Amazon SageMaker Runtime

amazonaws · Cloud

Cloud No Auth Free & Open cloud

The Amazon SageMaker runtime API.

Authentication

No authentication requiredFree to use with no key needed.

Sample Requests

POST InvokeEndpoint

After you deploy a model into production using Amazon SageMaker hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint. For an overview of Amazon SageMaker, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/how-

https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations

Hover any highlighted part to learn what it does

curl -X POST "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations"

import requests
response = requests.post(
    "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations",
)
print(response.json())

const url = 'https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations';

const response = await fetch(url, {
  method: 'POST',
}); 
const data = await response.json();
console.log(data);

package main

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

func main() {
	targetURL := "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations"
	req, _ := http.NewRequest("POST", targetURL, nil)

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	body, _ := io.ReadAll(resp.Body)
	fmt.Println(string(body))
}

require "net/http"
require "json"

uri = URI("https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations")

http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = uri.scheme == "https"

req = Net::HTTP::Post.new(uri)

res = http.request(req)
puts JSON.parse(res.body)

<?php
$url = "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/invocations";
$opts = ["http" => [
    "method" => "POST",
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));

POST InvokeEndpointAsync

After you deploy a model into production using Amazon SageMaker hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint in an asynchronous manner. Inference requests sent to this API are enqueued for asynchronous processing.

https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation

Hover any highlighted part to learn what it does

Headers — extra info sent with the request

X-Amzn-SageMaker-InputLocation

example

curl -X POST "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation" \
  -H "X-Amzn-SageMaker-InputLocation: example"

import requests
headers = {
    "X-Amzn-SageMaker-InputLocation": "example"
}
response = requests.post(
    "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation",
    headers=headers,
)
print(response.json())

const url = 'https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation';

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'X-Amzn-SageMaker-InputLocation': 'example'
  },
}); 
const data = await response.json();
console.log(data);

package main

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

func main() {
	targetURL := "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation"
	req, _ := http.NewRequest("POST", targetURL, nil)
	req.Header.Set("X-Amzn-SageMaker-InputLocation", "example")

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	body, _ := io.ReadAll(resp.Body)
	fmt.Println(string(body))
}

require "net/http"
require "json"

uri = URI("https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation")

http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = uri.scheme == "https"

req = Net::HTTP::Post.new(uri)
req["X-Amzn-SageMaker-InputLocation"] = "example"

res = http.request(req)
puts JSON.parse(res.body)

<?php
$url = "https://api.apis.guru/v2/specs/amazonaws.com/runtime.sagemaker/2017-05-13/endpoints/{EndpointName}/async-invocations#X-Amzn-SageMaker-InputLocation";
$opts = ["http" => [
    "method" => "POST",
    "header" => implode("\r\n", [
        "X-Amzn-SageMaker-InputLocation: example"
    ]),
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));

Postman Setup Guide

Get Postman ↗

See official documentation for authentication and setup.

What can you build with Amazon SageMaker Runtime?

Amazon SageMaker Runtime is a Cloud API. Developers commonly use cloud APIs for:

provisioning and managing cloud infrastructure
automating deployments and container orchestration
monitoring uptime and performance metrics
managing storage buckets and databases
setting up auto-scaling and load balancing

No authentication required. This API is open — no signup or key needed. Ideal for quick prototypes and public-facing features. Amazon SageMaker Runtime is free to use, making it a low-risk choice to experiment with.

New to APIs? Read our beginner's guide

Open documentation ↗