Create a deployment

curl --request POST \
  --url https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "autoscaling": {
    "minReplicas": 123,
    "maxReplicas": 123,
    "scaleDownWindow": "<string>",
    "scaleUpWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "scalingMetrics": [
      {
        "name": "<string>",
        "target": 123,
        "percentile": "<string>"
      }
    ]
  },
  "modelId": "<string>",
  "modelRevisionId": "<string>",
  "configId": "<string>",
  "model": "<string>",
  "config": "<string>",
  "enableLora": true,
  "placement": {
    "inline": {
      "regions": [
        "<string>"
      ]
    }
  }
}
'

import requests

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

payload = {
    "name": "<string>",
    "autoscaling": {
        "minReplicas": 123,
        "maxReplicas": 123,
        "scaleDownWindow": "<string>",
        "scaleUpWindow": "<string>",
        "scaleToZeroWindow": "<string>",
        "scalingMetrics": [
            {
                "name": "<string>",
                "target": 123,
                "percentile": "<string>"
            }
        ]
    },
    "modelId": "<string>",
    "modelRevisionId": "<string>",
    "configId": "<string>",
    "model": "<string>",
    "config": "<string>",
    "enableLora": True,
    "placement": { "inline": { "regions": ["<string>"] } }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    autoscaling: {
      minReplicas: 123,
      maxReplicas: 123,
      scaleDownWindow: '<string>',
      scaleUpWindow: '<string>',
      scaleToZeroWindow: '<string>',
      scalingMetrics: [{name: '<string>', target: 123, percentile: '<string>'}]
    },
    modelId: '<string>',
    modelRevisionId: '<string>',
    configId: '<string>',
    model: '<string>',
    config: '<string>',
    enableLora: true,
    placement: {inline: {regions: ['<string>']}}
  })
};

fetch('https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'autoscaling' => [
        'minReplicas' => 123,
        'maxReplicas' => 123,
        'scaleDownWindow' => '<string>',
        'scaleUpWindow' => '<string>',
        'scaleToZeroWindow' => '<string>',
        'scalingMetrics' => [
                [
                                'name' => '<string>',
                                'target' => 123,
                                'percentile' => '<string>'
                ]
        ]
    ],
    'modelId' => '<string>',
    'modelRevisionId' => '<string>',
    'configId' => '<string>',
    'model' => '<string>',
    'config' => '<string>',
    'enableLora' => true,
    'placement' => [
        'inline' => [
                'regions' => [
                                '<string>'
                ]
        ]
    ]
  ]),
  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/{endpointId}/deployments"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"autoscaling\": {\n    \"minReplicas\": 123,\n    \"maxReplicas\": 123,\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"scalingMetrics\": [\n      {\n        \"name\": \"<string>\",\n        \"target\": 123,\n        \"percentile\": \"<string>\"\n      }\n    ]\n  },\n  \"modelId\": \"<string>\",\n  \"modelRevisionId\": \"<string>\",\n  \"configId\": \"<string>\",\n  \"model\": \"<string>\",\n  \"config\": \"<string>\",\n  \"enableLora\": true,\n  \"placement\": {\n    \"inline\": {\n      \"regions\": [\n        \"<string>\"\n      ]\n    }\n  }\n}")

	req, _ := http.NewRequest("POST", 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.post("https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"autoscaling\": {\n    \"minReplicas\": 123,\n    \"maxReplicas\": 123,\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"scalingMetrics\": [\n      {\n        \"name\": \"<string>\",\n        \"target\": 123,\n        \"percentile\": \"<string>\"\n      }\n    ]\n  },\n  \"modelId\": \"<string>\",\n  \"modelRevisionId\": \"<string>\",\n  \"configId\": \"<string>\",\n  \"model\": \"<string>\",\n  \"config\": \"<string>\",\n  \"enableLora\": true,\n  \"placement\": {\n    \"inline\": {\n      \"regions\": [\n        \"<string>\"\n      ]\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"autoscaling\": {\n    \"minReplicas\": 123,\n    \"maxReplicas\": 123,\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"scalingMetrics\": [\n      {\n        \"name\": \"<string>\",\n        \"target\": 123,\n        \"percentile\": \"<string>\"\n      }\n    ]\n  },\n  \"modelId\": \"<string>\",\n  \"modelRevisionId\": \"<string>\",\n  \"configId\": \"<string>\",\n  \"model\": \"<string>\",\n  \"config\": \"<string>\",\n  \"enableLora\": true,\n  \"placement\": {\n    \"inline\": {\n      \"regions\": [\n        \"<string>\"\n      ]\n    }\n  }\n}"

