ngrok launches AI Gateway: one URL to route cloud frontier models and self-hosted local LLMs
s_mohinii · x · 2026-09-04
ngrok has launched an AI Gateway that unifies frontier provider APIs and self-hosted models behind a single managed endpoint:
- One URL, any SDK: Point your OpenAI, Anthropic, or Vercel AI SDK at gateway.ngrok.ai, swap the key, and route — including fallback model lists — without changing code.
- Private local LLM access: Ollama on a laptop, vLLM on a server, or a fine-tuned model behind a firewall can all be reached without public IPs, inbound ports, or a VPN.
- BYOK and scoped keys: Keep using keys you already pay for, and give each app or developer an access key scoped to specific providers and models.
- Observability: Tokens, latency, errors, and costs rolled up per call and attributed to apps, devs, and models — not just provider-level spend.
Aimed at developers tired of juggling multiple APIs, keys, SDKs, and billing accounts, especially teams mixing private deployments with frontier models.
Related event: ngrok launches AI Gateway: one URL to route cloud and self-hosted models(7 posts)→
More from coding & agent
- Screenshot table to Excel in PowerShell: LLM only locates, code does the rest — dfinke · 2026-10-21
- One line of PowerShell turns any screenshot table into real Excel data in 4 seconds — dfinke · 2026-10-21
- Screenshot to spreadsheet in 4 seconds with one line of PowerShell — dfinke · 2026-10-21
- A mitm proxy that rewrites robots.txt to Allow: all gets you really far — generativist · 2026-10-21
- Anaconda ships MCP to stop coding agents from hallucinating malicious dependency packages — anacondainc · 2026-10-21
- 5-person team uses Claude and 300+ agents to design 318,484 proteins in 64 hours — 141_1337 · 2026-10-21