Horay.ai Uptime Monitor
High-Speed AI Model Inference Platform
Last 30 Days Performance
Average Uptime
100%
Based on 30-day monitoring period
Average Response Time
153.77ms
Mean response time across all checks
Daily Status Overview
Hover for detailsHistorical Performance
Dec-2025
99.82% uptime
Monthly Uptime
99.82%
Monthly Response Time
125ms
Daily Status Breakdown
Nov-2025
98.56% uptime
Monthly Uptime
98.56%
Monthly Response Time
127ms
Daily Status Breakdown
Oct-2025
99.73% uptime
Monthly Uptime
99.73%
Monthly Response Time
136ms
Daily Status Breakdown
Sep-2025
100% uptime
Monthly Uptime
100%
Monthly Response Time
139ms
Daily Status Breakdown
Aug-2025
99.87% uptime
Monthly Uptime
99.87%
Monthly Response Time
140ms
Daily Status Breakdown
Jul-2025
99.66% uptime
Monthly Uptime
99.66%
Monthly Response Time
127ms
Daily Status Breakdown
Jun-2025
99.92% uptime
Monthly Uptime
99.92%
Monthly Response Time
125ms
Daily Status Breakdown
May-2025
100% uptime
Monthly Uptime
100%
Monthly Response Time
129ms
Daily Status Breakdown
Apr-2025
100% uptime
Monthly Uptime
100%
Monthly Response Time
164ms
Daily Status Breakdown
Related Uptime Monitors
Explore uptime status for similar tools that also have monitoring enabled.
-
OperationalAvian API
Fastest, production grade API for Open Source LLMs
Avian API is an enterprise-grade language model inference platform offering state-of-the-art LLMs with superior speed and competitive pricing, powered by Meta's Llama models and Nvidia H200 SXM technology.
Last checked: 1 hour ago View Status -
OperationalLLM API
Access 200+ AI Models with One Unified API
LLM API provides seamless access to over 200 leading AI models from top providers like OpenAI, Anthropic, Google, and Meta through a single, reliable API, empowering businesses and developers with infinite scalability.
Last checked: 1 hour ago View Status -
IssuesDialoq AI
Run any AI models through one simple unified API
Dialoq AI is a comprehensive API gateway that enables developers to access and integrate 200+ Language Learning Models (LLMs) through a single, unified API, streamlining AI application development with enhanced reliability and cost predictability.
Last checked: 1 hour ago View Status -
OperationalOxyAPI
An AI Platform built for developers
OxyAPI provides developers with instant API access to a wide range of AI models, featuring global deployment and simple pay-as-you-go pricing.
Last checked: 1 hour ago View Status -
OperationalFriendliAI
Accelerate Generative AI Inference
FriendliAI provides a high-performance platform for accelerating generative AI inference, enabling fast, cost-effective, and reliable deployment and serving of Large Language Models (LLMs).
Last checked: 1 hour ago View Status -
OperationalGroq
Fast AI Inference for Openly-Available Models
Groq provides high-speed AI inference services for leading openly-available large language models (LLMs), automatic speech recognition (ASR), and vision models via its GroqCloud™ platform.
Last checked: 1 hour ago View Status