Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview
Compare with Gemini 2.5 Pro, Nano Banana Pro (Gemini 3 Pro Image), Gemini 3.1 Pro Preview Custom Tools
CompareGemini 3.1 Pro Preview
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 99.74% | 99.14% | 3.33s | 24.7s | 93 tps | 1.0M | $2.00 / $12.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 99.74% | 99.14% | 3.45s | 10.5s | 82 tps | 1.0M | $1.00 / $6.00 |
Google AI Studiogoogle-ai-studio/priority | Healthy | 99.74% | 99.14% | — | — | — | 1.0M | $3.60 / $21.60 |
Googlegoogle-vertex/global | Healthy | 98.72% | 95.32% | 2.85s | 31.5s | 104 tps | 1.0M | $2.00 / $12.00 |
Googlegoogle-vertex/global/flex | Healthy | 98.72% | 95.32% | — | — | — | 1.0M | $1.00 / $6.00 |
Googlegoogle-vertex/global/priority | Healthy | 98.72% | 95.32% | 5.66s | 6.03s | 72 tps | 1.0M | $3.60 / $21.60 |
- Google AI Studio99.74%Healthy24h 99.14%
- p50
- 3.33s
- p99
- 24.7s
- Throughput
- 93 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $12.00
google-ai-studio - Google AI Studio99.74%Healthy24h 99.14%
- p50
- 3.45s
- p99
- 10.5s
- Throughput
- 82 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $6.00
google-ai-studio/flex - Google AI Studio99.74%Healthy24h 99.14%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.60 / $21.60
google-ai-studio/priority - Google98.72%Healthy24h 95.32%
- p50
- 2.85s
- p99
- 31.5s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $12.00
google-vertex/global - Google98.72%Healthy24h 95.32%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.00 / $6.00
google-vertex/global/flex - Google98.72%Healthy24h 95.32%
- p50
- 5.66s
- p99
- 6.03s
- Throughput
- 72 tps
- Context
- 1.0M
- $/Mtok
- $3.60 / $21.60
google-vertex/global/priority
Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.