List custom models

curl --request GET \
  --url https://api.egp.scale.com/v5/models \
  --header 'x-api-key: <api-key>'

const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};

fetch('https://api.egp.scale.com/v5/models', 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.egp.scale.com/v5/models",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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.egp.scale.com/v5/models"

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

	req.Header.Add("x-api-key", "<api-key>")

	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.egp.scale.com/v5/models")

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

request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'

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

{
  "items": [
    {
      "id": "<string>",
      "name": "<string>",
      "model_type": "generic",
      "model_vendor": "openai",
      "status": "failed",
      "created_at": "2023-11-07T05:31:56Z",
      "created_by_user_id": "<string>",
      "created_by_identity_type": "user",
      "object": "model",
      "vendor_configuration": {
        "model_image": {
          "registry": "<string>",
          "repository": "<string>",
          "tag": "<string>",
          "command": [
            "<string>"
          ],
          "predict_route": "/predict",
          "streaming_predict_route": "<string>",
          "streaming_command": [
            "<string>"
          ],
          "request_schema": {},
          "response_schema": {},
          "env_vars": {},
          "readiness_delay": 120,
          "healthcheck_route": "/readyz"
        },
        "model_infra": {
          "endpoint_type": "sync",
          "cpus": 3,
          "gpus": 0,
          "gpu_type": "nvidia-tesla-t4",
          "memory": "8Gi",
          "storage": "16Gi",
          "min_workers": 0,
          "max_workers": 1,
          "per_worker": 10,
          "high_priority": false,
          "labels": {},
          "public_inference": false
        }
      },
      "status_reason": "<string>",
      "model_metadata": {},
      "model_availability": "unknown"
    }
  ],
  "total": 123,
  "has_more": true,
  "object": "list",
  "limit": 100
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Models

List custom models

List the custom model records registered in your account.

Returns a paginated list of the model records managed through this API — models your account deploys through the launch or llmengine serving vendors — optionally filtered by name and by model vendor, and scoped to the caller’s account. This is different from GET /v5/chat/completions/models, which lists the models available to invoke for chat completions; this endpoint returns the managed records along with their deployment status, not the catalog of callable completion models.

GET

models

List custom models

curl --request GET \
  --url https://api.egp.scale.com/v5/models \
  --header 'x-api-key: <api-key>'

const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};

fetch('https://api.egp.scale.com/v5/models', 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.egp.scale.com/v5/models",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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.egp.scale.com/v5/models"

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

	req.Header.Add("x-api-key", "<api-key>")

	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.egp.scale.com/v5/models")

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

request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'

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

{
  "items": [
    {
      "id": "<string>",
      "name": "<string>",
      "model_type": "generic",
      "model_vendor": "openai",
      "status": "failed",
      "created_at": "2023-11-07T05:31:56Z",
      "created_by_user_id": "<string>",
      "created_by_identity_type": "user",
      "object": "model",
      "vendor_configuration": {
        "model_image": {
          "registry": "<string>",
          "repository": "<string>",
          "tag": "<string>",
          "command": [
            "<string>"
          ],
          "predict_route": "/predict",
          "streaming_predict_route": "<string>",
          "streaming_command": [
            "<string>"
          ],
          "request_schema": {},
          "response_schema": {},
          "env_vars": {},
          "readiness_delay": 120,
          "healthcheck_route": "/readyz"
        },
        "model_infra": {
          "endpoint_type": "sync",
          "cpus": 3,
          "gpus": 0,
          "gpu_type": "nvidia-tesla-t4",
          "memory": "8Gi",
          "storage": "16Gi",
          "min_workers": 0,
          "max_workers": 1,
          "per_worker": 10,
          "high_priority": false,
          "labels": {},
          "public_inference": false
        }
      },
      "status_reason": "<string>",
      "model_metadata": {},
      "model_availability": "unknown"
    }
  ],
  "total": 123,
  "has_more": true,
  "object": "list",
  "limit": 100
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

x-api-key

string

header

required

Headers

x-selected-account-id

string | null

Query Parameters

name

string | null

model_vendor

enum<string> | null

Available options:

openai,

cohere,

vertex_ai,

anthropic,

azure,

gemini,

launch,

llmengine,

model_zoo,

bedrock,

xai,

fireworks_ai,

oci

starting_after

string | null

ending_before

string | null

limit

integer

default:100

Required range: 1 <= x <= 10000

sort_by

string | null

sort_order

enum<string> | null

default:asc

Available options:

asc,

desc

Response

Successful Response

items

Items · object[]

required

Show child attributes

total

integer

required

The total of items that match the query. This is greater than or equal to the number of items returned.

has_more

boolean

required

Whether there are more items left to be fetched.

object

string

default:list

Allowed value: "list"

limit

integer

default:100

The maximum number of items to return.

Inference

Questions

Rubrics

Vector Stores

Files

Models

Agent Configs

Datasets

Dataset Items

Evaluations

Evaluation Groups

Evaluation Charts

Evaluation Dashboards

Evaluation Items

Spans

Span Assessment

Annotation Tasks

Credentials

Agentex Cloud Build

Agentex Cloud Deploy

Agentex Agent

SGP Cloud Secrets

List custom models

Authorizations

Headers

Query Parameters

Response