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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 99.44% | 99.42% | 99.42% | 1.91s | 32.1s | 161 tps | 1.0M | $1.50 / $9.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.44% | 99.42% | 99.42% | 763ms◆ (best) | 16.7s | 67 tps | 1.0M | $0.750 / $4.50◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.44% | 99.42% | 99.42% | 1.52s | 2.50s | 200 tps◆ (best) | 1.0M | $2.70 / $16.20 |
Googlegoogle-vertex/global | Healthy | 99.77% | 99.67% | 99.67%◆ (best) | 99.67%◆ (best) | 1.61s | 7.75s | 129 tps | 1.0M | $1.50 / $9.00 |
Googlegoogle-vertex/global/flex | Healthy | 99.77% | 99.67% | 99.67%◆ (best) | 99.67%◆ (best) | — | — | — | 1.0M | $0.750 / $4.50◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 99.77% | 99.67% | 99.67%◆ (best) | 99.67%◆ (best) | 1.07s | 2.27s◆ (best) | 98 tps | 1.0M | $2.70 / $16.20 |
Googlegoogle-vertex/us | No data | — | — | — | — | — | — | — | 1.0M | $1.65 / $9.90 |
- Google AI Studio100%◆ (best)Healthy24h 99.44%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 1.91s
- p99
- 32.1s
- Throughput
- 161 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $9.00
google-ai-studio - Google AI Studio100%◆ (best)Healthy24h 99.44%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 763ms◆ (best)
- p99
- 16.7s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $4.50◆ (best)
google-ai-studio/flex - Google AI Studio100%◆ (best)Healthy24h 99.44%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 1.52s
- p99
- 2.50s
- Throughput
- 200 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.70 / $16.20
google-ai-studio/priority - Google99.77%Healthy24h 99.67%
- 7d
- 99.67%◆ (best)
- 30d
- 99.67%◆ (best)
- p50
- 1.61s
- p99
- 7.75s
- Throughput
- 129 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $9.00
google-vertex/global - Google99.77%Healthy24h 99.67%
- 7d
- 99.67%◆ (best)
- 30d
- 99.67%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.750 / $4.50◆ (best)
google-vertex/global/flex - Google99.77%Healthy24h 99.67%
- 7d
- 99.67%◆ (best)
- 30d
- 99.67%◆ (best)
- p50
- 1.07s
- p99
- 2.27s◆ (best)
- Throughput
- 98 tps
- Context
- 1.0M
- $/Mtok
- $2.70 / $16.20
google-vertex/global/priority - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.65 / $9.90
google-vertex/us
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, averaged over the hour.
Throughput
Median tokens per second.