Create Deployment

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "baseModel": "<string>",
  "displayName": "<string>",
  "description": "<string>",
  "expireTime": "2023-11-07T05:31:56Z",
  "annotations": {},
  "minReplicaCount": 123,
  "maxReplicaCount": 123,
  "maxWithRevocableReplicaCount": 123,
  "autoscalingPolicy": {
    "scaleUpWindow": "<string>",
    "scaleDownWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "loadTargets": {},
    "scalingSchedules": {}
  },
  "acceleratorCount": 123,
  "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
  "precision": "PRECISION_UNSPECIFIED",
  "maxConcurrencyPerReplica": 123,
  "enableAddons": true,
  "draftTokenCount": 123,
  "draftModel": "<string>",
  "ngramSpeculationLength": 123,
  "enableSessionAffinity": true,
  "directRouteApiKeys": [
    "<string>"
  ],
  "numPeftDeviceCached": 123,
  "directRouteType": "DIRECT_ROUTE_TYPE_UNSPECIFIED",
  "deploymentTemplate": "<string>",
  "autoTune": {
    "longPrompt": true
  },
  "placement": {
    "region": "REGION_UNSPECIFIED",
    "multiRegion": "MULTI_REGION_UNSPECIFIED",
    "regions": [
      "REGION_UNSPECIFIED"
    ]
  },
  "maxContextLength": 123,
  "disableDeploymentSizeValidation": true,
  "enableHotLoad": true,
  "hotLoadBucketType": "BUCKET_TYPE_UNSPECIFIED",
  "enableHotReloadLatestAddon": true,
  "deploymentShape": "<string>",
  "activeModelVersion": "<string>",
  "targetModelVersion": "<string>",
  "hotLoadBucketUrl": "<string>",
  "pricingPlanId": "<string>",
  "hotLoadTrainerJob": "<string>",
  "hotLoadTransitionType": "HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED",
  "preemptible": true
}
'

import requests

url = "https://api.fireworks.ai/v1/accounts/{account_id}/deployments"

payload = {
    "baseModel": "<string>",
    "displayName": "<string>",
    "description": "<string>",
    "expireTime": "2023-11-07T05:31:56Z",
    "annotations": {},
    "minReplicaCount": 123,
    "maxReplicaCount": 123,
    "maxWithRevocableReplicaCount": 123,
    "autoscalingPolicy": {
        "scaleUpWindow": "<string>",
        "scaleDownWindow": "<string>",
        "scaleToZeroWindow": "<string>",
        "loadTargets": {},
        "scalingSchedules": {}
    },
    "acceleratorCount": 123,
    "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
    "precision": "PRECISION_UNSPECIFIED",
    "maxConcurrencyPerReplica": 123,
    "enableAddons": True,
    "draftTokenCount": 123,
    "draftModel": "<string>",
    "ngramSpeculationLength": 123,
    "enableSessionAffinity": True,
    "directRouteApiKeys": ["<string>"],
    "numPeftDeviceCached": 123,
    "directRouteType": "DIRECT_ROUTE_TYPE_UNSPECIFIED",
    "deploymentTemplate": "<string>",
    "autoTune": { "longPrompt": True },
    "placement": {
        "region": "REGION_UNSPECIFIED",
        "multiRegion": "MULTI_REGION_UNSPECIFIED",
        "regions": ["REGION_UNSPECIFIED"]
    },
    "maxContextLength": 123,
    "disableDeploymentSizeValidation": True,
    "enableHotLoad": True,
    "hotLoadBucketType": "BUCKET_TYPE_UNSPECIFIED",
    "enableHotReloadLatestAddon": True,
    "deploymentShape": "<string>",
    "activeModelVersion": "<string>",
    "targetModelVersion": "<string>",
    "hotLoadBucketUrl": "<string>",
    "pricingPlanId": "<string>",
    "hotLoadTrainerJob": "<string>",
    "hotLoadTransitionType": "HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED",
    "preemptible": True
}
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({
    baseModel: '<string>',
    displayName: '<string>',
    description: '<string>',
    expireTime: '2023-11-07T05:31:56Z',
    annotations: {},
    minReplicaCount: 123,
    maxReplicaCount: 123,
    maxWithRevocableReplicaCount: 123,
    autoscalingPolicy: {
      scaleUpWindow: '<string>',
      scaleDownWindow: '<string>',
      scaleToZeroWindow: '<string>',
      loadTargets: {},
      scalingSchedules: {}
    },
    acceleratorCount: 123,
    acceleratorType: 'ACCELERATOR_TYPE_UNSPECIFIED',
    precision: 'PRECISION_UNSPECIFIED',
    maxConcurrencyPerReplica: 123,
    enableAddons: true,
    draftTokenCount: 123,
    draftModel: '<string>',
    ngramSpeculationLength: 123,
    enableSessionAffinity: true,
    directRouteApiKeys: ['<string>'],
    numPeftDeviceCached: 123,
    directRouteType: 'DIRECT_ROUTE_TYPE_UNSPECIFIED',
    deploymentTemplate: '<string>',
    autoTune: {longPrompt: true},
    placement: {
      region: 'REGION_UNSPECIFIED',
      multiRegion: 'MULTI_REGION_UNSPECIFIED',
      regions: ['REGION_UNSPECIFIED']
    },
    maxContextLength: 123,
    disableDeploymentSizeValidation: true,
    enableHotLoad: true,
    hotLoadBucketType: 'BUCKET_TYPE_UNSPECIFIED',
    enableHotReloadLatestAddon: true,
    deploymentShape: '<string>',
    activeModelVersion: '<string>',
    targetModelVersion: '<string>',
    hotLoadBucketUrl: '<string>',
    pricingPlanId: '<string>',
    hotLoadTrainerJob: '<string>',
    hotLoadTransitionType: 'HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED',
    preemptible: true
  })
};

fetch('https://api.fireworks.ai/v1/accounts/{account_id}/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.fireworks.ai/v1/accounts/{account_id}/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([
    'baseModel' => '<string>',
    'displayName' => '<string>',
    'description' => '<string>',
    'expireTime' => '2023-11-07T05:31:56Z',
    'annotations' => [
        
    ],
    'minReplicaCount' => 123,
    'maxReplicaCount' => 123,
    'maxWithRevocableReplicaCount' => 123,
    'autoscalingPolicy' => [
        'scaleUpWindow' => '<string>',
        'scaleDownWindow' => '<string>',
        'scaleToZeroWindow' => '<string>',
        'loadTargets' => [
                
