ngrok (@ngrokHQ) / X

ngrok

2,070 posts

ngrok

@ngrokHQ

One gateway for all your traffic. Service status available at status.ngrok.com.

localhost

Joined October 2020

Pinned
ngrok
@ngrokHQ
Aug 7
Mac Chaffee has argued with coworkers at every job they've had. So they interviewed our infra team about a contentious decision (adopt Argo Rollouts or build our own) to answer one question: Am I the problem? We let them publish whatever they found. macchaffee.com/blog/2026/am-i…
ngrok
@ngrokHQ
22h
New to the AI Gateway usage page: requests, success rate, and cost, broken down by provider and charted over time. Every attempt is itemized down to tokens in, tokens out, and cost, even the ones that hit a model you serve with vLLM. Sign up → app.ngrok.ai
ngrok
@ngrokHQ
Aug 9
The self-hosted model in this demo never gets a public URL. Our own @ryan_blunden routes Gemma 4, running in LM Studio on his machine, through the ngrok AI Gateway alongside OpenAI and Anthropic. Models you rent and models you run, one gateway ↓ ngrok.ai
00:00
ngrok
@ngrokHQ
Aug 7
Nine new models landed lately on the AI Gateway: seven Gemini, plus Claude Opus 5 and Sonnet 5, all flat-rate and fully through our managed inference. ... which means no need for Google or Anthropic accounts to route their way. Full model catalog ↓
ngrok.com
Model Catalog - ngrok documentation
Built-in providers and models available on ngrok.ai.
ngrok
@ngrokHQ
Aug 5
You should be able to send inference requests: → to any public provider → privately to models you self-host → to any number of fallbacks → with full access control and observability built in ngrok.ai is live on Product Hunt today ↓ producthunt.com/products/ngrok…
One gateway, every model — ngrok.ai
From ngrok.ai