inference-endpoints/pr_80/en/guides/private_link.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Create a Private Endpoint with AWS PrivateLink&quot;,&quot;local&quot;:&quot;create-a-private-endpoint-with-aws-privatelink&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/inference-endpoints/pr_80/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/entry/start.764a46f5.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/chunks/scheduler.389d799c.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/chunks/singletons.9ef40cf5.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/chunks/paths.ee77e15f.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/entry/app.020792f8.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/chunks/index.8f81d18f.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/nodes/0.bf7202c8.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/nodes/15.ca3027ea.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_80/en/_app/immutable/chunks/EditOnGithub.33306dfe.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Create a Private Endpoint with AWS PrivateLink&quot;,&quot;local&quot;:&quot;create-a-private-endpoint-with-aws-privatelink&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="create-a-private-endpoint-with-aws-privatelink" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#create-a-private-endpoint-with-aws-privatelink"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Create a Private Endpoint with AWS PrivateLink</span></h1> <p data-svelte-h="svelte-h7l3m2">Security and secure inference are key principles of Inference Endpoints. We currently offer three different levels of security: <a href="/docs/inference-endpoints/security">Public, Protected and Private</a>.</p> <p data-svelte-h="svelte-8rs0md">Public and Protected Endpoints do not require any additional configuration. But in order to create a Private Endpoint for a secure intra-region connection, you need to provide the AWS Account ID of the account which should also have access to Inference Endpoints.</p> <img src="https://raw.githubusercontent.com/huggingface/hf-endpoints-documentation/main/assets/6_private_type.png" alt="select private link"> <p data-svelte-h="svelte-1xmue9p">After you provide your AWS Account ID and click <strong>Create Endpoint</strong>, the Inference Service creates a VPC Endpoint and you should see the VPC Service Name in your overview.</p> <img src="https://raw.githubusercontent.com/huggingface/hf-endpoints-documentation/main/assets/6_service_name.png" alt="service link"> <p data-svelte-h="svelte-1066jxl">The VPC Service Name is used to create the VPC Interface Endpoint in your (customer) cloud account. Open your cloud account <a href="https://console.aws.amazon.com/vpc/home?#Endpoints" rel="nofollow">console</a> to go create the VPC Interface Endpoint.</p> <p data-svelte-h="svelte-ns5hok">An example of the VPC Endpoint configuration is shown below. You will need to select the VPC and subnets, as well as the security groups you want to use.</p> <img src="https://raw.githubusercontent.com/huggingface/hf-endpoints-documentation/main/assets/6_aws.png" alt="aws management console"> <p data-svelte-h="svelte-13vrrx">Once your Inference Endpoint is created successfully, go to the corresponding AWS account and add the VPC Endpoint as the endpoint.</p> <img src="https://raw.githubusercontent.com/huggingface/hf-endpoints-documentation/main/assets/6_private_with_url.png" alt="endpoint url"> <p data-svelte-h="svelte-643p47">After the VPC Endpoint status changes from <strong>pending</strong> to <strong>available</strong>, you should see a Endpoint URL in the overview. This URL can now be used inside your VPC to access your Endpoint in a secure and protected way, ensuring traffic is only occurring between the two endpoints and will never leave AWS.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hf-endpoints-documentation/blob/main/docs/source/guides/private_link.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1l46qe1 = {
						assets: "/docs/inference-endpoints/pr_80/en",
						base: "/docs/inference-endpoints/pr_80/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/inference-endpoints/pr_80/en/_app/immutable/entry/start.764a46f5.js"),
						import("/docs/inference-endpoints/pr_80/en/_app/immutable/entry/app.020792f8.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 15],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>