Gemini 3 Flash Preview
google/gemini-3-flash-previewInputOutput
Compare its 6 providersIncident RSSCompare with Gemini 3.1 Flash Lite, Gemini 2.5 Flash, Gemini 3.5 Flash
CompareGemini 3 Flash Preview
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/global | No data | — | — | 99.36% | 98.26% | — | — | — | 1.0M | $0.500 / $3.00 |
Googlegoogle-vertex/global/flex | No data | — | — | 99.63% | 46.43% | — | — | — | 1.0M | $0.250 / $1.50 |
Googlegoogle-vertex/global/priority | No data | — | — | 99.75% | 99.82% | — | — | — | 1.0M | $0.900 / $5.40 |
Google AI Studiogoogle-ai-studio | No data | — | — | 99.87% | 99.89% | — | — | — | 1.0M | $0.500 / $3.00 |
Google AI Studiogoogle-ai-studio/flex | No data | — | — | 99.88% | 99.92% | — | — | — | 1.0M | $0.250 / $1.50 |
Google AI Studiogoogle-ai-studio/priority | No data | — | — | 99.76% | 99.86% | — | — | — | 1.0M | $0.900 / $5.40 |
- No data24h —
- 7d
- 99.36%
- 30d
- 98.26%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-vertex/global - No data24h —
- 7d
- 99.63%
- 30d
- 46.43%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-vertex/global/flex - No data24h —
- 7d
- 99.75%
- 30d
- 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-vertex/global/priority - No data24h —
- 7d
- 99.87%
- 30d
- 99.89%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.00
google-ai-studio - No data24h —
- 7d
- 99.88%
- 30d
- 99.92%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.50
google-ai-studio/flex - No data24h —
- 7d
- 99.76%
- 30d
- 99.86%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.900 / $5.40
google-ai-studio/priority
No recent measurement.
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 · 46 days with data, 41 endpoint-days below 90%.