The most notable movement in the last 24 hours is a total collapse in availability across multiple provider families. Seven models, spanning the GPT-5.4, GPT-5.6, and Gemini 3.1 and 3.8 series, recorded 0% success rates during hourly uptime checks.
Speed
Median response times could not be calculated due to the complete lack of successful requests. The following table details the observed uptime for the affected models:
| Model | Median Response Time | Uptime Success Rate |
|---|---|---|
| GPT-5.4 Mini | — | 0% |
| GPT-5.6 Sol | — | 0% |
| GPT-5.6 Terra | — | 0% |
| GPT-5.6 Luna | — | 0% |
| Gemini 3.1 Pro (preview) | — | 0% |
| Gemini 3.1 Flash Lite | — | 0% |
| Gemini 3.8 Flash | — | 0% |
Prices
While availability failed, billed costs per million tokens remain as follows for Google's Gemini fleet. Several of these models were not responding during the latest checks.
- Gemini 3.5 Flash: $1.50/M in, $9.00/M out
- Gemini 3.1 Flash Lite: $0.250/M in, $1.50/M out
- Gemini 3.1 Pro (preview): $2.00/M in, $12.00/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
- Gemini 2.5 Pro: $1.25/M in, $10.00/M out
Benchmark
No standing benchmark data was recorded for the last 7 days.
These measurements prove a total absence of response from the listed models during the 24-hour window. They do not prove the cause of the outages or the current status of the providers' internal systems beyond the failure of the hourly checks.