        ],
        'scalingSchedules' => [
                
        ]
    ],
    'acceleratorCount' => 123,
    'acceleratorType' => 'ACCELERATOR_TYPE_UNSPECIFIED',
    'precision' => 'PRECISION_UNSPECIFIED',
    'maxConcurrencyPerReplica' => 123,
    'enableAddons' => true,
    'draftTokenCount' => 123,
    'draftModel' => '<string>',
    'ngramSpeculationLength' => 123,
    'enableSessionAffinity' => true,
    'directRouteApiKeys' => [
        '<string>'
    ],
    'numPeftDeviceCached' => 123,
    'directRouteType' => 'DIRECT_ROUTE_TYPE_UNSPECIFIED',
    'deploymentTemplate' => '<string>',
    'autoTune' => [
        'longPrompt' => true
    ],
    'placement' => [
        'region' => 'REGION_UNSPECIFIED',
        'multiRegion' => 'MULTI_REGION_UNSPECIFIED',
        'regions' => [
                'REGION_UNSPECIFIED'
        ]
    ],
    'maxContextLength' => 123,
    'disableDeploymentSizeValidation' => true,
    'enableHotLoad' => true,
    'hotLoadBucketType' => 'BUCKET_TYPE_UNSPECIFIED',
    'enableHotReloadLatestAddon' => true,
    'deploymentShape' => '<string>',
    'activeModelVersion' => '<string>',
    'targetModelVersion' => '<string>',
    'hotLoadBucketUrl' => '<string>',
    'pricingPlanId' => '<string>',
    'hotLoadTrainerJob' => '<string>',
    'hotLoadTransitionType' => 'HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED',
    'preemptible' => true
  ]),
  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.fireworks.ai/v1/accounts/{account_id}/deployments"

	payload := strings.NewReader("{\n  \"baseModel\": \"<string>\",\n  \"displayName\": \"<string>\",\n  \"description\": \"<string>\",\n  \"expireTime\": \"2023-11-07T05:31:56Z\",\n  \"annotations\": {},\n  \"minReplicaCount\": 123,\n  \"maxReplicaCount\": 123,\n  \"maxWithRevocableReplicaCount\": 123,\n  \"autoscalingPolicy\": {\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"loadTargets\": {},\n    \"scalingSchedules\": {}\n  },\n  \"acceleratorCount\": 123,\n  \"acceleratorType\": \"ACCELERATOR_TYPE_UNSPECIFIED\",\n  \"precision\": \"PRECISION_UNSPECIFIED\",\n  \"maxConcurrencyPerReplica\": 123,\n  \"enableAddons\": true,\n  \"draftTokenCount\": 123,\n  \"draftModel\": \"<string>\",\n  \"ngramSpeculationLength\": 123,\n  \"enableSessionAffinity\": true,\n  \"directRouteApiKeys\": [\n    \"<string>\"\n  ],\n  \"numPeftDeviceCached\": 123,\n  \"directRouteType\": \"DIRECT_ROUTE_TYPE_UNSPECIFIED\",\n  \"deploymentTemplate\": \"<string>\",\n  \"autoTune\": {\n    \"longPrompt\": true\n  },\n  \"placement\": {\n    \"region\": \"REGION_UNSPECIFIED\",\n    \"multiRegion\": \"MULTI_REGION_UNSPECIFIED\",\n    \"regions\": [\n      \"REGION_UNSPECIFIED\"\n    ]\n  },\n  \"maxContextLength\": 123,\n  \"disableDeploymentSizeValidation\": true,\n  \"enableHotLoad\": true,\n  \"hotLoadBucketType\": \"BUCKET_TYPE_UNSPECIFIED\",\n  \"enableHotReloadLatestAddon\": true,\n  \"deploymentShape\": \"<string>\",\n  \"activeModelVersion\": \"<string>\",\n  \"targetModelVersion\": \"<string>\",\n  \"hotLoadBucketUrl\": \"<string>\",\n  \"pricingPlanId\": \"<string>\",\n  \"hotLoadTrainerJob\": \"<string>\",\n  \"hotLoadTransitionType\": \"HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED\",\n  \"preemptible\": true\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.fireworks.ai/v1/accounts/{account_id}/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"baseModel\": \"<string>\",\n  \"displayName\": \"<string>\",\n  \"description\": \"<string>\",\n  \"expireTime\": \"2023-11-07T05:31:56Z\",\n  \"annotations\": {},\n  \"minReplicaCount\": 123,\n  \"maxReplicaCount\": 123,\n  \"maxWithRevocableReplicaCount\": 123,\n  \"autoscalingPolicy\": {\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"loadTargets\": {},\n    \"scalingSchedules\": {}\n  },\n  \"acceleratorCount\": 123,\n  \"acceleratorType\": \"ACCELERATOR_TYPE_UNSPECIFIED\",\n  \"precision\": \"PRECISION_UNSPECIFIED\",\n  \"maxConcurrencyPerReplica\": 123,\n  \"enableAddons\": true,\n  \"draftTokenCount\": 123,\n  \"draftModel\": \"<string>\",\n  \"ngramSpeculationLength\": 123,\n  \"enableSessionAffinity\": true,\n  \"directRouteApiKeys\": [\n    \"<string>\"\n  ],\n  \"numPeftDeviceCached\": 123,\n  \"directRouteType\": \"DIRECT_ROUTE_TYPE_UNSPECIFIED\",\n  \"deploymentTemplate\": \"<string>\",\n  \"autoTune\": {\n    \"longPrompt\": true\n  },\n  \"placement\": {\n    \"region\": \"REGION_UNSPECIFIED\",\n    \"multiRegion\": \"MULTI_REGION_UNSPECIFIED\",\n    \"regions\": [\n      \"REGION_UNSPECIFIED\"\n    ]\n  },\n  \"maxContextLength\": 123,\n  \"disableDeploymentSizeValidation\": true,\n  \"enableHotLoad\": true,\n  \"hotLoadBucketType\": \"BUCKET_TYPE_UNSPECIFIED\",\n  \"enableHotReloadLatestAddon\": true,\n  \"deploymentShape\": \"<string>\",\n  \"activeModelVersion\": \"<string>\",\n  \"targetModelVersion\": \"<string>\",\n  \"hotLoadBucketUrl\": \"<string>\",\n  \"pricingPlanId\": \"<string>\",\n  \"hotLoadTrainerJob\": \"<string>\",\n  \"hotLoadTransitionType\": \"HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED\",\n  \"preemptible\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.fireworks.ai/v1/accounts/{account_id}/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  \"baseModel\": \"<string>\",\n  \"displayName\": \"<string>\",\n  \"description\": \"<string>\",\n  \"expireTime\": \"2023-11-07T05:31:56Z\",\n  \"annotations\": {},\n  \"minReplicaCount\": 123,\n  \"maxReplicaCount\": 123,\n  \"maxWithRevocableReplicaCount\": 123,\n  \"autoscalingPolicy\": {\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"loadTargets\": {},\n    \"scalingSchedules\": {}\n  },\n  \"acceleratorCount\": 123,\n  \"acceleratorType\": \"ACCELERATOR_TYPE_UNSPECIFIED\",\n  \"precision\": \"PRECISION_UNSPECIFIED\",\n  \"maxConcurrencyPerReplica\": 123,\n  \"enableAddons\": true,\n  \"draftTokenCount\": 123,\n  \"draftModel\": \"<string>\",\n  \"ngramSpeculationLength\": 123,\n  \"enableSessionAffinity\": true,\n  \"directRouteApiKeys\": [\n    \"<string>\"\n  ],\n  \"numPeftDeviceCached\": 123,\n  \"directRouteType\": \"DIRECT_ROUTE_TYPE_UNSPECIFIED\",\n  \"deploymentTemplate\": \"<string>\",\n  \"autoTune\": {\n    \"longPrompt\": true\n  },\n  \"placement\": {\n    \"region\": \"REGION_UNSPECIFIED\",\n    \"multiRegion\": \"MULTI_REGION_UNSPECIFIED\",\n    \"regions\": [\n      \"REGION_UNSPECIFIED\"\n    ]\n  },\n  \"maxContextLength\": 123,\n  \"disableDeploymentSizeValidation\": true,\n  \"enableHotLoad\": true,\n  \"hotLoadBucketType\": \"BUCKET_TYPE_UNSPECIFIED\",\n  \"enableHotReloadLatestAddon\": true,\n  \"deploymentShape\": \"<string>\",\n  \"activeModelVersion\": \"<string>\",\n  \"targetModelVersion\": \"<string>\",\n  \"hotLoadBucketUrl\": \"<string>\",\n  \"pricingPlanId\": \"<string>\",\n  \"hotLoadTrainerJob\": \"<string>\",\n  \"hotLoadTransitionType\": \"HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED\",\n  \"preemptible\": true\n}"

