Confidential AI API: Secure LLM Inference at Scale

Create chat completion (OpenAI-compatible)

curl --request POST \
  --url https://gateway.prem.io/openai/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": false,
  "provider": "<string>"
}
'

import requests

url = "https://gateway.prem.io/openai/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "stream": False,
    "provider": "<string>"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: '<string>', messages: [{}], stream: false, provider: '<string>'})
};

fetch('https://gateway.prem.io/openai/chat/completions', 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://gateway.prem.io/openai/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'stream' => false,
    'provider' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://gateway.prem.io/openai/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": false,\n  \"provider\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://gateway.prem.io/openai/chat/completions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": false,\n  \"provider\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://gateway.prem.io/openai/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": false,\n  \"provider\": \"<string>\"\n}"

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

{}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 401,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 403,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 404,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

POST

openai

chat

completions

Create chat completion (OpenAI-compatible)

curl --request POST \
  --url https://gateway.prem.io/openai/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": false,
  "provider": "<string>"
}
'

import requests

url = "https://gateway.prem.io/openai/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "stream": False,
    "provider": "<string>"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: '<string>', messages: [{}], stream: false, provider: '<string>'})
};

fetch('https://gateway.prem.io/openai/chat/completions', 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://gateway.prem.io/openai/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'stream' => false,
    'provider' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://gateway.prem.io/openai/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": false,\n  \"provider\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://gateway.prem.io/openai/chat/completions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": false,\n  \"provider\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://gateway.prem.io/openai/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": false,\n  \"provider\": \"<string>\"\n}"

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

{}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 401,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 403,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 404,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

{
  "status": 400,
  "error": "Some error message",
  "message": null,
  "env": "development",
  "log": {
    "request_id": "req_1234567890"
  },
  "support_id": "support_uuidv7-something-else",
  "data": {},
  "validator": {
    "email": "Invalid email address",
    "password": "Password is required"
  }
}

Zero Data Retention

This is the standard inference route. Prem sends the request to a trusted partner. Prem does not keep your prompts or completions, and the partner does not keep them. Your content is plaintext at the Prem API Gateway and at the partner. Use /rvenc/chat/completions for a confidential path with client-side encryption and attestation. See ZDR vs Confidential.

Base URL

Set the base URL of an OpenAI client to https://gateway.prem.io/openai. Do not add a /v1 segment.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PREM_API_KEY"],
    base_url="https://gateway.prem.io/openai",
)

response = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Streaming

Set "stream": true to get a stream of server-sent events in the OpenAI format:

stream = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Count to 10"}],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Model availability

Send a model that GET /openai/models returns for your API key. A confidential-only model returns a 400 status with this message: Model {model} is available for encrypted inference only. See Models & Pricing for the mode errors.

Authorizations

Authorization

string

header

required

Send your access token as header Authorization: Bearer {accessToken}

Authorization

string

header

required

Your API key that starts with sk_live or sk_test. You can create yours at go.prem.io/api-keys.

Body

application/json

Chat completion request in the OpenAI Chat Completions format.

model

string

required

Model name, as listed by GET /models.

messages

object[]

required

Conversation messages.

stream

boolean

default:false

If true, the response is a server-sent events stream.

provider

string

Optional. Pin the request to one of the model's configured backends. Omit to let the platform choose.

Maximum string length: 64

Pattern: ^[a-z0-9][a-z0-9-]*$

Response

A chat completion, or a server-sent events stream when stream is true.

The response is of type object.

Get Started

Zero Data Retention

Core Concepts

Handling Errors

Guides

API Reference

Billing

Support

Create chat completion (OpenAI-compatible)

Zero Data Retention

Base URL

Streaming

Model availability

Authorizations

Body

Response

​Zero Data Retention

​Base URL

​Streaming

​Model availability

Authorizations

Body

Response

Zero Data Retention

Base URL

Streaming

Model availability