> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.milliseconds.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.milliseconds.ai/_mcp/server.

# Pick one label

POST https://api.milliseconds.ai/v1/decision-machine-1/classify
Content-Type: application/json

Picks the best label for the text and returns the full distribution. Describe labels for better accuracy.

Send `text` for one result, `texts` for a batch wrapped as `{ results: [...] }`, or `image` (one image, at most 5 MB decoded, optionally with `text`; never with `texts`). The response carries `x-input-chars` (input characters) and `x-input-tokens` (input tokens billed for this call) headers. Each item of `texts` (and each of `statements` or `questions`) counts as one request against the requests-per-minute limit.

Reference: https://docs.milliseconds.ai/api/decision-machine-1/classify

## Authentication

- `Authorization` header (bearer token, required) — A milliseconds API key, test\_sk-\{namespace}-\{entropy} or prod\_sk-\{namespace}-\{entropy}. Every /v1 route requires it.

## Request

### Body (application/json)

This endpoint expects a ClassifyRequest.

- `labels` (ClassifyRequestLabels, required) — Label names, or name -> description. Descriptions improve accuracy.
- `text` (string, optional) — The text to decide about.
- `texts` (list of string, optional) — Batch form: one result per text.
- `image` (string, optional) — One image: a `data:image/(jpeg|png|webp);base64,` URL, or bare base64 of a JPEG, PNG or WebP. 5 MB decoded at most. URLs are never fetched. May travel with `text` (extra context), never with `texts`.
- `detail` (enum, optional) — Image resolution: `low` 512 px, `medium` 768 px (default), `high` 1024 px longest edge. Higher sees more and bills more.
  - Allowed values: `low`, `medium`, `high`
- `question` (string, optional) — The question the model answers by choosing one label or level. Defaults to a generic one; a real rubric (what to look for, how to treat missing evidence) improves hard cases.

## Response

### 200

Result, or \{ results } for a batch

- `decision-machine-1_classify_Response_200`
  - ClassifyResult: ClassifyResult
  - DecisionMachine1ClassifyResponse2001

## Errors

### 400 Bad Request Error

Invalid request

- `error` (ErrorError, required)

### 502 Bad Gateway Error

Inference failed twice

- `error` (ErrorError, required)

## Types

### ClassifyRequestLabels

Label names, or name -> description. Descriptions improve accuracy.

- list of string
- map from string to string

### ClassifyResult

- `label` (string, required)
- `probability` (double, required)
- `confidence` (double, required) — 1 = one clear winner, 0 = flat
- `scores` (map from string to double, required)

### DecisionMachine1ClassifyResponse2001

- `results` (list of ClassifyResult, required)

### ErrorError

- `code` (string, required)
- `message` (string, required)

## Examples

**Request**

```json
{
  "labels": {
    "account": "Login, password, access",
    "billing": "Charges, invoices, refunds, double payments",
    "shipping": "Delivery, tracking, lost parcels"
  },
  "text": "I was charged twice for the same order and nobody answers my emails."
}
```

**Response**

```json
{
  "confidence": 0.972,
  "label": "billing",
  "probability": 0.995,
  "scores": {
    "account": 0.003,
    "billing": 0.995,
    "shipping": 0.002
  }
}
```

**SDK Code**

```python decision-machine-1_classify_example
import requests

url = "https://api.milliseconds.ai/v1/decision-machine-1/classify"

payload = {
    "labels": {
        "account": "Login, password, access",
        "billing": "Charges, invoices, refunds, double payments",
        "shipping": "Delivery, tracking, lost parcels"
    },
    "text": "I was charged twice for the same order and nobody answers my emails."
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript decision-machine-1_classify_example
const url = 'https://api.milliseconds.ai/v1/decision-machine-1/classify';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"labels":{"account":"Login, password, access","billing":"Charges, invoices, refunds, double payments","shipping":"Delivery, tracking, lost parcels"},"text":"I was charged twice for the same order and nobody answers my emails."}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go decision-machine-1_classify_example
package main

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

func main() {

	url := "https://api.milliseconds.ai/v1/decision-machine-1/classify"

	payload := strings.NewReader("{\n  \"labels\": {\n    \"account\": \"Login, password, access\",\n    \"billing\": \"Charges, invoices, refunds, double payments\",\n    \"shipping\": \"Delivery, tracking, lost parcels\"\n  },\n  \"text\": \"I was charged twice for the same order and nobody answers my emails.\"\n}")

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

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

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

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

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby decision-machine-1_classify_example
require 'uri'
require 'net/http'

url = URI("https://api.milliseconds.ai/v1/decision-machine-1/classify")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"labels\": {\n    \"account\": \"Login, password, access\",\n    \"billing\": \"Charges, invoices, refunds, double payments\",\n    \"shipping\": \"Delivery, tracking, lost parcels\"\n  },\n  \"text\": \"I was charged twice for the same order and nobody answers my emails.\"\n}"

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

```java decision-machine-1_classify_example
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.milliseconds.ai/v1/decision-machine-1/classify")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"labels\": {\n    \"account\": \"Login, password, access\",\n    \"billing\": \"Charges, invoices, refunds, double payments\",\n    \"shipping\": \"Delivery, tracking, lost parcels\"\n  },\n  \"text\": \"I was charged twice for the same order and nobody answers my emails.\"\n}")
  .asString();
```

```php decision-machine-1_classify_example
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.milliseconds.ai/v1/decision-machine-1/classify', [
  'body' => '{
  "labels": {
    "account": "Login, password, access",
    "billing": "Charges, invoices, refunds, double payments",
    "shipping": "Delivery, tracking, lost parcels"
  },
  "text": "I was charged twice for the same order and nobody answers my emails."
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp decision-machine-1_classify_example
using RestSharp;

var client = new RestClient("https://api.milliseconds.ai/v1/decision-machine-1/classify");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"labels\": {\n    \"account\": \"Login, password, access\",\n    \"billing\": \"Charges, invoices, refunds, double payments\",\n    \"shipping\": \"Delivery, tracking, lost parcels\"\n  },\n  \"text\": \"I was charged twice for the same order and nobody answers my emails.\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift decision-machine-1_classify_example
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "labels": [
    "account": "Login, password, access",
    "billing": "Charges, invoices, refunds, double payments",
    "shipping": "Delivery, tracking, lost parcels"
  ],
  "text": "I was charged twice for the same order and nobody answers my emails."
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.milliseconds.ai/v1/decision-machine-1/classify")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```