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

{
  "baseModel": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "description": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "expireTime": "2023-11-07T05:31:56Z",
  "purgeTime": "2023-11-07T05:31:56Z",
  "deleteTime": "2023-11-07T05:31:56Z",
  "state": "STATE_UNSPECIFIED",
  "status": {
    "code": "OK",
    "message": "<string>"
  },
  "annotations": {},
  "minReplicaCount": 123,
  "maxReplicaCount": 123,
  "maxWithRevocableReplicaCount": 123,
  "desiredReplicaCount": 123,
  "replicaCount": 123,
  "autoscalingPolicy": {
    "scaleUpWindow": "<string>",
    "scaleDownWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "loadTargets": {},
    "scalingSchedules": {}
  },
  "acceleratorCount": 123,
  "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
  "precision": "PRECISION_UNSPECIFIED",
  "maxConcurrencyPerReplica": 123,
  "cluster": "<string>",
  "enableAddons": true,
  "draftTokenCount": 123,
  "draftModel": "<string>",
  "ngramSpeculationLength": 123,
  "enableSessionAffinity": true,
  "directRouteApiKeys": [
    "<string>"
  ],
  "numPeftDeviceCached": 123,
  "directRouteType": "DIRECT_ROUTE_TYPE_UNSPECIFIED",
  "directRouteHandle": "<string>",
  "deploymentTemplate": "<string>",
  "autoTune": {
    "longPrompt": true
  },
  "placement": {
    "region": "REGION_UNSPECIFIED",
    "multiRegion": "MULTI_REGION_UNSPECIFIED",
    "regions": [
      "REGION_UNSPECIFIED"
    ]
  },
  "region": "REGION_UNSPECIFIED",
  "maxContextLength": 123,
  "updateTime": "2023-11-07T05:31:56Z",
  "disableDeploymentSizeValidation": true,
  "enableHotLoad": true,
  "hotLoadBucketType": "BUCKET_TYPE_UNSPECIFIED",
  "enableHotReloadLatestAddon": true,
  "deploymentShape": "<string>",
  "activeModelVersion": "<string>",
  "targetModelVersion": "<string>",
  "replicaStats": {
    "pendingSchedulingReplicaCount": 123,
    "downloadingModelReplicaCount": 123,
    "initializingReplicaCount": 123,
    "readyReplicaCount": 123,
    "revocableReplicaCount": 123,
    "effectiveReplicaCount": 123
  },
  "hotLoadBucketUrl": "<string>",
  "pricingPlanId": "<string>",
  "hotLoadTrainerJob": "<string>",
  "hotLoadTransitionType": "HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED",
  "preemptible": true
}

POST

accounts

{account_id}

deployments

Create Deployment

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "baseModel": "<string>",
  "displayName": "<string>",
  "description": "<string>",
  "expireTime": "2023-11-07T05:31:56Z",
  "annotations": {},
  "minReplicaCount": 123,
  "maxReplicaCount": 123,
  "maxWithRevocableReplicaCount": 123,
  "autoscalingPolicy": {
    "scaleUpWindow": "<string>",
    "scaleDownWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "loadTargets": {},
    "scalingSchedules": {}
  },
  "acceleratorCount": 123,
  "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
  "precision": "PRECISION_UNSPECIFIED",
  "maxConcurrencyPerReplica": 123,
  "enableAddons": true,
  "draftTokenCount": 123,
  "draftModel": "<string>",
  "ngramSpeculationLength": 123,
  "enableSessionAffinity": true,
  "directRouteApiKeys": [
    "<string>"
  ],
  "numPeftDeviceCached": 123,
  "directRouteType": "DIRECT_ROUTE_TYPE_UNSPECIFIED",
  "deploymentTemplate": "<string>",
  "autoTune": {
    "longPrompt": true
  },
  "placement": {
    "region": "REGION_UNSPECIFIED",
    "multiRegion": "MULTI_REGION_UNSPECIFIED",
    "regions": [
      "REGION_UNSPECIFIED"
    ]
  },
  "maxContextLength": 123,
  "disableDeploymentSizeValidation": true,
  "enableHotLoad": true,
  "hotLoadBucketType": "BUCKET_TYPE_UNSPECIFIED",
  "enableHotReloadLatestAddon": true,
  "deploymentShape": "<string>",
  "activeModelVersion": "<string>",
  "targetModelVersion": "<string>",
  "hotLoadBucketUrl": "<string>",
  "pricingPlanId": "<string>",
  "hotLoadTrainerJob": "<string>",
  "hotLoadTransitionType": "HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED",
  "preemptible": true
}
'

