Custom Vision Prediction Client
microsoft · Developer Tools
Custom Vision Prediction Client API
Authentication
Sample Requests
Classify an image and saves the result.
Hover any highlighted part to learn what it does
curl -X POST "https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/image?application=example"import requests
params = {
"application": "example"
}
response = requests.post(
"https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/image",
params=params,
)
print(response.json())const url = new URL('https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/image');
url.searchParams.set('application', 'example');
const response = await fetch(url, {
method: 'POST',
});
const data = await response.json();
console.log(data);package main
import (
"fmt"
"io"
"net/http"
"net/url"
)
func main() {
baseURL, _ := url.Parse("https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/image")
q := baseURL.Query()
q.Set("application", "example")
baseURL.RawQuery = q.Encode()
targetURL := baseURL.String()
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/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/image")
uri.query = URI.encode_www_form({
"application" => "example"
})
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/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/image?" . http_build_query([
"application" => "example"
]);
$opts = ["http" => [
"method" => "POST",
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));Classify an image url and saves the result.
Hover any highlighted part to learn what it does
curl -X POST "https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/url?application=example"import requests
params = {
"application": "example"
}
response = requests.post(
"https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/url",
params=params,
)
print(response.json())const url = new URL('https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/url');
url.searchParams.set('application', 'example');
const response = await fetch(url, {
method: 'POST',
});
const data = await response.json();
console.log(data);package main
import (
"fmt"
"io"
"net/http"
"net/url"
)
func main() {
baseURL, _ := url.Parse("https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/url")
q := baseURL.Query()
q.Set("application", "example")
baseURL.RawQuery = q.Encode()
targetURL := baseURL.String()
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/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/url")
uri.query = URI.encode_www_form({
"application" => "example"
})
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/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/classify/iterations/{publishedName}/url?" . http_build_query([
"application" => "example"
]);
$opts = ["http" => [
"method" => "POST",
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));Detect objects in an image and saves the result.
Hover any highlighted part to learn what it does
curl -X POST "https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/detect/iterations/{publishedName}/image?application=example"import requests
params = {
"application": "example"
}
response = requests.post(
"https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/detect/iterations/{publishedName}/image",
params=params,
)
print(response.json())const url = new URL('https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/detect/iterations/{publishedName}/image');
url.searchParams.set('application', 'example');
const response = await fetch(url, {
method: 'POST',
});
const data = await response.json();
console.log(data);package main
import (
"fmt"
"io"
"net/http"
"net/url"
)
func main() {
baseURL, _ := url.Parse("https://api.apis.guru/v2/specs/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/detect/iterations/{publishedName}/image")
q := baseURL.Query()
q.Set("application", "example")
baseURL.RawQuery = q.Encode()
targetURL := baseURL.String()
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/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/detect/iterations/{publishedName}/image")
uri.query = URI.encode_www_form({
"application" => "example"
})
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/microsoft.com/cognitiveservices-Prediction/3.0/{projectId}/detect/iterations/{publishedName}/image?" . http_build_query([
"application" => "example"
]);
$opts = ["http" => [
"method" => "POST",
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));Postman Setup Guide
- See official documentation for authentication and setup.
What can you build with Custom Vision Prediction Client?
Custom Vision Prediction Client is a Developer Tools API. Developers commonly use developer tools APIs for:
- automating code review and quality checks
- integrating CI/CD pipelines and build systems
- managing feature flags and A/B tests
- monitoring errors and application performance
- generating and validating test data
No authentication required. This API is open — no signup or key needed. Ideal for quick prototypes and public-facing features. Custom Vision Prediction Client is free to use, making it a low-risk choice to experiment with.
New to APIs? Read our beginner's guide