Skip to main content
GET
/
deploy
/
llm
/
presets
Deploy Llm Presets
curl --request GET \
  --url https://api.deepinfra.com/deploy/llm/presets \
  --header 'Authorization: Bearer <token>'
import requests

url = "https://api.deepinfra.com/deploy/llm/presets"

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

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

print(response.text)
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.deepinfra.com/deploy/llm/presets', 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.deepinfra.com/deploy/llm/presets",
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.deepinfra.com/deploy/llm/presets"

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.deepinfra.com/deploy/llm/presets")
.header("Authorization", "Bearer <token>")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.deepinfra.com/deploy/llm/presets")

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
[
  {
    "id": "<string>",
    "gpu_configs": [
      "<string>"
    ],
    "source": "deepinfra",
    "engine": "vllm",
    "standard_args": {
      "max_context_size": 5000000,
      "max_concurrent_requests": 512,
      "gpu_memory_fraction": 0.735,
      "max_prefill_tokens": 65792,
      "enable_prefix_caching": true
    },
    "extra_args": [
      "<string>"
    ],
    "label": ""
  }
]
{
"error": "<string>"
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

xi-api-key
string | null
x-api-key
string | null

Query Parameters

hf_repo_id
string
required
gpu
enum<string> | null
Available options:
L4-24GB,
L40S-48GB,
A100-80GB,
H100-80GB,
H200-141GB,
B200-180GB,
B300-270GB,
RTXPRO6000-96GB,
other
engine
string | null
source
string | null

Response

Successful Response

id
string
required

Preset id.

gpu_configs
string[]
required

Allowed Nx configs.

source
string
default:deepinfra

Config source.

engine
string
default:vllm

Inference engine.

standard_args
StandardArgs · object

Engine tuning knobs.

extra_args
string[] | null

Raw engine flags; vLLM recipes only.

label
string
default:""

Short display name (e.g. "Throughput-optimized").