Gemini 3.8 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/flex | Healthy | 100%◆ (best) | 99.81% | 99.89%◆ (best) | 99.68% | 1.81s | 45.6s | 185 tps | 1.0M | $0.375 / $1.88◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.69% | 98.69% | 98.64% | 1.85s | 4.89s◆ (best) | 200 tps◆ (best) | 1.0M | $1.35 / $6.75 |
Google AI Studiogoogle-ai-studio | Healthy | 99.94% | 99.91% | 99.82% | 99.73% | 1.37s◆ (best) | 6.83s | 152 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global | Healthy | 98.12% | 97.42% | 95.85% | 97.43% | 2.37s | 30.8s | 75 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/flex | Down | 52.38% | 75.42% | 82.79% | 87.36% | 14.8s | 228s | 43 tps | 1.0M | $0.375 / $1.88◆ (best) |
Googlegoogle-vertex/global/priority | No data | — | 99.79% | 99.88% | 99.80%◆ (best) | 1.89s | 6.12s | 104 tps | 1.0M | $1.35 / $6.75 |
- Google AI Studio100%◆ (best)Healthy24h 99.81%
- 7d
- 99.89%◆ (best)
- 30d
- 99.68%
- p50
- 1.81s
- p99
- 45.6s
- Throughput
- 185 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-ai-studio/flex - Google AI Studio100%◆ (best)Healthy24h 99.69%
- 7d
- 98.69%
- 30d
- 98.64%
- p50
- 1.85s
- p99
- 4.89s◆ (best)
- Throughput
- 200 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - Google AI Studio99.94%Healthy24h 99.91%
- 7d
- 99.82%
- 30d
- 99.73%
- p50
- 1.37s◆ (best)
- p99
- 6.83s
- Throughput
- 152 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google98.12%Healthy24h 97.42%
- 7d
- 95.85%
- 30d
- 97.43%
- p50
- 2.37s
- p99
- 30.8s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Google52.38%Down24h 75.42%
- 7d
- 82.79%
- 30d
- 87.36%
- p50
- 14.8s
- p99
- 228s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88◆ (best)
google-vertex/global/flex - No data24h 99.79%
- 7d
- 99.88%
- 30d
- 99.80%◆ (best)
- p50
- 1.89s
- p99
- 6.12s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority
Measured 3m 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.