import requests

url = "https://api.fireworks.ai/v1/accounts/{account_id}/deployments"

payload = {
    "baseModel": "<string>",
    "displayName": "<string>",
    "description": "<string>",
    "expireTime": "2023-11-07T05:31:56Z",
    "annotations": {},
    "minReplicaCount": 123,
    "maxReplicaCount": 123,
    "maxWithRevocableReplicaCount": 123,
    "autoscalingPolicy": {
        "scaleUpWindow": "<string>",
        "scaleDownWindow": "<string>",
        "scaleToZeroWindow": "<string>",
        "loadTargets": {},
        "scalingSchedules": {}
    },
    "acceleratorCount": 123,
    "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
    "precision": "PRECISION_UNSPECIFIED",
    "maxConcurrencyPerReplica": 123,
    "enableAddons": True,
    "draftTokenCount": 123,
    "draftModel": "<string>",
    "ngramSpeculationLength": 123,
    "enableSessionAffinity": True,
    "directRouteApiKeys": ["<string>"],
    "numPeftDeviceCached": 123,
    "directRouteType": "DIRECT_ROUTE_TYPE_UNSPECIFIED",
    "deploymentTemplate": "<string>",
    "autoTune": { "longPrompt": True },
    "placement": {
        "region": "REGION_UNSPECIFIED",
        "multiRegion": "MULTI_REGION_UNSPECIFIED",
        "regions": ["REGION_UNSPECIFIED"]
    },
    "maxContextLength": 123,
    "disableDeploymentSizeValidation": True,
    "enableHotLoad": True,
    "hotLoadBucketType": "BUCKET_TYPE_UNSPECIFIED",
    "enableHotReloadLatestAddon": True,
    "deploymentShape": "<string>",
    "activeModelVersion": "<string>",
    "targetModelVersion": "<string>",
    "hotLoadBucketUrl": "<string>",
    "pricingPlanId": "<string>",
    "hotLoadTrainerJob": "<string>",
    "hotLoadTransitionType": "HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED",
    "preemptible": True
}
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({
    baseModel: '<string>',
    displayName: '<string>',
    description: '<string>',
    expireTime: '2023-11-07T05:31:56Z',
    annotations: {},
    minReplicaCount: 123,
    maxReplicaCount: 123,
    maxWithRevocableReplicaCount: 123,
    autoscalingPolicy: {
      scaleUpWindow: '<string>',
      scaleDownWindow: '<string>',
      scaleToZeroWindow: '<string>',
      loadTargets: {},
      scalingSchedules: {}
    },
    acceleratorCount: 123,
    acceleratorType: 'ACCELERATOR_TYPE_UNSPECIFIED',
    precision: 'PRECISION_UNSPECIFIED',
    maxConcurrencyPerReplica: 123,
    enableAddons: true,
    draftTokenCount: 123,
    draftModel: '<string>',
    ngramSpeculationLength: 123,
    enableSessionAffinity: true,
    directRouteApiKeys: ['<string>'],
    numPeftDeviceCached: 123,
    directRouteType: 'DIRECT_ROUTE_TYPE_UNSPECIFIED',
    deploymentTemplate: '<string>',
    autoTune: {longPrompt: true},
    placement: {
      region: 'REGION_UNSPECIFIED',
      multiRegion: 'MULTI_REGION_UNSPECIFIED',
      regions: ['REGION_UNSPECIFIED']
    },
    maxContextLength: 123,
    disableDeploymentSizeValidation: true,
    enableHotLoad: true,
    hotLoadBucketType: 'BUCKET_TYPE_UNSPECIFIED',
    enableHotReloadLatestAddon: true,
    deploymentShape: '<string>',
    activeModelVersion: '<string>',
    targetModelVersion: '<string>',
    hotLoadBucketUrl: '<string>',
    pricingPlanId: '<string>',
    hotLoadTrainerJob: '<string>',
    hotLoadTransitionType: 'HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED',
    preemptible: true
  })
};

fetch('https://api.fireworks.ai/v1/accounts/{account_id}/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.fireworks.ai/v1/accounts/{account_id}/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([
    'baseModel' => '<string>',
    'displayName' => '<string>',
    'description' => '<string>',
    'expireTime' => '2023-11-07T05:31:56Z',
    'annotations' => [
        
    ],
    'minReplicaCount' => 123,
    'maxReplicaCount' => 123,
    'maxWithRevocableReplicaCount' => 123,
    'autoscalingPolicy' => [
        'scaleUpWindow' => '<string>',
        'scaleDownWindow' => '<string>',
        'scaleToZeroWindow' => '<string>',
        'loadTargets' => [
                
        ],
        'scalingSchedules' => [
                
        ]
    ],
    'acceleratorCount' => 123,
    'acceleratorType' => 'ACCELERATOR_TYPE_UNSPECIFIED',
    'precision' => 'PRECISION_UNSPECIFIED',
    'maxConcurrencyPerReplica' => 123,
    'enableAddons' => true,
    'draftTokenCount' => 123,
    'draftModel' => '<string>',
    'ngramSpeculationLength' => 123,
    'enableSessionAffinity' => true,
    'directRouteApiKeys' => [
        '<string>'
    ],
    'numPeftDeviceCached' => 123,
    'directRouteType' => 'DIRECT_ROUTE_TYPE_UNSPECIFIED',
    'deploymentTemplate' => '<string>',
    'autoTune' => [
        'longPrompt' => true
    ],
    'placement' => [
        'region' => 'REGION_UNSPECIFIED',
        'multiRegion' => 'MULTI_REGION_UNSPECIFIED',
        'regions' => [
                'REGION_UNSPECIFIED'
        ]
    ],
    'maxContextLength' => 123,
    'disableDeploymentSizeValidation' => true,
    'enableHotLoad' => true,
    'hotLoadBucketType' => 'BUCKET_TYPE_UNSPECIFIED',
    'enableHotReloadLatestAddon' => true,
    'deploymentShape' => '<string>',
    'activeModelVersion' => '<string>',
    'targetModelVersion' => '<string>',
    'hotLoadBucketUrl' => '<string>',
    'pricingPlanId' => '<string>',
    'hotLoadTrainerJob' => '<string>',
    'hotLoadTransitionType' => 'HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED',
    'preemptible' => true
  ]),
  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.fireworks.ai/v1/accounts/{account_id}/deployments"

