Confidential AI API: Secure LLM Inference at Scale

Prem Router is a beta service that provides access to a curated model catalog through an OpenAI-compatible API.

Prem Router is not confidential. Do not send secrets, personal data, regulated data, or other sensitive data. Use Prem API for confidential processing.

Prem Router uses the Chat Completions API. All models accept text. Selected models accept base64 images. The model catalog and API behavior can change during the beta.

Request an API key

Contact us to request a Prem Router API key. Include Router access in your message. Store the key in an environment variable. Do not commit it to source control.

export PREM_ROUTER_API_KEY="your-api-key"

Make your first request

Python

Install the OpenAI Python SDK:

pip install openai

Create a Python file with this code:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PREM_ROUTER_API_KEY"],
    base_url="https://router.prem.io/v1",
)

response = client.chat.completions.create(
    model="kimi-k3",
    messages=[
        {
            "role": "user",
            "content": "What can you help me build?",
        }
    ],
)

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

Run the file. The response appears in your terminal.

Node.js test

Use Node.js 22 or later. Install the OpenAI JavaScript SDK:

npm install openai

Create a file named router.test.mjs:

import assert from "node:assert/strict";
import test from "node:test";
import OpenAI from "openai";

const apiKey = process.env.PREM_ROUTER_API_KEY;
if (!apiKey) {
  throw new Error("Set PREM_ROUTER_API_KEY before you run this test.");
}

const client = new OpenAI({
  apiKey,
  baseURL: "https://router.prem.io/v1",
  maxRetries: 0,
  timeout: 120_000,
});

test("Prem Router returns a chat completion", async () => {
  const response = await client.chat.completions.create({
    model: "kimi-k3",
    messages: [
      {
        role: "user",
        content: "Reply with exactly: Router is working",
      },
    ],
  });

  assert.equal(response.model, "kimi-k3");
  assert.equal(response.choices[0].message.role, "assistant");
  assert.match(response.choices[0].message.content ?? "", /\S/);
});

Run the live test:

node --test router.test.mjs

Available models

The following models are currently available:

Model ID	Family	Context window	Streaming
`kimi-k3`	Kimi	1M tokens	Optional
`qwen-3.7-max`	Qwen	1M tokens	Required
`qwen-3.7-plus`	Qwen	1M tokens	Required
`qwen-3.6-plus`	Qwen	1M tokens	Required
`qwen-3.5-9b`	Qwen	262K tokens	Optional
`deepseek-v4-pro`	DeepSeek	512K tokens	Optional

For models marked Required, set stream=True in Python or stream: true in JavaScript. Use the exact lowercase model ID in every API request. Call GET /v1/models with your API key to retrieve the current catalog; availability may change during the beta. See API capabilities for tools, structured output, reasoning controls, vision, and log probabilities.

API capabilities

Use tool calls, structured output, reasoning, vision, log probabilities, and usage reporting.

Add a custom provider

Configure Prem Router in OpenCode, Pi, and other OpenAI-compatible tools.

Get Started

Router (Beta)

Core Concepts

Handling Errors

Guides

API Reference

Billing

Support

Prem Router (Beta)

Request an API key

Make your first request

Python

Node.js test

Available models

API capabilities

Add a custom provider

​Request an API key

​Make your first request

​Python

​Node.js test

​Available models

API capabilities

Add a custom provider

Request an API key

Make your first request

Python

Node.js test

Available models