---
title: "Update endpoint spec"
method: PUT
path: "/dedicated/beta/endpoint/{endpoint_id}"
tags: ["Dedicated.Endpoint"]
---

# Update endpoint spec

`PUT /dedicated/beta/endpoint/{endpoint_id}`

## Request

- Base URL: `https://api.friendli.ai`
- URL: `https://api.friendli.ai/dedicated/beta/endpoint/{endpoint_id}`
- Auth: HTTP bearer
- TypeScript: <https://skmtc.dev/friendli/apis/friendli-suite-api-reference/docs/dedicated/beta/endpoint/:endpoint_id/put.ts> (a function with typed inputs; its response is checked against the schema)

Update the specification of a specific endpoint

## Path parameters

- `endpoint_id` string, required: The ID of the endpoint

## Headers

- `X-Friendli-Team` string, nullable: ID of team to run requests as (optional parameter).

## Request body

- DedicatedEndpointUpdateBody: Dedicated endpoint update request.
  - `name` string, nullable: The name of the endpoint.
  - `advanced` EndpointAdvancedConfig: Endpoint advanced config.
    - `max_batch_size` integer, nullable
    - `tokenizer_skip_special_tokens` boolean, required
    - `tokenizer_add_special_tokens` boolean, required
    - `max_token_count` integer
    - `enable_content_logging` boolean, nullable
    - `max_input_length` integer, nullable
  - `simplescale` EndpointSimplescaleConfig: Simple scaling options.
    - `replicas` integer, required
  - `autoscalingPolicy` AutoscalingPolicy: Autoscaling policy.
    - `minReplica` integer: Setting `minReplica` to 0 allows the endpoint to sleep when idle, reducing costs. The minimum value is 0.
    - `maxReplica` integer: The maximum replicas that the endpoint can scale up to. The maximum value is 10.
    - `cooldownPeriod` integer: Determines how long the endpoint waits before scaling down after the last request.
  - `hfModelRepo` string, nullable: HF ID of the model.
  - `hfModelRepoRevision` string, nullable: HF commit hash of the model.
  - `newVersionComment` string, nullable: Comment for the new version.
  - `instanceOptionId` string, nullable: The ID of the instance option. Available options: - 1x NVIDIA A100 80GB: `ShbPuOs4tfGb` - 2x NVIDIA A100 80GB: `mrAHuYt7T40o` - 4x NVIDIA A100 80GB: `JkNob0NMdoF3` - 8x NVIDIA A100 80GB: `sYH4kHmAcA5P` - 1x NVIDIA H100: `TwD5AqnBSVN0` - 2x NVIDIA H100: `zfTutSiLn0Hq` - 4x NVIDIA H100: `lfkRz5G48REc` - 8x NVIDIA H100: `GUA4qYFmsYz8` - 1x NVIDIA H200: `LnK1wTaKc7WO` - 2x NVIDIA H200: `Tu6GjBnfHPe4` - 4x NVIDIA H200: `OhTzYtZuomzI` - 8x NVIDIA H200: `ahBzWtOuomsI` - 1x NVIDIA B200: `8GiQTLKfJNOr` - 2x NVIDIA B200: `brTZGIuYgVrs` - 4x NVIDIA B200: `AFoZMFXZnAdD` - 8x NVIDIA B200: `drbc6G9FxJWZ`

## Response `200`

Successfully updated the endpoint specification.

- DedicatedEndpointSpec: 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.
  - `instanceId` string, nullable: The ID of the instance.
  - `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.
  - `maxInputLength` integer, nullable: The maximum allowed input length.
  - `tokenizerSkipSpecialTokens` boolean, required: Whether to skip special tokens in tokenizer output.
  - `tokenizerAddSpecialTokens` boolean, required: Whether to add special tokens in tokenizer input.
  - `currReplicaCnt` integer, nullable: The current number of replicas.
  - `desiredReplicaCnt` integer, nullable: The desired number of replicas.
  - `updatedReplicaCnt` integer, nullable: The updated number of replicas.

## Other responses

- `400`: Bad Request
- `404`: Not Found
- `422`: Unprocessable Entity

---

[API](https://skmtc.dev/friendli/apis/friendli-suite-api-reference.md) - [All operations](https://skmtc.dev/friendli/apis/friendli-suite-api-reference/llms.txt) - [OpenAPI document](https://skmtc.dev/friendli/apis/friendli-suite-api-reference/revisions/38fb43993a11?raw)