Update an endpoint

PATCH

projects

{projectId}

endpoints

{id}

Together AI SDK (Python)

from together import Together

client = Together()
identity = client.whoami()
if identity.type != "project_api_key":
    raise RuntimeError("TOGETHER_API_KEY must be a project API key")
project_id = identity.project.id

endpoint = client.endpoints.update(
    "ep_abc123",
    project_id=project_id,
    traffic_split=[{"deployment_id": "dep_abc123", "weight": 1}],
)
print(endpoint.traffic_split)

import Together from "together-ai";

const client = new Together();
const identity = await client.whoami();
if (identity.type !== "project_api_key") {
  throw new Error("TOGETHER_API_KEY must be a project API key");
}
const projectId = identity.project.id;

const endpoint = await client.endpoints.update("ep_abc123", {
  projectId,
  trafficSplit: [{ deploymentId: "dep_abc123", weight: 1 }],
});
console.log(endpoint.trafficSplit);

import Together from "together-ai";

const client = new Together();
const identity = await client.whoami();
if (identity.type !== "project_api_key") {
  throw new Error("TOGETHER_API_KEY must be a project API key");
}
const projectId = identity.project.id;

const endpoint = await client.endpoints.update("ep_abc123", {
  projectId,
  trafficSplit: [{ deploymentId: "dep_abc123", weight: 1 }],
});
console.log(endpoint.trafficSplit);

curl --request PATCH \
  --url https://api.together.ai/v2/projects/{projectId}/endpoints/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "etag": "<string>",
  "trafficSplit": [
    {
      "deploymentId": "<string>",
      "weight": 123
    }
  ],
  "visibility": "VISIBILITY_PRIVATE"
}
'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.together.ai/v2/projects/{projectId}/endpoints/{id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'etag' => '<string>',
    'trafficSplit' => [
        [
                'deploymentId' => '<string>',
                'weight' => 123
        ]
    ],
    'visibility' => 'VISIBILITY_PRIVATE'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.together.ai/v2/projects/{projectId}/endpoints/{id}"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"etag\": \"<string>\",\n  \"trafficSplit\": [\n    {\n      \"deploymentId\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"visibility\": \"VISIBILITY_PRIVATE\"\n}")

	req, _ := http.NewRequest("PATCH", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.patch("https://api.together.ai/v2/projects/{projectId}/endpoints/{id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"etag\": \"<string>\",\n  \"trafficSplit\": [\n    {\n      \"deploymentId\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"visibility\": \"VISIBILITY_PRIVATE\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.together.ai/v2/projects/{projectId}/endpoints/{id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"etag\": \"<string>\",\n  \"trafficSplit\": [\n    {\n      \"deploymentId\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"visibility\": \"VISIBILITY_PRIVATE\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "projectId": "<string>",
  "name": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "updatedAt": "2023-11-07T05:31:56Z",
  "etag": "<string>",
  "trafficSplit": [
    {
      "deploymentId": "<string>",
      "weight": 123
    }
  ],
  "visibility": "VISIBILITY_PRIVATE",
  "endpointType": "ENDPOINT_TYPE_DEDICATED",
  "deployments": [
    {
      "id": "<string>",
      "modelId": "<string>",
      "trafficMode": "TRAFFIC_MODE_LIVE",
      "state": "DEPLOYMENT_STATE_PROVISIONING",
      "name": "<string>",
      "createdAt": "2023-11-07T05:31:56Z",
      "autoscaling": {
        "minReplicas": 123,
        "maxReplicas": 123,
        "scaleDownWindow": "<string>",
        "scaleUpWindow": "<string>",
        "scaleToZeroWindow": "<string>",
        "scalingMetrics": [
          {
            "name": "active_sessions",
            "type": "METRIC_TARGET_TYPE_VALUE",
            "target": 123,
            "percentile": "<string>"
          }
        ],
        "scaleUp": {
          "policies": [
            {
              "type": "SCALING_POLICY_TYPE_PERCENT",
              "value": 25,
              "periodSeconds": 60
            },
            {
              "type": "SCALING_POLICY_TYPE_PODS",
              "value": 10,
              "periodSeconds": 60
            }
          ],
          "selectPolicy": "SCALING_POLICY_SELECT_MIN"
        },
        "scaleDown": {
          "policies": [
            {
              "type": "SCALING_POLICY_TYPE_PERCENT",
              "value": 25,
              "periodSeconds": 60
            },
            {
              "type": "SCALING_POLICY_TYPE_PODS",
              "value": 10,
              "periodSeconds": 60
            }
          ],
          "selectPolicy": "SCALING_POLICY_SELECT_MIN"
        }
      },
      "model": "<string>",
      "estimatedEffectiveTrafficShare": 123,
      "hardware": "<string>",
      "desiredReplicas": 123,
      "readyReplicas": 123
    }
  ],
  "activeRolloutId": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": null,
    "code": null
  }
}

