batches

Cancel a translation

Stops within one task. Work already completed is charged (credits_charged in the response, because translation that ran has a real cost); the rest of the reservation is released. The batch lands in cancelled, a terminal status of its own since 2026-09-02. It used to be reported as failed carrying error.code: "cancelled", so any count of failures silently included deliberate stops; a cancelled batch now returns no error object at all.

POST/v1/batches/{batch_id}/cancel

Request

curl --request POST \
  --url 'https://api.ai-glot.com/v1/batches/<batch_id>/cancel' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{}'

import json
import requests

url = "https://api.ai-glot.com/v1/batches/<batch_id>/cancel"
headers = {
  "Authorization": "<api-key>",
  "Content-Type": "application/json"
}
payload = json.loads("{}")

response = requests.request("POST", url, headers=headers, json=payload)
print(response.json())

const response = await fetch("https://api.ai-glot.com/v1/batches/<batch_id>/cancel", {
  method: "POST",
  headers: {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({}),
});

const data = await response.json();
console.log(data);

<?php
$client = curl_init();

curl_setopt($client, CURLOPT_URL, "https://api.ai-glot.com/v1/batches/<batch_id>/cancel");
curl_setopt($client, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($client, CURLOPT_HTTPHEADER, [
    "Authorization: <api-key>",
    "Content-Type: application/json",
]);
curl_setopt($client, CURLOPT_POSTFIELDS, "{}");
curl_setopt($client, CURLOPT_RETURNTRANSFER, true);

$response = curl_exec($client);
curl_close($client);
echo $response;

package main

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

func main() {
  req, _ := http.NewRequest("POST", "https://api.ai-glot.com/v1/batches/<batch_id>/cancel", bytes.NewBuffer([]byte("{}")))
  req.Header.Set("Authorization", "<api-key>")
  req.Header.Set("Content-Type", "application/json")
  res, _ := http.DefaultClient.Do(req)
  defer res.Body.Close()
  data, _ := io.ReadAll(res.Body)
  fmt.Println(string(data))
}

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

var request = HttpRequest.newBuilder(URI.create("https://api.ai-glot.com/v1/batches/<batch_id>/cancel"))
    .header("Authorization", "<api-key>")
    .header("Content-Type", "application/json")
    .method("POST", HttpRequest.BodyPublishers.ofString("{}"))
    .build();

var response = HttpClient.newHttpClient().send(
    request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI("https://api.ai-glot.com/v1/batches/<batch_id>/cancel")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "<api-key>"
request["Content-Type"] = "application/json"
request.body = "{}"

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == "https") do |http|
  http.request(request)
end

puts response.body

application/json

{
  "data": {
    "id": "<string>",
    "cancelled": true,
    "credits_charged": 123
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

Requires batches:write. Stops within one task rather than instantly, because a task in flight is finished rather than abandoned half-written.

What you are charged

Work already completed is charged, and the response says how much in credits_charged. The unused part of the reservation is released back to the balance.

This is not a refund policy so much as an accounting fact: translation that ran consumed model capacity. Cancelling early costs less, cancelling near the end costs nearly the full amount.

Where the translation lands

The batch ends in cancelled, which is a terminal status of its own and not a kind of failure. error.code is also "cancelled", so a caller that only reads the error still learns why.

That distinction matters when you are polling. cancelled means nothing went wrong: someone stopped the work on purpose. failed means the translation could not finish and error.code says what broke. Treat both as terminal and stop polling, but only failed is worth retrying or alerting on.

Anything the translation had already produced is not downloadable. A partial result is not a translated file, and returning one would be worse than returning nothing.

Response

application/json

Cancel a running translation

dataobjectrequired

Show child attributes

idstringrequired

cancelledbooleanrequired

credits_chargedintegerrequired

request_idstringrequired

Cancel a translation

What you are charged

Where the translation lands

Response

Use these docs with your AI tools

Query these docs via MCP

Query these docs over HTTP

Read these docs as Markdown