← Gemini 2.5 Pro Preview 05-06
Gemini 2.5 Pro Preview 05-06: 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 | 99.59%◆ (best) | 99.14% | 99.24%◆ (best) | 99.24%◆ (best) | 2.70s | 9.55s | 75 tps | 1.0M | $1.25 / $10.00 |
Googlegoogle-vertex/global/flex | Healthy | 99.59%◆ (best) | 99.14% | 99.24%◆ (best) | 99.24%◆ (best) | — | — | — | 1.0M | $0.625 / $5.00◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 99.59%◆ (best) | 99.14% | 99.24%◆ (best) | 99.24%◆ (best) | 2.31s◆ (best) | 3.81s◆ (best) | 113 tps◆ (best) | 1.0M | $2.25 / $18.00 |
Google AI Studiogoogle-ai-studio | Healthy | 95.74% | 82.89% | 94.54% | 94.54% | 4.04s | 24.9s | 69 tps | 1.0M | $1.25 / $10.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 95.74% | 82.89% | 94.54% | 94.54% | 4.51s | 7.11s | 29 tps | 1.0M | $0.625 / $5.00◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 95.74% | 82.89% | 94.54% | 94.54% | — | — | — | 1.0M | $2.25 / $18.00 |
Googlegoogle-vertex/us | Healthy | 95.61% | 93.35% | 73.97% | 73.97% | 2.69s | 13.6s | 65 tps | 1.0M | $1.25 / $10.00 |
Googlegoogle-vertex/eu | No data | — | 94.09% | 86.81% | 86.81% | 17.4s | 27.8s | 89 tps | 1.0M | $1.25 / $10.00 |
- Google99.59%◆ (best)Healthy24h 99.14%
- 7d
- 99.24%◆ (best)
- 30d
- 99.24%◆ (best)
- p50
- 2.70s
- p99
- 9.55s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/global - Google99.59%◆ (best)Healthy24h 99.14%
- 7d
- 99.24%◆ (best)
- 30d
- 99.24%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.625 / $5.00◆ (best)
google-vertex/global/flex - Google99.59%◆ (best)Healthy24h 99.14%
- 7d
- 99.24%◆ (best)
- 30d
- 99.24%◆ (best)
- p50
- 2.31s◆ (best)
- p99
- 3.81s◆ (best)
- Throughput
- 113 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.25 / $18.00
google-vertex/global/priority - Google AI Studio95.74%Healthy24h 82.89%
- 7d
- 94.54%
- 30d
- 94.54%
- p50
- 4.04s
- p99
- 24.9s
- Throughput
- 69 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-ai-studio - Google AI Studio95.74%Healthy24h 82.89%
- 7d
- 94.54%
- 30d
- 94.54%
- p50
- 4.51s
- p99
- 7.11s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.625 / $5.00◆ (best)
google-ai-studio/flex - Google AI Studio95.74%Healthy24h 82.89%
- 7d
- 94.54%
- 30d
- 94.54%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.25 / $18.00
google-ai-studio/priority - Google95.61%Healthy24h 93.35%
- 7d
- 73.97%
- 30d
- 73.97%
- p50
- 2.69s
- p99
- 13.6s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/us - No data24h 94.09%
- 7d
- 86.81%
- 30d
- 86.81%
- p50
- 17.4s
- p99
- 27.8s
- Throughput
- 89 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $10.00
google-vertex/eu
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.