batches

Create a translation

Send the file one of three ways: JSON with content (the file itself as UTF-8 text — text formats only, the simplest path for agents), JSON with file_url (HTTPS, fetched server-side, no redirects), or multipart/form-data with a file field (required for XLSX and ZIP). filename is optional: if omitted, a clean default name is generated and the format is inferred automatically from the content. Include instruction to get the full trust-gated plan back in the same response (takes some seconds); omit it to receive four grounded suggested_instructions and continue with the plan endpoint. Quality is chosen at approval, not here — the plan quotes both tiers. Per-format size limits are on /v1/account as entitlements.max_upload_bytes_by_format. The upload also appears in the web app.

POST/v1/batches

Request

curl --request POST \
  --url 'https://api.ai-glot.com/v1/batches' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "file_url": "<string>",
  "content": "<string>",
  "filename": "<string>",
  "instruction": "<string>"
}'

import json
import requests

url = "https://api.ai-glot.com/v1/batches"
headers = {
  "Authorization": "<api-key>",
  "Content-Type": "application/json"
}
payload = json.loads("{\"file_url\":\"<string>\",\"content\":\"<string>\",\"filename\":\"<string>\",\"instruction\":\"<string>\"}")

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

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

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

<?php
$client = curl_init();

curl_setopt($client, CURLOPT_URL, "https://api.ai-glot.com/v1/batches");
curl_setopt($client, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($client, CURLOPT_HTTPHEADER, [
    "Authorization: <api-key>",
    "Content-Type: application/json",
]);
curl_setopt($client, CURLOPT_POSTFIELDS, "{\"file_url\":\"<string>\",\"content\":\"<string>\",\"filename\":\"<string>\",\"instruction\":\"<string>\"}");
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", bytes.NewBuffer([]byte("{\"file_url\":\"<string>\",\"content\":\"<string>\",\"filename\":\"<string>\",\"instruction\":\"<string>\"}")))
  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"))
    .header("Authorization", "<api-key>")
    .header("Content-Type", "application/json")
    .method("POST", HttpRequest.BodyPublishers.ofString("{\"file_url\":\"<string>\",\"content\":\"<string>\",\"filename\":\"<string>\",\"instruction\":\"<string>\"}"))
    .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")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "<api-key>"
request["Content-Type"] = "application/json"
request.body = "{\"file_url\":\"<string>\",\"content\":\"<string>\",\"filename\":\"<string>\",\"instruction\":\"<string>\"}"

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>",
    "name": "<string>",
    "file_name": "<string>",
    "status": "analyzing",
    "quality_tier": "<string>",
    "word_count": 123,
    "credit_cost": 123,
    "is_sample": true,
    "archived": true,
    "progress": {
      "phase": "<string>",
      "percent": 123.45,
      "updated_at": "<string>",
      "estimated_seconds_remaining": 123
    },
    "error": {
      "code": "<string>",
      "message": "<string>"
    },
    "created_at": "<string>",
    "completed_at": "<string>",
    "next_action": "provide_instruction",
    "plan": {
      "instruction": "<string>",
      "summary": "<string>",
      "will_translate": "<string>",
      "will_not_touch": "<string>",
      "special_rules": [
        "<string>"
      ],
      "assumptions": [
        "<string>"
      ],
      "not_included": [
        "<string>"
      ],
      "languages": [
        {
          "source": {},
          "target": {},
          "segments": {},
          "words": {}
        }
      ],
      "totals": {
        "segments": 123,
        "words": 123,
        "files": {}
      },
      "credits": {
        "standard": 123,
        "lite": 123
      },
      "preview": [
        {
          "location": {},
          "source_text": {},
          "source_lang": {},
          "target_lang": {}
        }
      ],
      "cached": true
    },
    "suggested_instructions": [
      "<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>"
}

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

Requires batches:create. Creating a translation costs nothing: credits are reserved only when you approve a plan.

Choosing how to send the file

Three transports, and the right one depends on the format rather than on preference.

Transport	Use it for	Notes
JSON with `content`	Any text format	The file itself as UTF-8 text. The simplest path for an agent that already holds the content in memory.
JSON with `file_url`	A file already hosted	HTTPS only, fetched server-side. Redirects are not followed, so give the final URL.
`multipart/form-data`	XLSX and ZIP	Required for binary formats: they cannot survive being sent as JSON text.

filename is optional but worth sending. The extension is how the format is identified, so a name like strings.xml and a name like export.csv lead to different parsers on identical bytes.

What happens next

The response gives you a batch_id. From there the sequence is always the same:

POST /v1/batches/{batch_id}/plan: describe what to translate, in your own words.
POST /v1/batches/{batch_id}/approve: spend credits and start.
GET /v1/batches/{batch_id}: poll until it finishes.
GET /v1/batches/{batch_id}/result: collect the result. It returns a signed link, not the file itself.

Response

application/json

Create a translation from a file

dataobjectrequired

Show child attributes

idstringrequired

namestring | nullrequired

file_namestring | nullrequired

statusstringrequired

Where the translation is. All seven values: analyzing — the file's structure is being read, which takes seconds; poll. awaiting_instructions — the file is read, nobody has said what to translate; call plan. awaiting_approval — a plan is waiting for a yes; call approve, the only call that spends credits. translating — running; poll. completed — fetch the result. failed — the run could not finish; read error. cancelled — someone stopped it on purpose; also terminal, and not a failure. The last three are terminal: stop polling.

quality_tierstring | nullrequired

word_countinteger | nullrequired

credit_costinteger | nullrequired

is_samplebooleanrequired

archivedbooleanrequired

progressobjectrequired

errorobject | nullrequired

created_atstring | nullrequired

completed_atstring | nullrequired

next_actionstring

The call to make next, so a client never has to map status itself. provide_instruction — call plan with an instruction. review_plan — the priced plan is embedded; check plan.not_included, then approve. wait — poll again; progress.estimated_seconds_remaining says how long is left. download — fetch the result. read_error — the run is over without a result; read error (and status says whether it broke or was cancelled). Absent only on a legacy pre-2026-08-31 CSV batch, which has no plan behind it; every translation created since then answers.

planobject | null

suggested_instructionsstring[] | null

request_idstringrequired

Create a translation

Choosing how to send the file

What happens next

Response

Use these docs with your AI tools

Query these docs via MCP

Query these docs over HTTP

Read these docs as Markdown