Gemini 3 Flash Preview: 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/flex | Healthy | 100%◆ (best) | 99.48% | 99.64% | 54.88% | 13.9s | 165s | 63 tps | 1.0M | $0.250 / $1.50◆ (best) |
Googlegoogle-vertex/global/priority | Healthy | 100%◆ (best) | 99.62% | 99.85% | 99.84% | 1.08s◆ (best) | 9.42s | 98 tps◆ (best) | 1.0M | $0.900 / $5.40 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.99% | 99.95%◆ (best) | 99.93%◆ (best) | 2.30s | 39.9s | 69 tps | 1.0M | $0.250 / $1.50◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.92% | 99.82% | 99.86% | 1.13s | 4.44s◆ (best) | 81 tps | 1.0M | $0.900 / $5.40 |
Google AI Studiogoogle-ai-studio | Healthy | 99.99% | 99.94% | 99.89% | 99.90% | 1.38s | 10.1s | 76 tps | 1.0M | $0.500 / $3.00 |
Googlegoogle-vertex/global | Healthy | 99.55% | 99.59% | 99.49% | 98.46% | 1.25s | 9.99s | 94 tps | 1.0M | $0.500 / $3.00 |
- Google100%◆ (best)Healthy24h 99.48%
- 7d
- 99.64%
- 30d
- 54.88%
- p50
- 13.9s
- p99
- 165s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50◆ (best)
google-vertex/global/flex - Google100%◆ (best)Healthy24h 99.62%
- 7d
- 99.85%
- 30d
- 99.84%
- p50
- 1.08s◆ (best)
- p99
- 9.42s
- Throughput
- 98 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-vertex/global/priority - Google AI Studio100%◆ (best)Healthy24h 99.99%
- 7d
- 99.95%◆ (best)
- 30d
- 99.93%◆ (best)
- p50
- 2.30s
- p99
- 39.9s
- Throughput
- 69 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50◆ (best)
google-ai-studio/flex - Google AI Studio100%◆ (best)Healthy24h 99.92%
- 7d
- 99.82%
- 30d
- 99.86%
- p50
- 1.13s
- p99
- 4.44s◆ (best)
- Throughput
- 81 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-ai-studio/priority - Google AI Studio99.99%Healthy24h 99.94%
- 7d
- 99.89%
- 30d
- 99.90%
- p50
- 1.38s
- p99
- 10.1s
- Throughput
- 76 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-ai-studio - Google99.55%Healthy24h 99.59%
- 7d
- 99.49%
- 30d
- 98.46%
- p50
- 1.25s
- p99
- 9.99s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-vertex/global
Measured 5m 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.