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,
"max_images_per_prompt": 512,
"gpu_memory_fraction": 0.735,
"max_prefill_tokens": 65792,
"kv_cache_dtype": "auto",
"enable_prefix_caching": true,
"quantization": "fp8"
},
"extra_args": [
"<string>"
],
"label": ""
}
]{
"error": "Model not found"
}Dedicated Models
Deploy Llm Presets
DeepInfra presets and mirrored vLLM recipes for hf_repo_id, told apart by
source; empty when none. Filter by gpu/engine/source.
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,
"max_images_per_prompt": 512,
"gpu_memory_fraction": 0.735,
"max_prefill_tokens": 65792,
"kv_cache_dtype": "auto",
"enable_prefix_caching": true,
"quantization": "fp8"
},
"extra_args": [
"<string>"
],
"label": ""
}
]{
"error": "Model not found"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Query Parameters
Available options:
L4-24GB, L40S-48GB, A100-80GB, H100-80GB, H200-141GB, B200-180GB, B300-270GB, RTXPRO6000-96GB, other Response
Successful Response
Preset id.
Allowed Nx configs.
Config source.
Inference engine.
Engine tuning knobs.
Show child attributes
Show child attributes
Raw engine flags; vLLM recipes only.
Short display name (e.g. "Throughput-optimized").