← 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.97% | 99.99%◆ (best) | 99.91% | 4.07s | 7.04s | 97 tps | 1.0M | $0.625 / $5.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 99.42% | 97.49% | 98.32% | 98.18% | 3.76s | 14.5s | 68 tps | 1.0M | $1.25 / $10.00 |
Google AI Studiogoogle-ai-studio | Healthy | 98.74% | 96.10% | 98.13% | 95.36% | 3.29s | 7.20s | 87 tps | 1.0M | $1.25 / $10.00 |
Googlegoogle-vertex/eu | Degraded | 93.55% | 89.94% | 93.39% | 81.31% | 4.38s | 11.3s | 63 tps | 1.0M | $1.25 / $10.00 |
Googlegoogle-vertex/global/flex | No data | — | — | — | — | — | — | — | 1.0M | $0.625 / $5.00◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.70% | 99.79% | 99.85% | 2.38s | 3.89s | 98 tps◆ (best) | 1.0M | $2.25 / $18.00 |
Googlegoogle-vertex/us | No data | — | 97.58% | 94.27% | 95.98% | 5.24s | 38.9s | 67 tps | 1.0M | $1.25 / $10.00 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 100% | — | 100%◆ (best) | 1.40s◆ (best) | 2.27s◆ (best) | 46 tps | 1.0M | $2.25 / $18.00 |
- Google AI Studio100%◆ (best)Healthy24h 99.97%
- 7d
- 99.99%◆ (best)
- 30d
- 99.91%
- p50
- 4.07s
- p99
- 7.04s
- Throughput
- 97 tps
- Context
- 1.0M
- $/Mtok
- $0.625 / $5.00◆ (best)
google-ai-studio/flex - Google99.42%Healthy24h 97.49%
- 7d
- 98.32%
- 30d
- 98.18%
- p50
- 3.76s
- p99
- 14.5s
- Throughput
- 68 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/global - Google AI Studio98.74%Healthy24h 96.10%
- 7d
- 98.13%
- 30d
- 95.36%
- p50
- 3.29s
- p99
- 7.20s
- Throughput
- 87 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-ai-studio - Google93.55%Degraded24h 89.94%
- 7d
- 93.39%
- 30d
- 81.31%
- p50
- 4.38s
- p99
- 11.3s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/eu - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.625 / $5.00◆ (best)
google-vertex/global/flex - No data24h 99.70%
- 7d
- 99.79%
- 30d
- 99.85%
- p50
- 2.38s
- p99
- 3.89s
- Throughput
- 98 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.25 / $18.00
google-vertex/global/priority - No data24h 97.58%
- 7d
- 94.27%
- 30d
- 95.98%
- p50
- 5.24s
- p99
- 38.9s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/us - No data24h 100%
- 7d
- —
- 30d
- 100%◆ (best)
- p50
- 1.40s◆ (best)
- p99
- 2.27s◆ (best)
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $2.25 / $18.00
google-ai-studio/priority
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.
Throughput
Median tokens per second.