ngrok launches AI Gateway: route self-hosted and frontier models through one managed URL
anthara_ai · x · 2026-09-05
ngrok launched AI Gateway (GOPHRS), a managed gateway unifying self-hosted and frontier provider models: swap your baseURL to gateway.ngrok.ai, change the API key, and it works with OpenAI, Anthropic, and Vercel AI SDKs.
Key capabilities:
- Smart routing and fallback: route to a self-hosted model (e.g. local Qwen GGUF) first, falling back to gpt-5.4, claude-opus, or other public providers
- Local LLM connectivity over private links, no public IPs or inbound ports
- BYOK key management: keep your existing provider keys and rates, with scoped per-app/per-dev keys controlling model access
- Observability: token, latency, error and cost rollups across apps, devs, and models
The company says the architecture is final, pitching it as "never bet on one model" multi-model routing.
Related event: ngrok Launches AI Gateway to Route Cloud and Local Models via One URL(6 posts)→
More from coding & agent
- A boring but effective way to test new models: feed them your stalled tasks — wightmanr · 2026-09-05
- Japanese indie dev's M3 interactive editor for agent prompts hits 500 GitHub stars — moeinteractive · 2026-09-05
- Rethinking skills and prompts for GPT-6 Astra: coding agent best practices are changing fast — pvncher · 2026-09-05
- serve: an MCP That Turns Hosting and Tunneling Into a Conversation With Your Agent — Imaginary-Bluejay721 · 2026-09-05
- Grok Build v1.0.19 ships background loops, worktree support, now powered by Grok 4.6 — elonmusk · 2026-09-05
- PSAISuite: one string swap in -Model runs any new model, unchanged for months — dfinke · 2026-09-05