Update Endpoint, This Can Also Be Used To Start Or Stop A Dedicated Endpoint

Updates an existing endpoint’s configuration. You can modify the display name, autoscaling settings, or change the endpoint’s state (start/stop).

PATCH /endpoints/{endpointId}

Update endpoint, this can also be used to start or stop a dedicated endpoint

cURL

curl --request PATCH \
  --url https://api.together.xyz/v1/endpoints/{endpointId} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "display_name": "My Llama3 70b endpoint",
  "state": "STARTED",
  "autoscaling": {
    "min_replicas": 123,
    "max_replicas": 123
  },
  "inactive_timeout": 60
}
'

200

{
  "object": "endpoint",
  "id": "endpoint-d23901de-ef8f-44bf-b3e7-de9c1ca8f2d7",
  "name": "devuser/meta-llama/Llama-3-8b-chat-hf-a32b82a1",
  "display_name": "My Llama3 70b endpoint",
  "model": "meta-llama/Llama-3-8b-chat-hf",
  "hardware": "1x_nvidia_a100_80gb_sxm",
  "type": "dedicated",
  "owner": "devuser",
  "state": "STARTED",
  "autoscaling": {
    "min_replicas": 123,
    "max_replicas": 123
  },
  "created_at": "2025-02-04T10:43:55.405Z"
}

Authorizations

Authorization · string · header · default: default · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

endpointId · string · required

The ID of the endpoint to update

Body

application/json

display_name · string

A human-readable name for the endpoint

Example:

"My Llama3 70b endpoint"

state · enum<string>

The desired state of the endpoint

Available options: STARTED, STOPPED

Example:

"STARTED"

autoscaling · object

New autoscaling configuration for the endpoint

Show child attributes

inactive_timeout · integer | null

The number of minutes of inactivity after which the endpoint will be automatically stopped. Set to 0 to disable automatic timeout.

Example:

60

Response

200

application/json

200

Details about a dedicated endpoint deployment

object · enum<string> · required

The type of object

Available options: endpoint

Example:

"endpoint"

id · string · required

Unique identifier for the endpoint

Example:

"endpoint-d23901de-ef8f-44bf-b3e7-de9c1ca8f2d7"

name · string · required

System name for the endpoint

Example:

"devuser/meta-llama/Llama-3-8b-chat-hf-a32b82a1"

display_name · string · required

Human-readable name for the endpoint

Example:

"My Llama3 70b endpoint"

model · string · required

The model deployed on this endpoint

Example:

"meta-llama/Llama-3-8b-chat-hf"

hardware · string · required

The hardware configuration used for this endpoint

Example:

"1x_nvidia_a100_80gb_sxm"

type · enum<string> · required

The type of endpoint

Available options: dedicated

Example:

"dedicated"

owner · string · required

The owner of this endpoint

Example:

"devuser"

state · enum<string> · required

Current state of the endpoint

Available options: PENDING, STARTING, STARTED, STOPPING, STOPPED, ERROR

Example:

"STARTED"

autoscaling · object · required

Configuration for automatic scaling of the endpoint

Show child attributes

created_at · string<date-time> · required

Timestamp when the endpoint was created

Example:

"2025-02-04T10:43:55.405Z"