# Running instances

## post by Eun on Jan 10, 2024

What do you mean by “billed for as long as GPU is running, regardless of being actively used”

## post by cody_b on Jan 10, 2024

Billing continues as long as an instance is running, even if the GPUs are idle like shown, below.

```auto
$ nvidia-smi
Wed Jan 10 21:52:26 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.12             Driver Version: 535.104.12   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA A10                     On  | 00000000:07:00.0 Off |                    0 |
|  0%   28C    P8               8W / 150W |      4MiB / 23028MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+
```