	payload := strings.NewReader("{\n  \"baseModel\": \"<string>\",\n  \"displayName\": \"<string>\",\n  \"description\": \"<string>\",\n  \"expireTime\": \"2023-11-07T05:31:56Z\",\n  \"annotations\": {},\n  \"minReplicaCount\": 123,\n  \"maxReplicaCount\": 123,\n  \"maxWithRevocableReplicaCount\": 123,\n  \"autoscalingPolicy\": {\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"loadTargets\": {},\n    \"scalingSchedules\": {}\n  },\n  \"acceleratorCount\": 123,\n  \"acceleratorType\": \"ACCELERATOR_TYPE_UNSPECIFIED\",\n  \"precision\": \"PRECISION_UNSPECIFIED\",\n  \"maxConcurrencyPerReplica\": 123,\n  \"enableAddons\": true,\n  \"draftTokenCount\": 123,\n  \"draftModel\": \"<string>\",\n  \"ngramSpeculationLength\": 123,\n  \"enableSessionAffinity\": true,\n  \"directRouteApiKeys\": [\n    \"<string>\"\n  ],\n  \"numPeftDeviceCached\": 123,\n  \"directRouteType\": \"DIRECT_ROUTE_TYPE_UNSPECIFIED\",\n  \"deploymentTemplate\": \"<string>\",\n  \"autoTune\": {\n    \"longPrompt\": true\n  },\n  \"placement\": {\n    \"region\": \"REGION_UNSPECIFIED\",\n    \"multiRegion\": \"MULTI_REGION_UNSPECIFIED\",\n    \"regions\": [\n      \"REGION_UNSPECIFIED\"\n    ]\n  },\n  \"maxContextLength\": 123,\n  \"disableDeploymentSizeValidation\": true,\n  \"enableHotLoad\": true,\n  \"hotLoadBucketType\": \"BUCKET_TYPE_UNSPECIFIED\",\n  \"enableHotReloadLatestAddon\": true,\n  \"deploymentShape\": \"<string>\",\n  \"activeModelVersion\": \"<string>\",\n  \"targetModelVersion\": \"<string>\",\n  \"hotLoadBucketUrl\": \"<string>\",\n  \"pricingPlanId\": \"<string>\",\n  \"hotLoadTrainerJob\": \"<string>\",\n  \"hotLoadTransitionType\": \"HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED\",\n  \"preemptible\": true\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.fireworks.ai/v1/accounts/{account_id}/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"baseModel\": \"<string>\",\n  \"displayName\": \"<string>\",\n  \"description\": \"<string>\",\n  \"expireTime\": \"2023-11-07T05:31:56Z\",\n  \"annotations\": {},\n  \"minReplicaCount\": 123,\n  \"maxReplicaCount\": 123,\n  \"maxWithRevocableReplicaCount\": 123,\n  \"autoscalingPolicy\": {\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"loadTargets\": {},\n    \"scalingSchedules\": {}\n  },\n  \"acceleratorCount\": 123,\n  \"acceleratorType\": \"ACCELERATOR_TYPE_UNSPECIFIED\",\n  \"precision\": \"PRECISION_UNSPECIFIED\",\n  \"maxConcurrencyPerReplica\": 123,\n  \"enableAddons\": true,\n  \"draftTokenCount\": 123,\n  \"draftModel\": \"<string>\",\n  \"ngramSpeculationLength\": 123,\n  \"enableSessionAffinity\": true,\n  \"directRouteApiKeys\": [\n    \"<string>\"\n  ],\n  \"numPeftDeviceCached\": 123,\n  \"directRouteType\": \"DIRECT_ROUTE_TYPE_UNSPECIFIED\",\n  \"deploymentTemplate\": \"<string>\",\n  \"autoTune\": {\n    \"longPrompt\": true\n  },\n  \"placement\": {\n    \"region\": \"REGION_UNSPECIFIED\",\n    \"multiRegion\": \"MULTI_REGION_UNSPECIFIED\",\n    \"regions\": [\n      \"REGION_UNSPECIFIED\"\n    ]\n  },\n  \"maxContextLength\": 123,\n  \"disableDeploymentSizeValidation\": true,\n  \"enableHotLoad\": true,\n  \"hotLoadBucketType\": \"BUCKET_TYPE_UNSPECIFIED\",\n  \"enableHotReloadLatestAddon\": true,\n  \"deploymentShape\": \"<string>\",\n  \"activeModelVersion\": \"<string>\",\n  \"targetModelVersion\": \"<string>\",\n  \"hotLoadBucketUrl\": \"<string>\",\n  \"pricingPlanId\": \"<string>\",\n  \"hotLoadTrainerJob\": \"<string>\",\n  \"hotLoadTransitionType\": \"HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED\",\n  \"preemptible\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.fireworks.ai/v1/accounts/{account_id}/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  \"baseModel\": \"<string>\",\n  \"displayName\": \"<string>\",\n  \"description\": \"<string>\",\n  \"expireTime\": \"2023-11-07T05:31:56Z\",\n  \"annotations\": {},\n  \"minReplicaCount\": 123,\n  \"maxReplicaCount\": 123,\n  \"maxWithRevocableReplicaCount\": 123,\n  \"autoscalingPolicy\": {\n    \"scaleUpWindow\": \"<string>\",\n    \"scaleDownWindow\": \"<string>\",\n    \"scaleToZeroWindow\": \"<string>\",\n    \"loadTargets\": {},\n    \"scalingSchedules\": {}\n  },\n  \"acceleratorCount\": 123,\n  \"acceleratorType\": \"ACCELERATOR_TYPE_UNSPECIFIED\",\n  \"precision\": \"PRECISION_UNSPECIFIED\",\n  \"maxConcurrencyPerReplica\": 123,\n  \"enableAddons\": true,\n  \"draftTokenCount\": 123,\n  \"draftModel\": \"<string>\",\n  \"ngramSpeculationLength\": 123,\n  \"enableSessionAffinity\": true,\n  \"directRouteApiKeys\": [\n    \"<string>\"\n  ],\n  \"numPeftDeviceCached\": 123,\n  \"directRouteType\": \"DIRECT_ROUTE_TYPE_UNSPECIFIED\",\n  \"deploymentTemplate\": \"<string>\",\n  \"autoTune\": {\n    \"longPrompt\": true\n  },\n  \"placement\": {\n    \"region\": \"REGION_UNSPECIFIED\",\n    \"multiRegion\": \"MULTI_REGION_UNSPECIFIED\",\n    \"regions\": [\n      \"REGION_UNSPECIFIED\"\n    ]\n  },\n  \"maxContextLength\": 123,\n  \"disableDeploymentSizeValidation\": true,\n  \"enableHotLoad\": true,\n  \"hotLoadBucketType\": \"BUCKET_TYPE_UNSPECIFIED\",\n  \"enableHotReloadLatestAddon\": true,\n  \"deploymentShape\": \"<string>\",\n  \"activeModelVersion\": \"<string>\",\n  \"targetModelVersion\": \"<string>\",\n  \"hotLoadBucketUrl\": \"<string>\",\n  \"pricingPlanId\": \"<string>\",\n  \"hotLoadTrainerJob\": \"<string>\",\n  \"hotLoadTransitionType\": \"HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED\",\n  \"preemptible\": true\n}"

