Use case

Benchmark YouTube Shorts against competitors on views and likes

Pull Shorts from any YouTube channel as JSON with title, views, likes, comments and date, to benchmark short-form performance against competitors.

Prepaid, no subscriptionREST or MCPOne key for models, data and agents
YouTubelovelyjsonitems[0]"title": "Latte art in 15 secon…"views": 2480000"likes": 151000"comments": 3200"date": "2026-10-19"

You post Shorts and have no idea whether 20,000 views is good. Your competitor posts three a week and one of them took off, but their channel page buries the numbers under the long videos. Lovely Router reads the Shorts of a channel for you. Send handles, get one JSON object per Short, pay per Short from a prepaid balance. Run it from a script or an AI agent with one API key.

Hand it to your AI agent

Copy this prompt into Claude Code, Cursor, Codex or any coding agent. It tells the agent where the docs are and how to use your API key.

Benchmark YouTube Shorts against competitors on views and likes. Use the Lovely Router data tools: each returns JSON and is billed per result.

- Docs (read first): https://lovelyrouter.com/docs/tools/find.md and https://lovelyrouter.com/docs/tools/run.md
- Plan first: POST https://lovelyrouter.com/v1/tools/suggest with `{"task": "<my task in plain words>"}` (free). It returns the tools to run in order, each with an example `input`, the `input_required` fields, an estimated cost and a ready-made `run` request. Replace the example values with my task's; if a field is unclear, read the tool with GET https://lovelyrouter.com/v1/tools/<id>. To browse instead, POST https://lovelyrouter.com/v1/tools/discover searches the catalog.
- Show me the plan and its estimated cost (`total_est_cost_usd`) before running anything large.
- Run: POST https://lovelyrouter.com/v1/tools/<id>/run with `{"input": {...}, "max_results": N}`. A 200 has the finished run with `items`; a 202 means it is still running, so poll the `poll` path until `status` is `succeeded`, `failed`, `timed_out` or `stopped`.
- Only delivered results are billed. Keep max_results small on the first run, check the output, then scale up.
- If you support MCP, connect https://lovelyrouter.com/mcp instead (Streamable HTTP, same key; https://lovelyrouter.com/docs/tools/mcp.md) and use suggest_tools, get_tool and run_tool.
- Auth: read my API key from the LOVELY_API_KEY environment variable and send it as `Authorization: Bearer $LOVELY_API_KEY`. Never print or commit the key. If it is not set, ask me to create one at https://lovelyrouter.com/app/keys.
- Billing is prepaid: every call is charged to my balance, so test with a small request before running anything large.
- Every docs page is plain Markdown; the full index is https://lovelyrouter.com/llms.txt.

My task: <the inputs (links, keywords or accounts) and how many results you need>
01

How it works

010203
  1. Pick the channels

    Your own channel, direct competitors, and a few creators you admire in the same niche. Use handles or the link to each Shorts tab.

  2. Run the tool with a cap

    Send them to POST /v1/tools/youtube-shorts/run, with maxItems for the number of Shorts and max_results as the run cap. The run holds its maximum cost from your balance and returns the Shorts as JSON.

  3. Set your baseline

    Compute the median and the top decile of views per channel. Judge your own Shorts against the competitors' median rather than against one viral outlier.

02

Get a channel's Shorts with one request

Get YouTube Shorts takes channel handles in youtubeHandles. Instead you can pass Shorts-tab URLs such as https://www.youtube.com/@MrBeast/shorts, or links to single Shorts, in startUrls:

curl https://lovelyrouter.com/v1/tools/youtube-shorts/run \
  -H "Authorization: Bearer $LOVELY_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "input": {
      "youtubeHandles": ["@MrBeast"],
      "maxItems": 3
    },
    "max_results": 3
  }'

A run still going after 60 seconds returns 202; Run a tool shows how to poll. One run can return up to 200 Shorts.

03

What each Short holds

Field groupWhat you get
IdentityTitle
ReachViews
EngagementLikes and comments
TimingPublication date
04

Recipes

Set a views benchmark

Pull the last 50 Shorts of five competitors and write down the median views of each. That number is what a normal Short earns in your niche.

Find the hits and read their titles

Sort a channel's Shorts by views, take the top five, and ask a model what the titles have in common.

Check posting rhythm

Count Shorts per week from the dates and compare with the views, to see if posting more helps or just dilutes.

Compare Shorts with long videos

Run youtube-channel for the same channels and compare views per upload between the two formats.

Report monthly

Keep a table per channel and per month for a client or your team.

Prefer plain words? Connect the MCP server and tell Claude Code or Cursor: "Get the latest 40 Shorts from @MrBeast and @MarkRober, then compare median views and likes per Short, and list each channel's top three by views. Set max_results to 80."

06

What you pay

You pay per Short: starting a run holds its maximum cost, the per-call fee plus the per-Short fee times max_results, and the run settles to what it returned. The rest of the hold goes back to your balance. A run that fails or times out pays only for the Shorts it delivered, and a run refused at the start costs nothing.

Benchmarking 5 channels at 50 Shorts each is billed as 250 Shorts. There is no subscription and no monthly minimum: top up from $5, and one balance pays for tools and models. The card above shows today's price; pricing lists every tool.

07

Frequently asked questions

?
Does this return only Shorts, or all videos?+

Only Shorts. For the long-form videos of a channel use YouTube channel videos.

Can I use the Shorts tab link instead of a handle?+

Yes. Put the Shorts-tab URL in startUrls, or a link to a single Short.

How many Shorts can I get per run?+

Up to 200. maxItems sets how many you ask for.

What does each Short include?+

Title, views, likes, comments and date.

Do I need a YouTube account?+

No. You send handles or links and an API key.

Do I need a subscription?+

No. You add credit to a prepaid balance and each run draws it down. Failed runs pay only for the results they delivered, and nothing renews automatically.

Choosing creators or tracking a niche? See influencer research, social listening and the tool catalog.

One prepaid key for models, data and agents

No subscription. Top up, use what you need, see every charge in your logs.