96 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.25 / $18.00
google-vertex/global/priority - Google AI Studio98.48%Healthy24h 82.83%
- 7d
- 94.53%
- 30d
- 94.53%
- p50
- 4.14s
- p99
- 23.1s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-ai-studio - Google AI Studio98.48%Healthy24h 82.83%
- 7d
- 94.53%
- 30d
- 94.53%
- p50
- 4.66s
- p99
- 6.51s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $0.625 / $5.00◆ (best)
google-ai-studio/flex - Google AI Studio98.48%Healthy24h 82.83%
- 7d
- 94.53%
- 30d
- 94.53%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.25 / $18.00
google-ai-studio/priority - No data24h 92.01%
- 7d
- 86.54%
- 30d
- 86.54%
- p50
- 20.0s
- p99
- 26.7s
- Throughput
- 86 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/eu - Degraded24h 93.48%
- 7d
- 74.28%
- 30d
- 74.28%
- p50
- 3.60s
- p99
- 23.4s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/us
Measured 2m 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.