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

{
  "id": "<string>",
  "projectId": "<string>",
  "endpointId": "<string>",
  "name": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "updatedAt": "2023-11-07T05:31:56Z",
  "modelId": "<string>",
  "modelRevisionId": "<string>",
  "model": "<string>",
  "autoscaling": {
    "minReplicas": 123,
    "maxReplicas": 123,
    "scaleDownWindow": "<string>",
    "scaleUpWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "scalingMetrics": [
      {
        "name": "<string>",
        "target": 123,
        "percentile": "<string>"
      }
    ]
  },
  "configId": "<string>",
  "config": "<string>",
  "etag": "<string>",
  "hardware": "<string>",
  "status": {
    "message": "<string>",
    "readyReplicas": 123,
    "scheduledReplicas": 123
  },
  "speculatorId": "<string>",
  "speculatorRevisionId": "<string>",
  "speculator": "<string>",
  "estimatedEffectiveTrafficShare": 123,
  "enableLora": true,
  "runtimeInfo": {
    "engineType": "<string>",
    "engineVersion": "<string>",
    "functionCallingSupported": true,
    "structuredOutputSupported": true
  },
  "desiredReplicas": 123,
  "placement": {
    "inline": {
      "regions": [
        "<string>"
      ]
    }
  }
}

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

POST

projects

{projectId}

endpoints

{endpointId}

deployments

Create a deployment

curl --request POST \
  --url https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "autoscaling": {
    "minReplicas": 123,
    "maxReplicas": 123,
    "scaleDownWindow": "<string>",
    "scaleUpWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "scalingMetrics": [
      {
        "name": "<string>",
        "target": 123,
        "percentile": "<string>"
      }
    ]
  },
  "modelId": "<string>",
  "modelRevisionId": "<string>",
  "configId": "<string>",
  "model": "<string>",
  "config": "<string>",
  "enableLora": true,
  "placement": {
    "inline": {
      "regions": [
        "<string>"
      ]
    }
  }
}
'

import requests

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

payload = {
    "name": "<string>",
    "autoscaling": {
        "minReplicas": 123,
        "maxReplicas": 123,
        "scaleDownWindow": "<string>",
        "scaleUpWindow": "<string>",
        "scaleToZeroWindow": "<string>",
        "scalingMetrics": [
            {
                "name": "<string>",
                "target": 123,
                "percentile": "<string>"
            }
        ]
    },
    "modelId": "<string>",
    "modelRevisionId": "<string>",
    "configId": "<string>",
    "model": "<string>",
    "config": "<string>",
    "enableLora": True,
    "placement": { "inline": { "regions": ["<string>"] } }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    autoscaling: {
      minReplicas: 123,
      maxReplicas: 123,
      scaleDownWindow: '<string>',
      scaleUpWindow: '<string>',
      scaleToZeroWindow: '<string>',
      scalingMetrics: [{name: '<string>', target: 123, percentile: '<string>'}]
    },
    modelId: '<string>',
    modelRevisionId: '<string>',
    configId: '<string>',
    model: '<string>',
    config: '<string>',
    enableLora: true,
    placement: {inline: {regions: ['<string>']}}
  })
};

