Gemini 3.6 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/global | Healthy | 99.92%◆ (best) | 99.70% | 99.45% | 99.45% | 1.27s◆ (best) | 4.38s | 150 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/flex | Healthy | 99.92%◆ (best) | 99.70% | 99.45% | 99.45% | 7.74s | 8.75s | 64 tps | 1.0M | $0.375 / $1.88◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 99.92%◆ (best) | 99.70% | 99.45% | 99.45% | 2.05s | 2.49s◆ (best) | 3.0 tps | 1.0M | $1.35 / $6.75 |
Google AI Studiogoogle-ai-studio | Healthy | 99.48% | 99.60% | 99.51% | 99.51% | 1.69s | 12.1s | 111 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.48% | 99.60% | 99.51% | 99.51% | 1.41s | 4.83s | 157 tps◆ (best) | 1.0M | $0.375 / $1.88◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.48% | 99.60% | 99.51% | 99.51% | — | — | — | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/us | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $0.825 / $4.13 |
- Google99.92%◆ (best)Healthy24h 99.70%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 1.27s◆ (best)
- p99
- 4.38s
- Throughput
- 150 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Google99.92%◆ (best)Healthy24h 99.70%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 7.74s
- p99
- 8.75s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-vertex/global/flex - Google99.92%◆ (best)Healthy24h 99.70%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 2.05s
- p99
- 2.49s◆ (best)
- Throughput
- 3.0 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority - Google AI Studio99.48%Healthy24h 99.60%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- 1.69s
- p99
- 12.1s
- Throughput
- 111 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio99.48%Healthy24h 99.60%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- 1.41s
- p99
- 4.83s
- Throughput
- 157 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-ai-studio/flex - Google AI Studio99.48%Healthy24h 99.60%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.825 / $4.13
google-vertex/us
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.