Hanzo

Gpus

Per-accelerator GPU inventory

Per-accelerator GPU inventory

Base URLhttps://api.hanzo.ai
Operations2
AuthAuthorization: Bearer $HANZO_API_KEY

gpus

Is an HONEST empty surface: Visor exposes no GPU alert inventory, so this returns [] rather than fabricating alerts.

GET /v1/gpus/alerts

Is an HONEST empty surface: Visor exposes no GPU alert inventory, so this returns [] rather than fabricating alerts. It stays a real, tenant-gated route so the console's alerts fetch resolves (200 [], not a 404) — an honest "no alerts", the same discipline the rest of the surface follows.

Returns one row per physical accelerator the caller's org has, derived from its real GPU machines (the size slug says how many cards a node holds) and from the accelerators BYO workers report through nvidia-smi.

GET /v1/gpus

Returns one row per physical accelerator the caller's org has, derived from its real GPU machines (the size slug says how many cards a node holds) and from the accelerators BYO workers report through nvidia-smi.

Live telemetry is absent on Visor rows because Visor's machine object carries none — an honest omission the console renders as "—", never a fabricated 0.


All Hanzo APIs · Interactive reference

How is this guide?

On this page