Six models returned to active status following failed checks in the last 24 hours, including GPT-5.4 Mini, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, Gemini 3.1 Pro (preview), and Gemini 3.1 Flash Lite.
Prices
Gemini 3.1 Flash Lite is priced at $0.250/M for input and $1.50/M for output. The Gemini 3.1 Pro (preview) model costs $2.00/M for input and $12.00/M for output. Several Google models did not respond during the latest pricing check, including Gemini 3.5 Flash ($1.50/M in, $9.00/M out), Gemini 2.5 Flash ($0.300/M in, $2.50/M out), Gemini 2.5 Flash Lite ($0.100/M in, $0.400/M out), and Gemini 2.5 Pro ($1.25/M in, $10.00/M out).
Speed
Median response times and uptime for the last 24 hours are detailed below. All measured models shared a consistent uptime of 41.7%.
| Model | Median Response Time | Uptime |
|---|---|---|
| GPT-5.4 Mini | 705ms | 41.7% |
| Gemini 3.1 Flash Lite | 903ms | 41.7% |
| GPT-5.6 Terra | 1.28s | 41.7% |
| GPT-5.6 Sol | 1.33s | 41.7% |
| GPT-5.6 Luna | 1.34s | 41.7% |
| Gemini 3.8 Flash | 3.43s | 41.7% |
| Gemini 3.1 Pro (preview) | 3.79s | 41.7% |
Benchmark
Standing benchmark results from the last 7 days show Gemini 3.8 Flash and GPT-5.6 Terra tied for the lead with 100% of available points, both requiring $0 spend to run. Gemini 3.1 Flash Lite reached 84.4% of points with $0 spend. GPT-5.6 Luna achieved 66.7% of points with $0 spend.
These measurements prove current response times and benchmark percentages for the listed models. They do not prove the cause of the 41.7% uptime rate or the reason for the lack of response from Gemini 2.5 and 3.5 series models during pricing checks.