fetch('https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'autoscaling' => [
        'minReplicas' => 123,
        'maxReplicas' => 123,
        'scaleDownWindow' => '<string>',
        'scaleUpWindow' => '<string>',
        'scaleToZeroWindow' => '<string>',
        'scalingMetrics' => [
                [
                                'name' => '<string>',
                                'target' => 123,
                                'percentile' => '<string>'
                ]
        ]
    ],
    'modelId' => '<string>',
    'modelRevisionId' => '<string>',
    'configId' => '<string>',
    'model' => '<string>',
    'config' => '<string>',
    'enableLora' => true,
    'placement' => [
        'inline' => [
                'regions' => [
                                '<string>'
                ]
        ]
    ]
  ]),
  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/{endpointId}/deployments"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"autoscaling\": {\n    \"minReplicas\": 123,\n    \"maxReplicas\": 123,\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"scalingMetrics\": [\n      {\n        \"name\": \"<string>\",\n        \"target\": 123,\n        \"percentile\": \"<string>\"\n      }\n    ]\n  },\n  \"modelId\": \"<string>\",\n  \"modelRevisionId\": \"<string>\",\n  \"configId\": \"<string>\",\n  \"model\": \"<string>\",\n  \"config\": \"<string>\",\n  \"enableLora\": true,\n  \"placement\": {\n    \"inline\": {\n      \"regions\": [\n        \"<string>\"\n      ]\n    }\n  }\n}")

	req, _ := http.NewRequest("POST", 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.post("https://api.together.ai/v2/projects/{projectId}/endpoints/{endpointId}/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"autoscaling\": {\n    \"minReplicas\": 123,\n    \"maxReplicas\": 123,\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"scalingMetrics\": [\n      {\n        \"name\": \"<string>\",\n        \"target\": 123,\n        \"percentile\": \"<string>\"\n      }\n    ]\n  },\n  \"modelId\": \"<string>\",\n  \"modelRevisionId\": \"<string>\",\n  \"configId\": \"<string>\",\n  \"model\": \"<string>\",\n  \"config\": \"<string>\",\n  \"enableLora\": true,\n  \"placement\": {\n    \"inline\": {\n      \"regions\": [\n        \"<string>\"\n      ]\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"autoscaling\": {\n    \"minReplicas\": 123,\n    \"maxReplicas\": 123,\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"scalingMetrics\": [\n      {\n        \"name\": \"<string>\",\n        \"target\": 123,\n        \"percentile\": \"<string>\"\n      }\n    ]\n  },\n  \"modelId\": \"<string>\",\n  \"modelRevisionId\": \"<string>\",\n  \"configId\": \"<string>\",\n  \"model\": \"<string>\",\n  \"config\": \"<string>\",\n  \"enableLora\": true,\n  \"placement\": {\n    \"inline\": {\n      \"regions\": [\n        \"<string>\"\n      ]\n    }\n  }\n}"

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

{
  "id": "<string>",
  "projectId": "<string>",
  "endpointId": "<string>",
  "name": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "updatedAt": "2023-11-07T05:31:56Z",
  "modelId": "<string>",
  "modelRevisionId": "<string>",
  "model": "<string>",
  "autoscaling": {
    "minReplicas": 123,
    "maxReplicas": 123,
    "scaleDownWindow": "<string>",
    "scaleUpWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "scalingMetrics": [
      {
        "name": "<string>",
        "target": 123,
        "percentile": "<string>"
      }
    ]
  },
  "configId": "<string>",
  "config": "<string>",
  "etag": "<string>",
  "hardware": "<string>",
  "status": {
    "message": "<string>",
    "readyReplicas": 123,
    "scheduledReplicas": 123
  },
  "speculatorId": "<string>",
  "speculatorRevisionId": "<string>",
  "speculator": "<string>",
  "estimatedEffectiveTrafficShare": 123,
  "enableLora": true,
  "runtimeInfo": {
    "engineType": "<string>",
    "engineVersion": "<string>",
    "functionCallingSupported": true,
    "structuredOutputSupported": true
  },
  "desiredReplicas": 123,
  "placement": {
    "inline": {
      "regions": [
        "<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

ID of the project that owns the endpoint.

endpointId

string

required

ID of the endpoint that will contain the deployment.

