Gemini 3.8 Flash
google/gemini-3.8-flashInputOutput
Compare its 6 providersIncident RSSCompare with Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash
CompareGemini 3.8 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio/flex | Healthy | 100% | 99.81% | 99.89% | 99.68% | 1.86s | 51.5s | 185 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio | Healthy | 99.99% | 99.91% | 99.81% | 99.73% | 1.38s | 7.75s | 144 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global | Healthy | 96.12% | 97.54% | 95.85% | 97.43% | 2.33s | 28.3s | 70 tps | 1.0M | $0.750 / $3.75 |
Googlegoogle-vertex/global/priority | Down | 89.80% | 99.87% | 99.90% | 99.81% | 1.88s | 8.03s | 106 tps | 1.0M | $1.35 / $6.75 |
Googlegoogle-vertex/global/flex | Down | — | 77.36% | 83.14% | 87.52% | 13.9s | 265s | 50 tps | 1.0M | $0.375 / $1.88 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 99.69% | 98.69% | 98.63% | 1.79s | 6.04s | 76 tps | 1.0M | $1.35 / $6.75 |
- Google AI Studio100%Healthy24h 99.81%
- 7d
- 99.89%
- 30d
- 99.68%
- p50
- 1.86s
- p99
- 51.5s
- Throughput
- 185 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-ai-studio/flex - Google AI Studio99.99%Healthy24h 99.91%
- 7d
- 99.81%
- 30d
- 99.73%
- p50
- 1.38s
- p99
- 7.75s
- Throughput
- 144 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-ai-studio - Google96.12%Healthy24h 97.54%
- 7d
- 95.85%
- 30d
- 97.43%
- p50
- 2.33s
- p99
- 28.3s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.75
google-vertex/global - Google89.80%Down24h 99.87%
- 7d
- 99.90%
- 30d
- 99.81%
- p50
- 1.88s
- p99
- 8.03s
- Throughput
- 106 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-vertex/global/priority - Down24h 77.36%
- 7d
- 83.14%
- 30d
- 87.52%
- p50
- 13.9s
- p99
- 265s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.88
google-vertex/global/flex - No data24h 99.69%
- 7d
- 98.69%
- 30d
- 98.63%
- p50
- 1.79s
- p99
- 6.04s
- Throughput
- 76 tps
- Context
- 1.0M
- $/Mtok
- $1.35 / $6.75
google-ai-studio/priority
Measured 1m 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 · 6 endpoints · 15 days with data, 23 endpoint-days below 90%.