Skip to main content
PUT
/
dedicated
/
beta
/
endpoint
/
{endpoint_id}
Update endpoint spec
curl --request PUT \
  --url https://api.friendli.ai/dedicated/beta/endpoint/{endpoint_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "name": "<string>",
  "advanced": {
    "max_batch_size": 256,
    "tokenizer_skip_special_tokens": true,
    "tokenizer_add_special_tokens": true,
    "max_token_count": 2560,
    "enable_content_logging": true,
    "max_input_length": 123
  },
  "simplescale": {
    "replicas": 2
  },
  "autoscalingPolicy": {
    "minReplica": 0,
    "maxReplica": 1,
    "cooldownPeriod": 300
  },
  "hfModelRepo": "<string>",
  "hfModelRepoRevision": "<string>",
  "newVersionComment": "<string>",
  "instanceOptionId": "<string>"
}'
{
  "name": "endpoint-name",
  "gpuType": "NVIDIA H100",
  "numGpu": 1,
  "instanceId": "instance-id",
  "projectId": "project-id",
  "creatorId": "creator-id",
  "teamId": "team-id",
  "autoscalingMin": 0,
  "autoscalingMax": 1,
  "autoscalingCooldown": 300,
  "maxBatchSize": 10,
  "maxInputLength": 1024,
  "tokenizerSkipSpecialTokens": true,
  "tokenizerAddSpecialTokens": true,
  "currReplicaCnt": 1,
  "desiredReplicaCnt": 1,
  "updatedReplicaCnt": 1
}
Update a Dedicated Endpoint deployment with new configuration. To request successfully, it is mandatory to enter a Friendli Token (e.g. flp_XXX) value in the Bearer Token field. Refer to the authentication section on our introduction page to learn how to acquire this variable and visit here to generate your token.
This API is currently in Beta. While we strive to provide a stable and reliable experience, this feature is still under active development. As a result, you may encounter unexpected behavior or limitations. We encourage you to provide feedback to help us improve the feature before its official release.

Authorizations

​
Authorization
string
header
required

When using Friendli Suite API for inference requests, you need to provide a Friendli Token for authentication and authorization purposes.

For more detailed information, please refer here.

Headers

​
X-Friendli-Team
string | null

ID of team to run requests as (optional parameter).

Path Parameters

​
endpoint_id
string
required

The ID of the endpoint

Body

application/json

Dedicated endpoint update request.

​
name
string | null

The name of the endpoint.

​
advanced
object | null

The advanced configuration of the endpoint. Endpoint advanced config.

​
simplescale
object | null

The simple scaling configuration of the endpoint. Simple scaling options.

​
autoscalingPolicy
object | null

The auto scaling configuration of the endpoint. Autoscaling policy.

​
hfModelRepo
string | null

HF ID of the model.

​
hfModelRepoRevision
string | null

HF commit hash of the model.

​
newVersionComment
string | null

Comment for the new version.

​
instanceOptionId
string | null

The ID of the instance option.

Response

Successfully updated the endpoint specification.

Dedicated endpoint specification.

​
name
string
required

The name of the endpoint.

​
gpuType
string
required

The type of GPU to use for the endpoint.

​
numGpu
integer
required

The number of GPUs to use per replica.

​
projectId
string
required

The ID of the project that owns the endpoint.

​
creatorId
string
required

The ID of the user who created the endpoint.

​
teamId
string
required

The ID of the team that owns the endpoint.

​
autoscalingMin
integer
required

The minimum number of replicas to maintain.

​
autoscalingMax
integer
required

The maximum number of replicas allowed.

​
autoscalingCooldown
integer
required

The cooldown period in seconds between scaling operations.

​
maxBatchSize
integer
required

The maximum batch size for inference requests.

​
tokenizerSkipSpecialTokens
boolean
required

Whether to skip special tokens in tokenizer output.

​
tokenizerAddSpecialTokens
boolean
required

Whether to add special tokens in tokenizer input.

​
instanceId
string | null

The ID of the instance.

​
maxInputLength
integer | null

The maximum allowed input length.

​
currReplicaCnt
integer | null

The current number of replicas.

​
desiredReplicaCnt
integer | null

The desired number of replicas.

​
updatedReplicaCnt
integer | null

The updated number of replicas.