N

NexusAI

Sign in to the admin console

key

Token is defined in ADMIN_TOKEN env var

NexusAI 99.99% Uptime

One API.
Every Frontier Model.

Unified inference infrastructure for production-grade LLM workloads. Sub-100ms latency, enterprise security, usage-based pricing — all behind a single OpenAI-compatible endpoint.

dns

RunPod Deployment

Live status of the backing GPU endpoint

Loading...

Endpoint

—

Name

—

GPU Type

—

GPUs

—

Workers Idle

—

Workers Running

—

Workers Pending

—

Worker Count

—

Image

—

Memory

—

Disk

—

smart_toy Quick Start With Copilot

Add this entry to your VS Code chatLanguageModels.json file to use NexusAI with GitHub Copilot:

[
    {
        "name": "NexusAI",
        "vendor": "ollama-models",
        "url": "https://agent.ash-api.online"
    }
]
info File path: ~/Library/Application Support/Code/User/chatLanguageModels.json

Live Monitoring

Real-time inference tracking

Monitor every API request, response, tokens consumed, and latency metrics in real time.

receipt_long

Inference Logs

0
Time User Endpoint Model Prompt Tokens Latency View