Gemini 3.1 Pro Preview: 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 | Healthy | 99.79%◆ (best) | 99.54% | 99.52% | 99.58% | 3.07s | 11.6s | 104 tps | 1.0M | $2.00 / $12.00 |
Googlegoogle-vertex/global | Healthy | 99.64% | 99.41% | 98.99% | 98.16% | 3.11s | 31.1s | 105 tps | 1.0M | $2.00 / $12.00 |
Googlegoogle-vertex/global/flex | No data | — | 94.82% | 99.24% | 43.57% | 89.5s | 202s | 11 tps | 1.0M | $1.00 / $6.00◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.74% | 99.62% | 99.87%◆ (best) | 3.80s | 10.8s | 30 tps | 1.0M | $3.60 / $21.60 |
Google AI Studiogoogle-ai-studio/flex | No data | — | 99.96% | 99.73%◆ (best) | 99.81% | 2.80s | 17.9s | 90 tps | 1.0M | $1.00 / $6.00◆ (best) |
Google AI Studiogoogle-ai-studio/priority | No data | — | 97.71% | 99.35% | 99.55% | 2.43s◆ (best) | 2.43s◆ (best) | 154 tps◆ (best) | 1.0M | $3.60 / $21.60 |
- Google AI Studio99.79%◆ (best)Healthy24h 99.54%
- 7d
- 99.52%
- 30d
- 99.58%
- p50
- 3.07s
- p99
- 11.6s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $12.00
google-ai-studio - Google99.64%Healthy24h 99.41%
- 7d
- 98.99%
- 30d
- 98.16%
- p50
- 3.11s
- p99
- 31.1s
- Throughput
- 105 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $12.00
google-vertex/global - No data24h 94.82%
- 7d
- 99.24%
- 30d
- 43.57%
- p50
- 89.5s
- p99
- 202s
- Throughput
- 11 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $6.00◆ (best)
google-vertex/global/flex - No data24h 99.74%
- 7d
- 99.62%
- 30d
- 99.87%◆ (best)
- p50
- 3.80s
- p99
- 10.8s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $3.60 / $21.60
google-vertex/global/priority - No data24h 99.96%
- 7d
- 99.73%◆ (best)
- 30d
- 99.81%
- p50
- 2.80s
- p99
- 17.9s
- Throughput
- 90 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $6.00◆ (best)
google-ai-studio/flex - No data24h 97.71%
- 7d
- 99.35%
- 30d
- 99.55%
- p50
- 2.43s◆ (best)
- p99
- 2.43s◆ (best)
- Throughput
- 154 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $3.60 / $21.60
google-ai-studio/priority
Measured 1m 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.