> ## Documentation Index
> Fetch the complete documentation index at: https://docs.veri.studio/llms.txt
> Use this file to discover all available pages before exploring further.

# DigitalOcean

> H100, L40S, and AMD MI300X GPU Droplets for serving — wired but feature-gated; creates return a 400 until the gate lifts.

DigitalOcean serving is wired but currently feature-gated: a `provider="digitalocean"` create returns a "coming soon" 400 until the gate lifts.

## Planned serving shapes

| `gpu_type`     | Memory | GPUs per node | Status      |
| -------------- | ------ | ------------- | ----------- |
| `H100-80GB`    | 80 GB  | 1             | Coming soon |
| `L40S-48GB`    | 48 GB  | 1             | Coming soon |
| `MI300X-192GB` | 192 GB | 1             | Coming soon |

Two shapes worth noting:

* **L40S-48GB** — the genuine cheap single-GPU shape that still fits a 7B-13B bf16 model, which the 24 GB L4/A10G cannot.
* **MI300X-192GB** — the same 192 GB AMD card [Hot Aisle serves today](/deployments/providers/hotaisle); on DigitalOcean it arrives with per-second billing.

Watch `veri gpu list` — the `(soon)` marker on the serving column disappears when the gate lifts.

## Where to go next

<CardGroup cols={2}>
  <Card title="All serving providers" icon="server" href="/deployments/providers">
    Compare shapes, status, and the live CLI catalog.
  </Card>

  <Card title="Hot Aisle (AMD)" icon="microchip" href="/deployments/providers/hotaisle">
    MI300X serving that's available today.
  </Card>
</CardGroup>