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

{
  "baseModel": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "description": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "expireTime": "2023-11-07T05:31:56Z",
  "purgeTime": "2023-11-07T05:31:56Z",
  "deleteTime": "2023-11-07T05:31:56Z",
  "state": "STATE_UNSPECIFIED",
  "status": {
    "code": "OK",
    "message": "<string>"
  },
  "annotations": {},
  "minReplicaCount": 123,
  "maxReplicaCount": 123,
  "maxWithRevocableReplicaCount": 123,
  "desiredReplicaCount": 123,
  "replicaCount": 123,
  "autoscalingPolicy": {
    "scaleUpWindow": "<string>",
    "scaleDownWindow": "<string>",
    "scaleToZeroWindow": "<string>",
    "loadTargets": {},
    "scalingSchedules": {}
  },
  "acceleratorCount": 123,
  "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
  "precision": "PRECISION_UNSPECIFIED",
  "maxConcurrencyPerReplica": 123,
  "cluster": "<string>",
  "enableAddons": true,
  "draftTokenCount": 123,
  "draftModel": "<string>",
  "ngramSpeculationLength": 123,
  "enableSessionAffinity": true,
  "directRouteApiKeys": [
    "<string>"
  ],
  "numPeftDeviceCached": 123,
  "directRouteType": "DIRECT_ROUTE_TYPE_UNSPECIFIED",
  "directRouteHandle": "<string>",
  "deploymentTemplate": "<string>",
  "autoTune": {
    "longPrompt": true
  },
  "placement": {
    "region": "REGION_UNSPECIFIED",
    "multiRegion": "MULTI_REGION_UNSPECIFIED",
    "regions": [
      "REGION_UNSPECIFIED"
    ]
  },
  "region": "REGION_UNSPECIFIED",
  "maxContextLength": 123,
  "updateTime": "2023-11-07T05:31:56Z",
  "disableDeploymentSizeValidation": true,
  "enableHotLoad": true,
  "hotLoadBucketType": "BUCKET_TYPE_UNSPECIFIED",
  "enableHotReloadLatestAddon": true,
  "deploymentShape": "<string>",
  "activeModelVersion": "<string>",
  "targetModelVersion": "<string>",
  "replicaStats": {
    "pendingSchedulingReplicaCount": 123,
    "downloadingModelReplicaCount": 123,
    "initializingReplicaCount": 123,
    "readyReplicaCount": 123,
    "revocableReplicaCount": 123,
    "effectiveReplicaCount": 123
  },
  "hotLoadBucketUrl": "<string>",
  "pricingPlanId": "<string>",
  "hotLoadTrainerJob": "<string>",
  "hotLoadTransitionType": "HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED",
  "preemptible": true
}

Creating a deployment with a deployment shape

Deployment shapes are pre-configured templates optimized for speed, cost, or efficiency. To create a deployment with a specific shape, pass the deploymentShape field in the request body along with baseModel. Use the Match Deployment Shape Versions endpoint to find available shapes for your model: it takes a deployment create request and returns the validated shape versions compatible with that model, ready to pass as deploymentShape.

curl -X POST "https://api.fireworks.ai/v1/accounts/YOUR_ACCOUNT_ID/deployments" \
  -H "Authorization: Bearer $FIREWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "baseModel": "accounts/fireworks/models/gpt-oss-120b",
    "deploymentShape": "accounts/fireworks/deploymentShapes/gpt-oss-120b-minimal",
    "minReplicaCount": 0,
    "maxReplicaCount": 1
  }'

When using a deployment shape, you do not need to specify activeModelVersion or targetModelVersion — the shape provides the necessary configuration.

Always pass `deploymentShape`

Shapes are validated, so the hardware, precision, and serving configuration are known to work together. Omitting deploymentShape — whether or not you set acceleratorType, acceleratorCount, or precision — creates the deployment without a shape. Deployments without a shape are the most common cause of failed deployment creations, and the unshaped path may be deprecated in the future: always pass deploymentShape. See What is a deployment shape? for how to find shapes for your model. Each model is validated only on the accelerator type, GPU count, and precision combinations covered by its shapes — many models support just one. Check Match Deployment Shape Versions before overriding acceleratorType or acceleratorCount: an unsupported combination typically fails at creation with a generic Internal error occurred message that does not name the hardware mismatch.

Authorizations

Authorization

string

header

required

Bearer authentication using your Fireworks API key. Format: Bearer <API_KEY>

Path Parameters

account_id

string

required

The Account Id

Query Parameters

disableAutoDeploy

boolean

By default, a deployment created with a currently undeployed base model will be deployed to this deployment. If true, this auto-deploy function is disabled.

disableSpeculativeDecoding

boolean

By default, a deployment will use the speculative decoding settings from the base model. If true, this will disable speculative decoding.

deploymentId

string

The ID of the deployment. If not specified, a random ID will be generated.

validateOnly

boolean

If true, this will not create the deployment, but will return the deployment that would be created.

skipShapeValidation

boolean

By default, a deployment will ensure the deployment shape provided is validated. If true, we will not require the deployment shape to be validated.

skipImageTagValidation

boolean

If true, skip the image tag policy validation that blocks certain image tags. This allows creating deployments with image tags that would otherwise be blocked.

Body

application/json

The properties of the deployment being created.

baseModel

string

required

displayName

string

Human-readable display name of the deployment. e.g. "My Deployment" Must be fewer than 64 characters long.

description

string

Description of the deployment.

expireTime

string<date-time>

Deprecated: This field is deprecated and no longer causes auto-deletion. The time at which this deployment will automatically be deleted.

annotations

object

Annotations to identify deployment properties. Key/value pairs may be used by external tools or other services. Customer-managed keys supplied during deployment creation must begin with "custom/"; bare keys return HTTP 403 (PERMISSION_DENIED). See Deployment Tags for tag management and migration guidance. Responses to regular account users include only customer-owned tags with keys under the "custom/" prefix.