Authorizations

Authorization

string

header

default:default

required

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

Path Parameters

projectId

string

required

Project identifier.

string

required

Endpoint identifier.

Query Parameters

updateMask

string

Fields to update. If not set, the fields populated are updated.

Body

application/json

Mutable endpoint fields for update requests.

name

string

Updated endpoint string.

etag

string

Current endpoint version. The update is rejected if this value no longer matches.

trafficSplit

object[]

Replacement live traffic split. Use an empty list to stop routing live traffic.

Show child attributes

visibility

enum<string>

default:VISIBILITY_PRIVATE

Who can discover the endpoint. VISIBILITY_PRIVATE restricts it to the project; VISIBILITY_INTERNAL shares it with the organization.

Available options:

VISIBILITY_PRIVATE,

VISIBILITY_INTERNAL

Response

Stable inference entry point that groups deployments and routes requests among them.

string

required

read-only

Unique endpoint identifier.

projectId

string

required

read-only

ID of the project that owns the endpoint.

name

string

required

Project-qualified endpoint name in the form <project_slug>/<endpoint_name>. Pass this value as model in inference requests. Create and update requests may use either a bare endpoint name or the qualified form; a supplied project slug must match the project in the request path.

createdAt

string<date-time>

required

read-only

Timestamp when the endpoint was created.

updatedAt

string<date-time>

required

Output only. Timestamp when the endpoint was last updated.

etag

string

required

Opaque version tag for optimistic concurrency control. Supply on update/delete to ensure consistent read-modify-write. If not set, the write overwrites based on current state.

trafficSplit

object[]

required

Deployments eligible for live traffic and their capacity weights. An empty list leaves the endpoint unrouted.

Show child attributes

visibility

enum<string>

default:VISIBILITY_PRIVATE

required

Who can discover the endpoint. VISIBILITY_PRIVATE restricts it to the project; VISIBILITY_INTERNAL shares it with the organization.

Available options:

VISIBILITY_PRIVATE,

VISIBILITY_INTERNAL

endpointType

enum<string>

required

read-only

Serving class of the endpoint. Reserved endpoints use reserved capacity.

Available options:

ENDPOINT_TYPE_DEDICATED,

ENDPOINT_TYPE_SERVERLESS,

ENDPOINT_TYPE_RESERVED

deployments

object[]

required

read-only

Lightweight summaries of deployments under this endpoint. Retrieve a deployment through the endpoint's deployment API for full details.

Show child attributes

activeRolloutId

string

read-only

ID of the currently active rollout in an in-flight state, including paused.

⌘I

Together AI SDK (Python)

from together import Together

client = Together()
identity = client.whoami()
if identity.type != "project_api_key":
    raise RuntimeError("TOGETHER_API_KEY must be a project API key")
project_id = identity.project.id

endpoint = client.endpoints.update(
    "ep_abc123",
    project_id=project_id,
    traffic_split=[{"deployment_id": "dep_abc123", "weight": 1}],
)
print(endpoint.traffic_split)

import Together from "together-ai";

const client = new Together();
const identity = await client.whoami();
if (identity.type !== "project_api_key") {
  throw new Error("TOGETHER_API_KEY must be a project API key");
}
const projectId = identity.project.id;

const endpoint = await client.endpoints.update("ep_abc123", {
  projectId,
  trafficSplit: [{ deploymentId: "dep_abc123", weight: 1 }],
});
console.log(endpoint.trafficSplit);

