LayerX launches AI Gateway unified gateway
Understand this story
LayerX has released AI Gateway, which unifies self-hosted vLLM and Ollama models with third-party providers such as OpenAI, Groq, and Together into a single OpenAI-compatible endpoint, deployed on the user's own servers. The gateway provides usage controls: each user has daily and monthly token budgets, each key has a per-minute request limit, and administrators can specify which models each user can call. LayerX also says that if users do not want to run it themselves, they can contact it for hosting and management. The product is currently available via a contact form, and pricing has not yet been announced.
AI overview based on source reports · Updated 7 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIAI Gateway: Manage your company's AI from one place
AI Gateway is a self-hosted, OpenAI-compatible endpoint that routes requests to your own GPU servers (vLLM, Ollama) first and falls back to providers like OpenAI, Groq and Together when needed. It adds per-user keys, token budgets and model access controls, plus a dashboard tracking tokens and cost per user, key, model and provider, and it does not log or store prompts and responses. Deployment is on your own servers or hosted by the vendor, and existing OpenAI SDK code only needs a base URL and key change.
Activity for this story
Not enough continuous observations to show a trend yet.