LLM Latency Tracker
远程Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
安装配置
{
"mcpServers": {
"llm-latency-tracker": {
"url": "https://llmlatency.dev/mcp"
}
}
}
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
{
"mcpServers": {
"llm-latency-tracker": {
"url": "https://llmlatency.dev/mcp"
}
}
}