Gemini 3.8 Flash
google/gemini-3.8-flashInputOutput
Compare its 7 providersIncident RSSCompare with Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash
CompareGemini 3.8 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/global | Healthy | 100% | 100% | 99.56% | 97.36% | 2.50s | 18.9s | 76 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/priority | Healthy | 100% | 100% | 99.78% | 99.15% | 2.27s | 16.6s | 51 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/us | Healthy | 100% | 99.71% | 93.50% | 94.40% | 2.91s | 15.9s | 85 tps | 1.0M | $0.825 / $4.13 |
Google AI Studiogoogle-ai-studio | Healthy | 100% | 100% | 100% | 99.98% | 2.85s | 12.0s | 70 tps | 1.0M | $0.750 / $3.75 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100% | 100% | 100% | 99.97% | 2.54s | 10.9s | 79 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100% | 100% | 99.73% | 99.54% | 5.17s | 9.62s | 85 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global/flex | No data | — | 74.85% | 86.33% | 86.65% | 13.7s | 98.9s | 24 tps | 1.0M | $0.375 / $1.88 |
- Google100%Healthy24h 100%
- 7d
- 99.56%
- 30d
- 97.36%
- p50
- 2.50s
- p99
- 18.9s
- Throughput
- 76 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Google100%Healthy24h 100%
- 7d
- 99.78%
- 30d
- 99.15%
- p50
- 2.27s
- p99
- 16.6s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority - Google100%Healthy24h 99.71%
- 7d
- 93.50%
- 30d
- 94.40%
- p50
- 2.91s
- p99
- 15.9s
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $0.825 / $4.13
google-vertex/us - Google AI Studio100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.98%
- p50
- 2.85s
- p99
- 12.0s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google AI Studio100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.97%
- p50
- 2.54s
- p99
- 10.9s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - Google AI Studio100%Healthy24h 100%
- 7d
- 99.73%
- 30d
- 99.54%
- p50
- 5.17s
- p99
- 9.62s
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority - No data24h 74.85%
- 7d
- 86.33%
- 30d
- 86.65%
- p50
- 13.7s
- p99
- 98.9s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global/flex
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 7 endpoints · 61 days with data, 94 endpoint-days below 90%.
Price changes
- Gemini 3.8 FlashGooglegoogle-vertex/us$0.750 → $0.825 / $3.75 → $4.13cache read $0.075 → $0.083reasoning $3.75 → $4.132026-10-15 19:31 UTC