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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 99.84% | 99.86% | 99.86% | 1.16s | 4.88s | 78 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.66% | 99.90% | 99.91% | 2.55s | 11.7s | 148 tps◆ (best) | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global | Healthy | 99.77% | 99.92% | 99.90% | 99.61% | 1.34s | 5.77s | 120 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/flex | No data | — | 99.78% | 99.36% | 93.49% | 7.72s | 8.69s | 75 tps | 1.0M | $0.375 / $1.88◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.90% | 99.85% | 99.69% | 1.14s◆ (best) | 1.96s◆ (best) | 90 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/us | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.23s | 3.71s | 58 tps | 1.0M | $0.825 / $4.13 |
Google AI Studiogoogle-ai-studio/flex | No data | — | 99.79% | 99.95% | 99.91% | 1.23s | 4.45s | 143 tps | 1.0M | $0.375 / $1.88◆ (best) |
- Google AI Studio100%◆ (best)Healthy24h 99.84%
- 7d
- 99.86%
- 30d
- 99.86%
- p50
- 1.16s
- p99
- 4.88s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio100%◆ (best)Healthy24h 99.66%
- 7d
- 99.90%
- 30d
- 99.91%
- p50
- 2.55s
- p99
- 11.7s
- Throughput
- 148 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google99.77%Healthy24h 99.92%
- 7d
- 99.90%
- 30d
- 99.61%
- p50
- 1.34s
- p99
- 5.77s
- Throughput
- 120 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - No data24h 99.78%
- 7d
- 99.36%
- 30d
- 93.49%
- p50
- 7.72s
- p99
- 8.69s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-vertex/global/flex - No data24h 99.90%
- 7d
- 99.85%
- 30d
- 99.69%
- p50
- 1.14s◆ (best)
- p99
- 1.96s◆ (best)
- Throughput
- 90 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.23s
- p99
- 3.71s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.825 / $4.13
google-vertex/us - No data24h 99.79%
- 7d
- 99.95%
- 30d
- 99.91%
- p50
- 1.23s
- p99
- 4.45s
- Throughput
- 143 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-ai-studio/flex
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.