(cache)ngrok on X: "You can now call models running on your own hardware through a hosted AI gateway. Privately, with one command: `ngrok http 8000 --url https://vllm.internal` Plus all the public models you know and love. ↓ https://t.co/CR5RB8LamL" / X

Post

ngrok
@ngrokHQ
You can now call models running on your own hardware through a hosted AI gateway. Privately, with one command: `ngrok http 8000 --url https://vllm.internal` Plus all the public models you know and love. ↓
One gateway, every model — ngrok.ai
From ngrok.ai
7:20 PM · Jul 1, 2026580KViews
ngrok
@ngrokHQ
Jul 1
One baseURL change and an access key gets you: → routing to every model, even dedicated ones on AWS, Azure, etc → automatic failover + retries when a model slows or fails → scoped keys per app → token, latency, and cost visibility by app, dev, and model
ngrok
@ngrokHQ
Jul 1
When you route to a local model, it's full private connectivity: no publicly addressable URLs, no public IPs to allowlist, or ports to open, wherever you've got those GPUs humming. Works with Ollama, vLLM, LM Studio, and the neoclouds, too.
ngrok
@ngrokHQ
Jul 1
One flat fee: $0.05 per million tokens with your inference billed on top. Buy credits as you go. Full writeup → ngrok.com/blog/new-ngrok… Docs → ngrok.com/docs/ai-gatewa…
Join the conversation
Read 1 more reply