Query Parameters

validateOnly

boolean

When true, validates the request without creating or provisioning a deployment.

Body

application/json

Configuration for creating a deployment that binds a model and immutable config to an endpoint.

name

string

required

Name for the deployment within its endpoint. Returned as a project- and endpoint-qualified inference name.

autoscaling

object

required

Autoscaling configuration for the deployment.

Show child attributes

modelId

string

Deprecated. Use model. Model identifier to serve, accepted when model is unset.

modelRevisionId

string

Deprecated. Use model with a /revisions/{revisionId} segment. If omitted, the latest revision is resolved at creation.

configId

string

Deprecated. Use config. Config revision identifier to deploy, accepted when config is unset.

model

string

Model resource name in the form projects/{projectId}/models/{modelId}[/revisions/{revisionId}]. Omit the revision segment to pin the latest revision at creation time.

config

string

Immutable config revision in the form projects/{projectId}/configs/{configRevisionId}. The config must be compatible with the model.

enableLora

boolean

Enables dynamic loading of LoRA adapters on the deployment.

placement

object

Placement policy to use when scheduling the deployment.

Option 1
Option 2

Show child attributes

Response

Serving workload that binds a model and immutable config to an endpoint and manages its replicas.

string

required

read-only

Unique deployment identifier.

projectId

string

required

read-only

ID of the project that owns the deployment.

endpointId

string

required

ID of the endpoint that contains the deployment.

name

string

required

Project- and endpoint-qualified deployment name in the form <project_slug>/<endpoint_name>/<deployment_name>. Pass it as model in an inference request to target this deployment directly instead of using the endpoint's traffic split.

createdAt

string<date-time>

required

read-only

Timestamp when the deployment was created.

updatedAt

string<date-time>

required

read-only

Timestamp when the deployment was last updated.

modelId

string

required

Deprecated. Use model. Model identifier being served, populated during migration.

modelRevisionId

string

required

Deprecated. Use model with a /revisions/{revisionId} segment. Pin to a specific model revision.

model

string

required

Pinned model resource in the form projects/{projectId}/models/{modelId}/revisions/{revisionId}.

autoscaling

object

required

Replica bounds, timing windows, and metrics that control horizontal scaling.

Show child attributes

configId

string

required

Deprecated. Use config. Config revision identifier, populated during migration.

config

string

required

Immutable config revision in the form projects/{projectId}/configs/{configRevisionId}.

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.

hardware

string

required

read-only

Hardware selected by the deployment config, including GPU type and count.

trafficMode

enum<string>

required

read-only

Whether the deployment serves client-visible responses or only mirrored shadow traffic.

Available options:

TRAFFIC_MODE_LIVE,

TRAFFIC_MODE_SHADOW

status

object

required

Current lifecycle state and observed replica counts.

Show child attributes

speculatorId

string

read-only

Deprecated. Use speculator. Speculative decoding model identifier derived from the deployment config.

speculatorRevisionId

string

read-only

Deprecated. Use speculator. ID of the speculative decoding draft-model revision pinned at creation time.

speculator

string

read-only

Pinned draft-model resource used for speculative decoding, in the same form as model. Omitted when speculative decoding is disabled.

Estimated fraction in [0, 1] of endpoint traffic that reaches this deployment under the current routing configuration. Absent or unrouted deployments are 0.

enableLora

boolean

Whether the deployment can dynamically load LoRA adapters.

runtimeInfo

object

Serving engine and feature support derived from the immutable config.

Show child attributes

desiredReplicas

integer

read-only

Number of replicas the autoscaler currently wants across all regions.

placement

object

Region constraints used to schedule the deployment's replicas.

Option 1
Option 2

Show child attributes

List deployments

Get a deployment

⌘I