Show child attributes

minReplicaCount

integer<int32>

The minimum number of replicas. If not specified, the default is 0.

maxReplicaCount

integer<int32>

The maximum number of replicas. If not specified, the default is max(min_replica_count, 1). May be set to 0 to downscale the deployment to 0.

maxWithRevocableReplicaCount

integer<int32>

max_with_revocable_replica_count is max replica count including revocable capacity. The max revocable capacity will be max_with_revocable_replica_count - max_replica_count.

autoscalingPolicy

object

Show child attributes

acceleratorCount

integer<int32>

The number of accelerators used per replica. If not specified, the default is the estimated minimum required by the base model.

acceleratorType

enum<string>

default:ACCELERATOR_TYPE_UNSPECIFIED

The type of accelerator to use.

Available options:

ACCELERATOR_TYPE_UNSPECIFIED,

NVIDIA_A100_80GB,

NVIDIA_H100_80GB,

AMD_MI300X_192GB,

NVIDIA_A10G_24GB,

NVIDIA_A100_40GB,

NVIDIA_L4_24GB,

NVIDIA_H200_141GB,

NVIDIA_B200_180GB,

AMD_MI325X_256GB,

AMD_MI350X_288GB,

NVIDIA_B300_288GB,

NVIDIA_GB200,

NVIDIA_GB300

precision

enum<string>

default:PRECISION_UNSPECIFIED

The precision with which the model should be served.

Available options:

PRECISION_UNSPECIFIED,

FP16,

FP8,

FP8_MM,

FP8_AR,

FP8_MM_KV_ATTN,

FP8_KV,

FP8_MM_V2,

FP8_V2,

FP8_MM_KV_ATTN_V2,

NF4,

FP4,

BF16,

FP4_BLOCKSCALED_MM,

FP4_MX_MOE

maxConcurrencyPerReplica

integer<int32>

The maximum number of concurrent (in-flight) requests a single replica will accept before shedding load. Requests that arrive while a replica is already at this limit are rejected early with HTTP 429 instead of queueing — a per-replica admission gate for controlling tail latency. When unset (0), the platform default is used.

enableAddons

boolean

If true, PEFT addons are enabled for this deployment.

draftTokenCount

integer<int32>

The number of candidate tokens to generate per step for speculative decoding. Default is the base model's draft_token_count. Set CreateDeploymentRequest.disable_speculative_decoding to false to disable this behavior.

draftModel

string

The draft model name for speculative decoding. e.g. accounts/fireworks/models/my-draft-model If empty, speculative decoding using a draft model is disabled. Default is the base model's default_draft_model. Set CreateDeploymentRequest.disable_speculative_decoding to false to disable this behavior.

ngramSpeculationLength

integer<int32>

The length of previous input sequence to be considered for N-gram speculation.

enableSessionAffinity

boolean

Whether to apply sticky routing based on user field. Serverless will be set to true when creating deployment.

directRouteApiKeys

string[]

The set of API keys used to access the direct route deployment. If direct routing is not enabled, this field is unused.

numPeftDeviceCached

integer<int32>

directRouteType

enum<string>

default:DIRECT_ROUTE_TYPE_UNSPECIFIED

If set, this deployment will expose an endpoint that bypasses the Fireworks API gateway.

Available options:

DIRECT_ROUTE_TYPE_UNSPECIFIED,

INTERNET,

GCP_PRIVATE_SERVICE_CONNECT,

AWS_PRIVATELINK

deploymentTemplate

string

The name of the deployment template to use for this deployment. Only available to enterprise accounts.

autoTune

object

The performance profile to use for this deployment.

Show child attributes

placement

object

The desired geographic region where the deployment must be placed. If unspecified, the default is the GLOBAL multi-region.

Show child attributes

maxContextLength

integer<int32>

The maximum context length supported by the model (context window). If set to 0 or not specified, the model's default maximum context length will be used.

disableDeploymentSizeValidation

boolean

Whether the deployment size validation is disabled.

enableHotLoad

boolean

Whether to use hot load for this deployment.

hotLoadBucketType

enum<string>

default:BUCKET_TYPE_UNSPECIFIED

Available options:

BUCKET_TYPE_UNSPECIFIED,

MINIO,

S3,

NEBIUS,

FW_HOSTED

enableHotReloadLatestAddon

boolean

Allows up to 1 addon at a time to be loaded, and will merge it into the base model.

deploymentShape

string

The name of the deployment shape that this deployment is using. On the server side, this will be replaced with the deployment shape version name.

activeModelVersion

string

The model version that is currently active and applied to running replicas of a deployment.

targetModelVersion

string

The target model version that is being rolled out to the deployment. In a ready steady state, the target model version is the same as the active model version.

hotLoadBucketUrl

string

pricingPlanId

string

Optional pricing plan ID for custom billing configuration. If set, this deployment will use the pricing plan's billing rules instead of default billing behavior.

hotLoadTrainerJob

string

hotLoadTransitionType

enum<string>

default:HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED

Controls hot-load reload semantics for this deployment. ASYNC (default when enable_hot_load is set) pauses the generator/prefiller mid-flight and skips draining in-flight requests during hot load. SYNC drains in-flight requests before applying the new model.

Available options:

HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED,

ASYNC,

SYNC

preemptible

boolean

When true, this deployment runs as preemptible.

Response

200 - application/json

A successful response.

baseModel

string

required

name

string

read-only

displayName

string

Human-readable display name of the deployment. e.g. "My Deployment" Must be fewer than 64 characters long.

description

string

Description of the deployment.

createTime

string<date-time>

read-only

The creation time of the deployment.

expireTime

string<date-time>

Deprecated: This field is deprecated and no longer causes auto-deletion. The time at which this deployment will automatically be deleted.

purgeTime

string<date-time>

read-only

The time at which the resource will be hard deleted.

deleteTime

string<date-time>

read-only

The time at which the resource will be soft deleted.

state

enum<string>

default:STATE_UNSPECIFIED

read-only

The state of the deployment.

Available options:

STATE_UNSPECIFIED,

CREATING,

READY,

DELETING,

FAILED,

UPDATING,

DELETED

status

Mimics [https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto] · object

read-only

Detailed status information regarding the most recent operation.

Show child attributes

annotations

object

Show child attributes

minReplicaCount

integer<int32>

The minimum number of replicas. If not specified, the default is 0.

maxReplicaCount

integer<int32>

The maximum number of replicas. If not specified, the default is max(min_replica_count, 1). May be set to 0 to downscale the deployment to 0.

maxWithRevocableReplicaCount

integer<int32>

max_with_revocable_replica_count is max replica count including revocable capacity. The max revocable capacity will be max_with_revocable_replica_count - max_replica_count.

desiredReplicaCount

integer<int32>

read-only

The desired number of replicas for this deployment. This represents the target replica count that the system is trying to achieve.

replicaCount

integer<int32>

read-only

autoscalingPolicy

object

Show child attributes

acceleratorCount

integer<int32>

The number of accelerators used per replica. If not specified, the default is the estimated minimum required by the base model.

acceleratorType

enum<string>

default:ACCELERATOR_TYPE_UNSPECIFIED

The type of accelerator to use.

