Vet X (Twitter) accounts before you sponsor, hire or partner
Pull bio, followers, following, verification and counts for a list of X handles as JSON, to vet influencers, partners and speakers before you commit.
A sponsorship, a speaker slot or a partnership usually starts with a list of handles and a quick look at each profile, and that look gets skipped when the list has 80 names. Lovely Router does the look for all of them. Send the handles, get one JSON object per profile, pay per profile from a prepaid balance. Call it from a script, a spreadsheet job 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.
Vet X (Twitter) accounts before you sponsor, hire or partner. 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>How it works
Collect the handles
Paste the usernames from your shortlist, with or without the @: creators you are considering, speakers, partner founders, accounts that mentioned you.
Run the tool with a cap
Send the handles to
POST /v1/tools/x-profile/runwithmax_results. The run holds its maximum cost from your balance and returns the profiles as JSON.Score and decide
Put followers, following, verification and counts side by side, apply your own thresholds, and read the bios of whoever passes.
Get X profiles with one request
Get X (Twitter) profiles takes a list of usernames in twitterHandles. The cap goes in maxItems:
curl https://lovelyrouter.com/v1/tools/x-profile/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{
"input": {
"twitterHandles": ["openai", "fieldnotes_ai"],
"maxItems": 2
},
"max_results": 2
}'Set maxItems and max_results to the number of handles you send. A run still going after 60 seconds returns 202; Run a tool shows how to poll.
What each profile holds
| Field group | What you get |
|---|---|
| Identity | The handle and the bio |
| Audience | Followers and following |
| Trust | Verification status |
| Activity | The counts shown on the profile |
The tool describes a profile as bio, followers, following, verification and counts, so build your checks on those and bring other signals (engagement on recent posts, for example) from x-search.
Recipes
Run the 60 handles an agency sent you, then compute the ratio of followers to following and flag accounts that follow far more than they are followed.
When an account tags you, look up its bio and size before deciding whether to reply, amplify or ignore it.
Pull the profiles of everyone who applied to speak, sort by followers, and read the bios of the top twenty.
Run the same handles every month and store followers with a date. Growth that stalls or jumps is easy to see.
Join profile data to your CRM by handle, then ask a model to draft a one-line opener from each bio.
Prefer plain words? Connect the MCP server and tell Claude Code or Cursor: "Look up the X profiles for the handles in creators.txt and give me a table of handle, bio, followers, following and verified. Set max_results to the number of handles."
Pair it with other creator checks
Profile numbers say how big an account is, not whether its audience pays attention:
Profile details for X/Twitter handles: bio, followers, following, verification, counts.
Tweets matching search terms, hashtags or from given handles: text, author, engagement, date. Each search term takes X's advanced search operators (from:, since:, min_faves:, filter:, lang: …).
Replies to X/Twitter posts by URL: text, author, engagement, date.
Instagram profile details by username: bio, followers, posts count, recent posts.
A TikTok account's videos with the author's follower and like counts.
x-searchshows what an account posts and how those posts perform, usingfrom:in the search term.x-repliesreads the replies under a post, which shows whether followers are real people talking.instagram-profiledoes the same check for the creator's Instagram.tiktok-profilecovers their TikTok account.
For the full workflow across platforms, see influencer research.
These are public profiles, but you are responsible for using any personal information you collect lawfully, including privacy and anti-spam rules in the places you operate.
What you pay
You pay per profile: starting a run holds its maximum cost, the per-call fee plus the per-profile 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 profiles it delivered, and a run refused at the start costs nothing.
Vetting 100 accounts is billed as 100 profiles. 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.
Frequently asked questions
Can I look up many handles at once?+
Yes. Put them all in twitterHandles and set max_results to at least the number of handles. One run can return up to 100 profiles.
Do I include the @ in the handle?+
Either works. The input accepts usernames with or without the @.
Can I tell if an account is verified?+
Yes. Verification is one of the fields a profile holds.
Does it show an account's posts or engagement rate?+
Not this tool; it returns the profile. For posts and their engagement, search with from:handle in x-search.
Do I need an X account or API access?+
No. You send handles 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.
Comparing creators across networks? See influencer research, social listening and the rest of the tool catalog.