Gemini 3.5 Flash: 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/us | Healthy | 100%◆ (best) | 100% | 99.34% | 96.93% | 2.22s | 5.24s | 190 tps | 1.0M | $1.65 / $9.90 |
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 99.84% | 99.76% | 99.72% | 1.68s | 15.4s | 200 tps◆ (best) | 1.0M | $1.50 / $9.00 |
Googlegoogle-vertex/global | Healthy | 99.77% | 99.16% | 99.20% | 99.27% | 1.86s | 11.5s | 98 tps | 1.0M | $1.50 / $9.00 |
Googlegoogle-vertex/global/flex | No data | — | 99.88% | 99.93% | 87.32% | 13.1s | 240s | 14 tps | 1.0M | $0.750 / $4.50◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.89% | 99.96%◆ (best) | 99.98%◆ (best) | 1.62s | 6.48s | 124 tps | 1.0M | $2.70 / $16.20 |
Google AI Studiogoogle-ai-studio/flex | No data | — | 99.95% | 99.92% | 99.88% | 1.16s◆ (best) | 15.1s | 115 tps | 1.0M | $0.750 / $4.50◆ (best) |
Google AI Studiogoogle-ai-studio/priority | No data | — | 99.94% | 99.93% | 99.95% | 1.18s | 5.24s◆ (best) | 70 tps | 1.0M | $2.70 / $16.20 |
- Google100%◆ (best)Healthy24h 100%
- 7d
- 99.34%
- 30d
- 96.93%
- p50
- 2.22s
- p99
- 5.24s
- Throughput
- 190 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $9.90
google-vertex/us - Google AI Studio100%◆ (best)Healthy24h 99.84%
- 7d
- 99.76%
- 30d
- 99.72%
- p50
- 1.68s
- p99
- 15.4s
- Throughput
- 200 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.50 / $9.00
google-ai-studio - Google99.77%Healthy24h 99.16%
- 7d
- 99.20%
- 30d
- 99.27%
- p50
- 1.86s
- p99
- 11.5s
- Throughput
- 98 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $9.00
google-vertex/global - No data24h 99.88%
- 7d
- 99.93%
- 30d
- 87.32%
- p50
- 13.1s
- p99
- 240s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $4.50◆ (best)
google-vertex/global/flex - No data24h 99.89%
- 7d
- 99.96%◆ (best)
- 30d
- 99.98%◆ (best)
- p50
- 1.62s
- p99
- 6.48s
- Throughput
- 124 tps
- Context
- 1.0M
- $/Mtok
- $2.70 / $16.20
google-vertex/global/priority - No data24h 99.95%
- 7d
- 99.92%
- 30d
- 99.88%
- p50
- 1.16s◆ (best)
- p99
- 15.1s
- Throughput
- 115 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $4.50◆ (best)
google-ai-studio/flex - No data24h 99.94%
- 7d
- 99.93%
- 30d
- 99.95%
- p50
- 1.18s
- p99
- 5.24s◆ (best)
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $2.70 / $16.20
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.