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

# VastAI.create_workergroup

Create a new autoscale worker group.

## Signature

```python theme={null}
VastAI.create_workergroup(
    template_hash: Optional[str] = None,
    template_id: Optional[int] = None,
    no_default: bool = False,
    launch_args: Optional[str] = None,
    endpoint_name: Optional[str] = None,
    endpoint_id: Optional[int] = None,
    test_workers: int = 3,
    gpu_ram: Optional[float] = None,
    search_params: Optional[str] = None,
    min_load: Optional[float] = None,
    target_util: Optional[float] = None,
    cold_mult: Optional[float] = None,
    cold_workers: Optional[int] = None
) -> str
```

## Parameters

<ParamField path="template_hash" type="Optional[str]">
  Hash of the instance template to use for workers.
</ParamField>

<ParamField path="template_id" type="Optional[int]">
  ID of the instance template to use for workers.
</ParamField>

<ParamField path="no_default" type="bool" default="False">
  Disable the default search query filters when finding offers.
</ParamField>

<ParamField path="launch_args" type="Optional[str]">
  Additional CLI arguments passed when launching worker instances.
</ParamField>

<ParamField path="endpoint_name" type="Optional[str]">
  Human-readable name for the endpoint this group belongs to.
</ParamField>

<ParamField path="endpoint_id" type="Optional[int]">
  ID of the endpoint this worker group belongs to.
</ParamField>

<ParamField path="test_workers" type="int" default="3">
  Number of test workers to spin up during initial scaling evaluation.
</ParamField>

<ParamField path="gpu_ram" type="Optional[float]">
  Minimum GPU RAM in GiB required per worker.
</ParamField>

<ParamField path="search_params" type="Optional[str]">
  Query string for filtering available GPU offers (e.g. "gpu\_name=RTX\_4090 num\_gpus=1").
</ParamField>

<ParamField path="min_load" type="Optional[float]">
  Minimum load (requests/sec) below which idle workers are scaled down.
</ParamField>

<ParamField path="target_util" type="Optional[float]">
  Target worker utilization ratio (0.0-1.0); workers are added to stay at this level.
</ParamField>

<ParamField path="cold_mult" type="Optional[float]">
  Multiplier applied to warm worker count for pre-warming cold workers.
</ParamField>

<ParamField path="cold_workers" type="Optional[int]">
  Number of pre-warmed (cold) workers to keep ready.
</ParamField>

## Returns

`str`, Result from the API call.

## Example

```python theme={null}
from vastai import VastAI

client = VastAI(api_key="YOUR_API_KEY")
result = client.create_workergroup()
print(result)
```