⚡
Eluvix Application Suite (Live Interactive Simulator)
SIMULATOR LIVEExperience the entire Eluvix system directly in your browser. All tabs are interactive with zero installation required.
PROXY: 127.0.0.1:3000
Installation Docs ➔Gateway Port
127.0.0.1:3000
OpenAI API Compatible • Online
Active Upstreams
7 / 7
5 zero-cost local engines
Routing Strategy
Local Workload Ratio
88.4%
Average compute cost: $0.0000/req
🔌 Upstream Engines & Local GatewaysSorted by Execution Priority
Eluvix queries local hardware first, falling back to lower-priority or cloud providers only when necessary.
Local vLLM GPU Servervllm$0.00 / 1k (Local)
http://localhost:8000•14ms ping
Priority:
Models:meta-llama/Llama-3-8bmeta-llama/Llama-3-70bmistralai/Mistral-7B-Instruct-v0.3
Local vLLM-sr (Speculative)vllm-sr$0.00 / 1k (Local)
http://localhost:8001•9ms ping
Priority:
Models:meta-llama/Llama-3-8b-instructdeepseek-ai/deepseek-coder-6.7b
Local Ollama Engineollama$0.00 / 1k (Local)
http://localhost:11434•18ms ping
Priority:
Models:llama3.1:latestqwen2.5-coder:7bmistral:latestphi3:minillava:latest
Lemonade Routerlemonade$0.00 / 1k (Local)
http://localhost:13305•12ms ping
Priority:
Models:llama3.2-1b-FLMQwen3.5-4B-MTP-GGUF
Local Switchyard Edge Nodeswitchyard$0.00 / 1k (Local)
http://localhost:8080•24ms ping
Priority:
Models:deepseek-ai/deepseek-coder-6.7bcodellama:13b
Billama Decentralized Meshbillama$0.00015 / 1k (Cloud)
https://api.billama.dev•48ms ping
Priority:
Models:* (Community GPU Mesh)
OpenAI Direct Frontieropenai-compatible$0.00500 / 1k (Cloud)
https://api.openai.com•310ms ping
Priority:
Models:gpt-4ogpt-4o-minio1-preview
🐳 Local Docker MicroservicesDocker Daemon Connected
Manage containerized LLM inference engines with one click.
Ollama EngineRunning
Port: 11434
Img: ollama/ollama:latest
vLLM OpenAI ServerRunning
Port: 8000
Img: vllm/vllm-openai:latest
Lemonade RouterRunning
Port: 13305
Img: lemonade/router:latest
Switchyard NodeStopped
Port: 8080
Img: eluvix/switchyard:v0.1