List model endpoints

Returns model gateway endpoints configured in the workspace. Each model represents a proxy to an external LLM provider (OpenAI, Anthropic, etc.) with unified access control. Starting with API version 2026-04-28 the response is wrapped in {data, meta} and supports cursor pagination via the cursor and limit query parameters; older versions keep returning a bare array with all models.

GET /models

List model endpoints

cURL

curl --request GET \
  --url https://api.blaxel.ai/v0/models \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.blaxel.ai/v0/models"

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

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

print(response.text)

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

fetch('https://api.blaxel.ai/v0/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.blaxel.ai/v0/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 => [
    "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.blaxel.ai/v0/models"

	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))

}

HttpResponse<String> response = Unirest.get("https://api.blaxel.ai/v0/models")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.blaxel.ai/v0/models")

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

200

{
  "data": [
    {
      "metadata": {
        "name": "my-resource",
        "createdAt": "<string>",
        "updatedAt": "<string>",
        "createdBy": "<string>",
        "updatedBy": "<string>",
        "displayName": "My Resource",
        "externalId": "my-session-123",
        "labels": {},
        "plan": "<string>",
        "url": "<string>",
        "workspace": "<string>"
      },
      "spec": {
        "enabled": true,
        "flavors": [
          {
            "name": "t4",
            "type": "cpu"
          }
        ],
        "integrationConnections": [
          "<string>"
        ],
        "policies": [
          "<string>"
        ],
        "runtime": {
          "endpointName": "<string>",
          "model": "gpt-4.1",
          "organization": "org-abc123",
          "type": "openai"
        },
        "sandbox": false
      },
      "events": [
        {
          "canaryRevision": "<string>",
          "message": "Deployment successful",
          "revision": "rev-abc123",
          "status": "DEPLOYED",
          "time": "2025-01-15T10:30:00Z",
          "type": "deployment"
        }
      ]
    }
  ],
  "meta": {
    "hasMore": true,
    "nextCursor": "<string>",
    "total": 123
  }
}

{
  "error": "Resource already exists",
  "code": 409,
  "message": "Invalid request body"
}

{
  "error": "Resource already exists",
  "code": 409,
  "message": "Invalid request body"
}

{
  "error": "Resource already exists",
  "code": 409,
  "message": "Invalid request body"
}

Authorizations

OAuth2ApiKeyAuth

Authorization · string · header · required

OAuth2 authentication with JWT tokens

Query Parameters

cursor · string

Opaque cursor returned by a previous response's meta.nextCursor. Only valid for the same query (workspace + filters); the server rejects cursors bound to a different query or older than 24h. Omit on the first page.

limit · integer · default: 50

Maximum number of items to return per page. Defaults to 50, clamped to 200.

Required range: 1 <= x <= 200

sort · enum<string>

Sort spec, formatted as <key>:<direction>. Allowed values are createdAt:desc (default), createdAt:asc, name:asc, name:desc. The cursor fingerprint is bound to the sort, so a cursor opened with one value cannot be reused with another. Only honoured starting on Blaxel-Version 2026-04-28.

Available options: createdAt:desc, createdAt:asc, name:asc, name:desc

q · string

Substring search across metadata.name, metadata.displayName and labels (keys + values). Trimmed and lowercased server-side; queries shorter than 2 characters fall back to the unfiltered listing. Bound into the cursor fingerprint so a cursor opened with one query cannot be reused with another. Only honoured starting on Blaxel-Version 2026-04-28.

Maximum string length: 200

anchor · enum<string>

Start from a known pagination boundary. end is only supported for createdAt:desc listings and returns the oldest page directly without walking every cursor from the first page.

Available options: end

Response

200

application/json

successful operation

Cursor-paginated list of model gateway endpoints. Returned starting with API version 2026-04-28; older API versions return a bare array.

data · object[]

Page of models.

Show child attributes

meta · object

Pagination metadata returned alongside a page of listing results. Always present on listing endpoints starting with API version 2026-04-28.

Show child attributes