Douyin Comment replies API

Please help me write a data collection script with the EveryInfra Douyin Comment replies endpoint (douyin/comment_replies).

How the endpoint works:
- Request: POST https://api.everyinfra.com/api/v1/social with the header Authorization: Bearer <API key>. Read the key from the EVERYINFRA_API_KEY environment variable and never hard-code it.
- In the request body, set platform to douyin and action to comment_replies, and put the parameters inside params.
- Required parameters:
  - url: Full URL of the target Douyin video, formatted as https://www.douyin.com/video/<video_id>.
  - comment_id: The ID of the top-level comment whose replies you want, digits only, taken from the id of a comments row; only comments whose reply_count is above zero have replies.
- Optional parameters:
  - page_token: Page token for comment_replies: send an empty string page_token="" to start from the first reply, then pass back each response's next_page_token exactly as received, keeping the other parameters unchanged.
  - limit: The most rows to return in this call, an integer from 1 to 100. The default applies when you leave it out, and a call can return fewer rows. Larger values return 422 before any charge. (default: 20)
- Returns a list of records. Main fields of each record: next_page_token (Page token (user_posts / comments / com…), id, text, like_count, author_name, author_id, author_uid (Numeric user ID of the author (on comme…), author_avatar_url (Author avatar image URL: the creator on…), ip_location (IP region Douyin displays (set by the p…), liked_by_author (Whether the video's author liked the co…), is_reply (Whether the row is a reply), reply_to_id (ID of the top-level comment this reply…); 18 fields in total, full list at https://api.everyinfra.com/api/v1/social/catalog?platform=douyin.
- Example request body:
{
  "platform": "douyin",
  "action": "comment_replies",
  "params": {
    "url": "https://www.douyin.com/video/7551364376725409062",
    "comment_id": "7648918588065661753"
  }
}
- Price: $0.56 per 1,000 requests; failed and empty results are not charged.
- For dozens or hundreds of targets, add "mode": "async" to the body: you get a job_id at once and poll GET https://api.everyinfra.com/api/v1/jobs/{job_id} for the result.
- On 422, fix the request using the suggested parameter names and allowed values in the error; on 429 or 503, wait for Retry-After and try again.

Before writing code, ask me which targets I need, how many, which fields, and what output format I want; then confirm the plan and the rough cost with me.