Get Deployment Shape - Fireworks AI Docs

GET

accounts

{account_id}

deploymentShapes

{deployment_shape_id}

Get Deployment Shape

curl --request GET \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id} \
  --header 'Authorization: Bearer <token>'

import requests

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

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id}', 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}/deploymentShapes/{deployment_shape_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

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

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id}")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "baseModel": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "description": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "updateTime": "2023-11-07T05:31:56Z",
  "modelType": "<string>",
  "parameterCount": "<string>",
  "acceleratorCount": 123,
  "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
  "precision": "PRECISION_UNSPECIFIED",
  "disableDeploymentSizeValidation": true,
  "enableAddons": true,
  "draftTokenCount": 123,
  "draftModel": "<string>",
  "ngramSpeculationLength": 123,
  "disableSpeculativeDecoding": true,
  "enableSessionAffinity": true,
  "numLoraDeviceCached": 123,
  "maxContextLength": 123,
  "presetType": "PRESET_TYPE_UNSPECIFIED"
}

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

deployment_shape_id

string

required

The Deployment Shape Id

Query Parameters

readMask

string

The fields to be returned in the response. If empty or "*", all fields will be returned.

skipShapeValidation

boolean

If true, returns the latest version regardless of validation status. By default, returns the latest validated version.

Response

200 - application/json

A successful response.

baseModel

string

required

Mutable, but only via UpdateDeploymentShape and only to a compatible model: one with the same model_type, parameter_count, and embedding status. The derived model_type / parameter_count fields (OUTPUT_ONLY, IMMUTABLE) are therefore preserved across a swap. Any incompatible change is rejected.

name

string

read-only

displayName

string

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

description

string

The description of the deployment shape. Must be fewer than 1000 characters long.

createTime

string<date-time>

read-only

The creation time of the deployment shape.

updateTime

string<date-time>

read-only

The update time for the deployment shape.

modelType

string

read-only

The model type of the base model.

parameterCount

string<int64>

read-only

The parameter count of the base model .

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. If not specified, the default is NVIDIA_A100_80GB.

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

disableDeploymentSizeValidation

boolean

If true, the deployment size validation is disabled.

enableAddons

boolean

If true, LORA addons are enabled for deployments created from this shape. Deprecated: set enable_addons on the deployment instead.

draftTokenCount

integer<int32>

The number of candidate tokens to generate per step for speculative decoding. Default is the base model's draft_token_count.

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. Deprecated: set default_draft_model on the base model instead.

ngramSpeculationLength

integer<int32>

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

disableSpeculativeDecoding

boolean

DEPRECATED: This field is a no-op. Speculative decoding is configured on deployment.

enableSessionAffinity

boolean

Whether to apply sticky routing based on user field.

numLoraDeviceCached

integer<int32>

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.

presetType

enum<string>

default:PRESET_TYPE_UNSPECIFIED

Type of deployment shape for different deployment configurations.

Available options:

PRESET_TYPE_UNSPECIFIED,

MINIMAL,

FAST,

THROUGHPUT,

FULL_PRECISION,

AGENTIC_CODING,

CHAT,

SUMMARIZATION,

MULTI_LORA

⌘I

Get Deployment Shape

curl --request GET \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id} \
  --header 'Authorization: Bearer <token>'

import requests

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

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id}', 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}/deploymentShapes/{deployment_shape_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

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

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id}")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "baseModel": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "description": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "updateTime": "2023-11-07T05:31:56Z",
  "modelType": "<string>",
  "parameterCount": "<string>",
  "acceleratorCount": 123,
  "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
  "precision": "PRECISION_UNSPECIFIED",
  "disableDeploymentSizeValidation": true,
  "enableAddons": true,
  "draftTokenCount": 123,
  "draftModel": "<string>",
  "ngramSpeculationLength": 123,
  "disableSpeculativeDecoding": true,
  "enableSessionAffinity": true,
  "numLoraDeviceCached": 123,
  "maxContextLength": 123,
  "presetType": "PRESET_TYPE_UNSPECIFIED"
}