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 | 99.73%◆ (best) | 99.54% | 99.52% | 99.58% | 3.26s | 13.2s | 110 tps | 1.0M | $2.00 / $12.00 |
Googlegoogle-vertex/global | Healthy | 99.42% | 99.42% | 98.98% | 98.16% | 3.24s | 28.8s | 111 tps◆ (best) | 1.0M | $2.00 / $12.00 |
Googlegoogle-vertex/global/flex | No data | — | 94.80% | 99.24% | 43.67% | 97.5s | 143s | 14 tps | 1.0M | $1.00 / $6.00◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.79% | 99.62% | 99.87%◆ (best) | 2.76s | 5.31s | 72 tps | 1.0M | $3.60 / $21.60 |
Google AI Studiogoogle-ai-studio/flex | No data | — | 99.96% | 99.73%◆ (best) | 99.81% | 2.71s | 4.01s | 89 tps | 1.0M | $1.00 / $6.00◆ (best) |
Google AI Studiogoogle-ai-studio/priority | No data | — | 97.71% | 99.35% | 99.55% | 2.23s◆ (best) | 3.63s◆ (best) | 91 tps | 1.0M | $3.60 / $21.60 |
- Google AI Studio99.73%◆ (best)Healthy24h 99.54%
- 7d
- 99.52%
- 30d
- 99.58%
- p50
- 3.26s
- p99
- 13.2s
- Throughput
- 110 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $12.00
google-ai-studio - Google99.42%Healthy24h 99.42%
- 7d
- 98.98%
- 30d
- 98.16%
- p50
- 3.24s
- p99
- 28.8s
- Throughput
- 111 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.00 / $12.00
google-vertex/global - No data24h 94.80%
- 7d
- 99.24%
- 30d
- 43.67%
- p50
- 97.5s
- p99
- 143s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $6.00◆ (best)
google-vertex/global/flex - No data24h 99.79%
- 7d
- 99.62%
- 30d
- 99.87%◆ (best)
- p50
- 2.76s
- p99
- 5.31s
- Throughput
- 72 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
- 2.71s
- p99
- 4.01s
- Throughput
- 89 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
- 2.23s◆ (best)
- p99
- 3.63s◆ (best)
- Throughput
- 91 tps
- Context
- 1.0M
- $/Mtok
- $3.60 / $21.60
google-ai-studio/priority
Measured 4m 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.