Vercel AI Gateway adds Private Inference for self-hosted and fine-tuned models
soleio · x · 2026-11-17
Vercel announced Private Inference on AI Gateway, callable via a private/<slug> scheme.
Developers can now route their own fine-tuned, self-hosted, or prerelease models through the gateway alongside catalog models, using the same APIs, auth, and logging — no separate integration layer needed for private models.
More from Infra
- NVIDIA open-sources cuPotential, 3x faster molecular dynamics on Blackwell GPUs — AllThingsApx · 2026-11-17
- Flights, banks and Microsoft hit by mass outages; officials deny cyberattack — AaronBergman18 · 2026-11-17
- Critical systems keep having unexplained outages that officials claim are unrelated — josh_bickett · 2026-11-17
- From a Core i5 Mini PC to Xeon + 1080 Ti: One User's Four-Year Local AI Stack Journey — revennest · 2026-11-17
- Q-CTRL unifies calibration and execution into autonomous workflow, QPUs ready in hours — MJBiercuk · 2026-11-17
- SPARE preprint: 2.55x faster decoding for linear attention on a 1.3B model — krishnan · 2026-11-17