Available options:

ACCELERATOR_TYPE_UNSPECIFIED,

NVIDIA_A100_80GB,

NVIDIA_H100_80GB,

AMD_MI300X_192GB,

NVIDIA_A10G_24GB,

NVIDIA_A100_40GB,

NVIDIA_L4_24GB,

NVIDIA_H200_141GB,

NVIDIA_B200_180GB,

AMD_MI325X_256GB,

AMD_MI350X_288GB,

NVIDIA_B300_288GB,

NVIDIA_GB200,

NVIDIA_GB300

precision

enum<string>

default:PRECISION_UNSPECIFIED

The precision with which the model should be served.

Available options:

PRECISION_UNSPECIFIED,

FP16,

FP8,

FP8_MM,

FP8_AR,

FP8_MM_KV_ATTN,

FP8_KV,

FP8_MM_V2,

FP8_V2,

FP8_MM_KV_ATTN_V2,

NF4,

FP4,

BF16,

FP4_BLOCKSCALED_MM,

FP4_MX_MOE

maxConcurrencyPerReplica

integer<int32>

cluster

string

read-only

If set, this deployment is deployed to a cloud-premise cluster.

enableAddons

boolean

If true, PEFT addons are enabled for this deployment.

draftTokenCount

integer<int32>

draftModel

string

ngramSpeculationLength

integer<int32>

The length of previous input sequence to be considered for N-gram speculation.

enableSessionAffinity

boolean

Whether to apply sticky routing based on user field. Serverless will be set to true when creating deployment.

directRouteApiKeys

string[]

The set of API keys used to access the direct route deployment. If direct routing is not enabled, this field is unused.

numPeftDeviceCached

integer<int32>

directRouteType

enum<string>

default:DIRECT_ROUTE_TYPE_UNSPECIFIED

If set, this deployment will expose an endpoint that bypasses the Fireworks API gateway.

Available options:

DIRECT_ROUTE_TYPE_UNSPECIFIED,

INTERNET,

GCP_PRIVATE_SERVICE_CONNECT,

AWS_PRIVATELINK

directRouteHandle

string

read-only

The handle for calling a direct route. The meaning of the handle depends on the direct route type of the deployment: INTERNET -> The host name for accessing the deployment GCP_PRIVATE_SERVICE_CONNECT -> The service attachment name used to create the PSC endpoint. AWS_PRIVATELINK -> The service name used to create the VPC endpoint.

deploymentTemplate

string

The name of the deployment template to use for this deployment. Only available to enterprise accounts.

autoTune

object

The performance profile to use for this deployment.

Show child attributes

placement

object

The desired geographic region where the deployment must be placed. If unspecified, the default is the GLOBAL multi-region.

Show child attributes

region

enum<string>

default:REGION_UNSPECIFIED

read-only

The geographic region where the deployment is presently located. This region may change over time, but within the placement constraint.

Available options:

REGION_UNSPECIFIED,

US_IOWA_1,

US_VIRGINIA_1,

US_VIRGINIA_2,

US_ILLINOIS_1,

AP_TOKYO_1,

US_ARIZONA_1,

US_TEXAS_1,

US_ILLINOIS_2,

EU_FRANKFURT_1,

US_TEXAS_2,

EU_ICELAND_1,

EU_ICELAND_2,

US_WASHINGTON_1,

US_WASHINGTON_2,

US_WASHINGTON_3,

AP_TOKYO_2,

US_CALIFORNIA_1,

US_UTAH_1,

US_ARIZONA_3,

US_GEORGIA_1,

US_GEORGIA_2,

US_WASHINGTON_4,

US_GEORGIA_3,

NA_BRITISHCOLUMBIA_1,

US_GEORGIA_4,

US_OHIO_1,

US_NEWYORK_1,

EU_NETHERLANDS_1,

US_WASHINGTON_5,

US_MINNESOTA_1,

US_CALIFORNIA_2,

NA_BRITISHCOLUMBIA_2,

AP_MALAYSIA_2,

US_OREGON_1,

NA_BRITISHCOLUMBIA_3,

AP_NEWSOUTHWALES_1,

AP_TAIWAN_1

maxContextLength

integer<int32>

The maximum context length supported by the model (context window). If set to 0 or not specified, the model's default maximum context length will be used.

updateTime

string<date-time>

read-only

The update time for the deployment.

disableDeploymentSizeValidation

boolean

Whether the deployment size validation is disabled.

enableHotLoad

boolean

Whether to use hot load for this deployment.

hotLoadBucketType

enum<string>

default:BUCKET_TYPE_UNSPECIFIED

Available options:

BUCKET_TYPE_UNSPECIFIED,

MINIO,

S3,

NEBIUS,

FW_HOSTED

enableHotReloadLatestAddon

boolean

Allows up to 1 addon at a time to be loaded, and will merge it into the base model.

deploymentShape

string

The name of the deployment shape that this deployment is using. On the server side, this will be replaced with the deployment shape version name.

activeModelVersion

string

The model version that is currently active and applied to running replicas of a deployment.

targetModelVersion

string

The target model version that is being rolled out to the deployment. In a ready steady state, the target model version is the same as the active model version.

replicaStats

object

read-only

Per-replica deployment status counters. Provides visibility into the deployment process by tracking replicas in different stages of the deployment lifecycle.

Show child attributes

hotLoadBucketUrl

string

pricingPlanId

string

Optional pricing plan ID for custom billing configuration. If set, this deployment will use the pricing plan's billing rules instead of default billing behavior.

hotLoadTrainerJob

string

hotLoadTransitionType

enum<string>

default:HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED

Available options:

HOT_LOAD_TRANSITION_TYPE_UNSPECIFIED,

ASYNC,

SYNC

preemptible

boolean

When true, this deployment runs as preemptible.

⌘I

API Reference

Inference

Deployments

Training

Training SDK

Evals

Admin

Create Deployment

Creating a deployment with a deployment shape

Always pass `deploymentShape`

Authorizations

Path Parameters

Query Parameters

Body

Response

​Creating a deployment with a deployment shape

​Always pass deploymentShape

Authorizations

Path Parameters

Query Parameters

Body

Response

Creating a deployment with a deployment shape

Always pass `deploymentShape`