Skip to main content
PUT
/
api
/
v0
/
workergroups
/
{id}
update workergroup
curl --request PUT \
  --url https://console.vast.ai/api/v0/workergroups/{id}/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "min_load": 1,
  "target_util": 0.9,
  "cold_mult": 3,
  "test_workers": 3,
  "template_hash": "abc123def456",
  "template_id": 456,
  "search_params": "gpu_name=RTX_3090 rentable=true",
  "launch_args": "--env VAR=value",
  "gpu_ram": 24,
  "endpoint_name": "vLLM-Qwen3-8B",
  "endpoint_id": 123
}
'
{
  "success": true
}

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.

Authorizations

​
Authorization
string
header
required

API key must be provided in the Authorization header

Path Parameters

​
id
integer
required

The ID of the workergroup to update.

Example:

4242

Body

application/json
​
min_load
number

Minimum load for the workergroup.

Example:

1

​
target_util
number

Target utilization for the workergroup.

Example:

0.9

​
cold_mult
number

Cold multiplier for the workergroup.

Example:

3

​
test_workers
integer
default:3

Number of test workers for performance estimation.

Example:

3

​
template_hash
string

Template hash for the workergroup.

Example:

"abc123def456"

​
template_id
integer

Template ID for the workergroup.

Example:

456

​
search_params
string
default:verified=true rentable=true rented=false

Search parameters for offers (JSON object or query string).

Example:

"gpu_name=RTX_3090 rentable=true"

​
launch_args
string

Launch arguments for creating instances.

Example:

"--env VAR=value"

​
gpu_ram
number

Estimated GPU RAM requirement.

Example:

24

​
endpoint_name
string

Deployment endpoint name.

Example:

"vLLM-Qwen3-8B"

​
endpoint_id
integer

Deployment endpoint ID.

Example:

123

Response

Successfully updated the workergroup.

​
success
boolean
Example:

true