> ## 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.

# AWS

> The default serving provider: single-GPU L4/A10G and whole-node A100/H100 on EC2.

AWS is the default serving provider — omit the `provider` field to use it.

## Serving shapes

| `gpu_type`  | Memory | GPUs per node  | Good for                                     |
| ----------- | ------ | -------------- | -------------------------------------------- |
| `L4-24GB`   | 24 GB  | 1              | Small models (≤3B), cost-sensitive endpoints |
| `A10G-24GB` | 24 GB  | 1              | Same tier as L4, Ampere                      |
| `A100-80GB` | 80 GB  | 8 (whole node) | Large models with tensor parallel            |
| `H100-80GB` | 80 GB  | 8 (whole node) | Fastest per-request latency, TP up to 8      |

<Note>
  AWS has no single-GPU A100/H100 instance — the smallest SKU is the whole 8-GPU node, and you pay for all of it. For a single A100/H100, pick a provider with a genuine 1-GPU shape ([GCP](/deployments/providers/gcp), or DigitalOcean when it lands).
</Note>

## Creating a deployment

```python theme={null}
client.deployments.create(
    model="Qwen/Qwen2.5-0.5B-Instruct",
    source="huggingface",
    name="my-deploy",
    gpu={"gpu_type": "L4-24GB", "gpu_count": 1},
    # provider defaults to "aws"
)
```

Both engines (`vllm` default, `max`) are supported. Replicas, autoscaling, and scale-to-zero work as documented in [Scaling](/cli/deployments#replicas-autoscaling-and-scale-to-zero).

## 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="GPU sizing" icon="ruler" href="/deployments/hosting">
    Match GPU memory to model size.
  </Card>
</CardGroup>