import Together from "together-ai";

const client = new Together();
const identity = await client.whoami();
if (identity.type !== "project_api_key") {
  throw new Error("TOGETHER_API_KEY must be a project API key");
}
const projectId = identity.project.id;

const endpoint = await client.endpoints.update("ep_abc123", {
  projectId,
  trafficSplit: [{ deploymentId: "dep_abc123", weight: 1 }],
});
console.log(endpoint.trafficSplit);

curl --request PATCH \
  --url https://api.together.ai/v2/projects/{projectId}/endpoints/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "etag": "<string>",
  "trafficSplit": [
    {
      "deploymentId": "<string>",
      "weight": 123
    }
  ],
  "visibility": "VISIBILITY_PRIVATE"
}
'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.together.ai/v2/projects/{projectId}/endpoints/{id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'etag' => '<string>',
    'trafficSplit' => [
        [
                'deploymentId' => '<string>',
                'weight' => 123
        ]
    ],
    'visibility' => 'VISIBILITY_PRIVATE'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.together.ai/v2/projects/{projectId}/endpoints/{id}"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"etag\": \"<string>\",\n  \"trafficSplit\": [\n    {\n      \"deploymentId\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"visibility\": \"VISIBILITY_PRIVATE\"\n}")

	req, _ := http.NewRequest("PATCH", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.patch("https://api.together.ai/v2/projects/{projectId}/endpoints/{id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"etag\": \"<string>\",\n  \"trafficSplit\": [\n    {\n      \"deploymentId\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"visibility\": \"VISIBILITY_PRIVATE\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.together.ai/v2/projects/{projectId}/endpoints/{id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"etag\": \"<string>\",\n  \"trafficSplit\": [\n    {\n      \"deploymentId\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"visibility\": \"VISIBILITY_PRIVATE\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "projectId": "<string>",
  "name": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "updatedAt": "2023-11-07T05:31:56Z",
  "etag": "<string>",
  "trafficSplit": [
    {
      "deploymentId": "<string>",
      "weight": 123
    }
  ],
  "visibility": "VISIBILITY_PRIVATE",
  "endpointType": "ENDPOINT_TYPE_DEDICATED",
  "deployments": [
    {
      "id": "<string>",
      "modelId": "<string>",
      "trafficMode": "TRAFFIC_MODE_LIVE",
      "state": "DEPLOYMENT_STATE_PROVISIONING",
      "name": "<string>",
      "createdAt": "2023-11-07T05:31:56Z",
      "autoscaling": {
        "minReplicas": 123,
        "maxReplicas": 123,
        "scaleDownWindow": "<string>",
        "scaleUpWindow": "<string>",
        "scaleToZeroWindow": "<string>",
        "scalingMetrics": [
          {
            "name": "active_sessions",
            "type": "METRIC_TARGET_TYPE_VALUE",
            "target": 123,
            "percentile": "<string>"
          }
        ],
        "scaleUp": {
          "policies": [
            {
              "type": "SCALING_POLICY_TYPE_PERCENT",
              "value": 25,
              "periodSeconds": 60
            },
            {
              "type": "SCALING_POLICY_TYPE_PODS",
              "value": 10,
              "periodSeconds": 60
            }
          ],
          "selectPolicy": "SCALING_POLICY_SELECT_MIN"
        },
        "scaleDown": {
          "policies": [
            {
              "type": "SCALING_POLICY_TYPE_PERCENT",
              "value": 25,
              "periodSeconds": 60
            },
            {
              "type": "SCALING_POLICY_TYPE_PODS",
              "value": 10,
              "periodSeconds": 60
            }
          ],
          "selectPolicy": "SCALING_POLICY_SELECT_MIN"
        }
      },
      "model": "<string>",
      "estimatedEffectiveTrafficShare": 123,
      "hardware": "<string>",
      "desiredReplicas": 123,
      "readyReplicas": 123
    }
  ],
  "activeRolloutId": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": null,
    "code": null
  }
}

TOGETHER APIS

SDK LIBRARIES

ERROR CODES

Authorizations

Path Parameters

Query Parameters

Body

Response