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

# Serverless Loops

> Train and sample without managing deployments, and pay for the tokens you use.

In the serverless mode, you create a run and call the same training and sampling operations as in any Loops run. Baseten manages the infrastructure, and you pay for the tokens you train and sample. It's self-serve: start runs, and start more of them, without contacting Baseten.

The serverless mode supports a subset of models. Filter the [model catalog](https://docs.baseten.co/loops/supported-models.md) by **Serverless** to see them and the sequence length each supports.

## Start a serverless run

When your workspace has serverless access to the model, runs use the serverless mode by default; you don't need to change your code. To require the serverless mode, set `scope` to `serverless`:

```python theme={"system"}
from baseten.loops import ServiceClient

training_client = ServiceClient().create_lora_training_client(
    base_model="zai-org/GLM-5.3-Flash",
    scope="serverless",
)
```

With `scope="serverless"`, creating the run fails instead of falling back to the dedicated mode when serverless can't take the run. See [choose a mode](https://docs.baseten.co/loops/availability-modes/overview.md#choose-a-mode) for the environment variable and REST equivalents.

To check serverless access for your workspace, call [Get server capabilities](https://docs.baseten.co/reference/loops-api/server/get-capabilities.md). Each model in the response has a `serverless` field.

## When a run can't use serverless

With the default `scope`, a run uses the [dedicated mode](https://docs.baseten.co/loops/availability-modes/dedicated.md) instead when:

* Your workspace doesn't have serverless access to the model.
* The run asks for a LoRA rank or sequence length that serverless doesn't support for the model.
* The run reuses another run's deployments.

Replica counts and the `availability_model` capacity type apply only in the dedicated mode. To scale out a run with them, set `scope` to `deployment`.

## Billing

Serverless runs bill for training and sampling token usage. Time between training operations, such as time spent reading results or changing a reward function, doesn't bill.

## Usage and logs

`baseten loops usage` reports dedicated GPU allocations. It doesn't report serverless token usage or spend.

**To inspect dedicated GPU allocations**:

Run the following command with an authenticated [Baseten CLI](https://docs.baseten.co/reference/cli/baseten/overview.md):

```bash Command theme={"system"}
baseten loops usage
```

```text Example output theme={"system"}
Trainer GPUs: 0 in use, 0 scaled to zero. Sampler GPUs: 0 in use, 0 scaled to zero.
62 allocation(s) holding no live GPUs hidden; pass --all to show them.
```

When allocations hold GPUs, the output also includes a table of runs, GPU types, and statuses. For more information, see [`baseten loops usage`](https://docs.baseten.co/reference/cli/baseten/loops#usage).

Deployment logs cover dedicated runs. For more information about errors from serverless training and sampling calls, see [Loops troubleshooting](https://docs.baseten.co/troubleshooting/loops.md).

## Finish a run

An idle serverless run incurs no token charges, so deactivation isn't required to avoid idle billing. Saved checkpoints remain available to download, deploy, or start a new run from.

**To end a run and its paired sampler**:

Save the checkpoints you need, then run the following command. Replace `<run_id>` with `TrainingClient.run_id`, and confirm when prompted:

```bash theme={"system"}
baseten loops run deactivate --run-id "<run_id>"
```

The CLI confirms success with `Deactivated Loops run <run_id>`.

For more information, see [Deactivate a run](https://docs.baseten.co/loops/deactivate-a-run.md).