Analysis
Tweet viral score API for X posts and drafts
Score how viral X posts and drafts read with AI. Get a Viral Score from 0 to 100, a verdict, and the 8 traits behind it. Costs 2 credits per analyzed post.
POST
Tweet viral score API for X posts and drafts
2 credits per analyzed post · All plans from $0.00012/credit · Supports guest paid reads
0 to 100. The endpoint is
POST /api/v1/x/analysis/viral-score.
The score rates the wording. It does not predict likes or views.
Score drafts before you post
Send up to 100 drafts intexts. Xquik reads nothing from X for them, and each
draft costs the same as 1 analyzed post. Drafts come back with the IDs
text:1, text:2, and so on.
Rewrite a draft with a low hook or clarity first. Those 2 traits carry half
of the score.
Read the Viral Score
Hook, clarity, payoff, and the expected reaction raise the score. Payoff is the higher ofinformative and funny. Wording that reads like generic machine
copy lowers it.
Hard stops cap the score of likely spam, ragebait, and generic machine copy.
viral.stops lists the stops that applied, such as spam. viral.weights
names the version of these rules, such as viral_lite:1.
viralScore is null when a trait has no answer. Xquik never fills a missing
score with a guess.
Compare with real engagement
For posts read from X,viralAlgorithmScore applies X’s published ranking
weights to the post’s public counts: like 0.5, reply 5, repost 1, and
quote 5. It divides the sum by views and multiplies by 1,000. A post without
a view count uses followers. viral.algorithmBasis names the divisor.
The AI never sees these counts. It reads the text and its context only. The
estimate is not the score X computes, since X uses signals public data does not
show.
viralActualEngagementRate is log10(1 + weighted engagement per 1,000 followers). analysisSummary.viral.calibration compares it with the Viral
Score across the posts.
Score an account’s posts
Sendusername to score an account’s recent posts. analysisSummary.viral
then holds a report per author in accounts and a leaderboard.
Pick the posts to analyze
SendtweetIds, texts, or a search, never more than 1. Sending none, or more
than 1, returns 400 invalid_input.
A search combines every search field you send into 1 X search.
queryType sets the order, Latest or Top. For more posts than 1 call
returns, send the same search again with cursor set to next_cursor. Stop
when has_next_page is false.
Compare with an earlier answer
Send theresults of an earlier call as baseline to see what changed. Each
row in the new results gets monitor, and analysisSummary.monitor counts
the posts per status. The comparison costs nothing extra.
id, or tweet.id, and its answers. Send
whole result rows when you have them. Their monitor carries the settings’
fingerprint, so rows from other settings show as not_comparable.
A decision counts as changed only when the new answer clearly leaves the old
one, so near ties between calls stay
unchanged. Keep analysis the same
between calls for comparable answers.
Budget the analysis
Each analyzed post costs 2 credits. Each text intexts costs the same. Posts
in unanalyzed cost nothing.
When credits cover fewer posts than you asked for, fewer come back. The posts
left over appear in unanalyzed with insufficient_credits. If credits cover
no post, the call returns 402 insufficient_credits.
Body
string[]
Up to 100 post IDs or post URLs, such as
x.com/nasa/status/20. A post named
twice is analyzed once. Send tweetIds, texts, or a search, not more than 1.string
X search to analyze, with the operators of Search Tweets.
string
Analyze 1 account’s posts. Send a handle, with or without
@, or a profile URL.string
Analyze a public List’s posts. Send its ID or URL.
string
Analyze the quotes of 1 post. Send its ID or URL.
string
Analyze the replies in 1 post’s conversation. Send its ID or URL.
string
Inclusive start of the search, such as
2026-09-25T00:00:00Z. Unix seconds
also work. A time without an offset is UTC.string
Exclusive end of the search. Unix seconds also work. A time without an offset
is UTC.
string
Search order:
Latest or Top. Defaults to Latest.integer
Maximum posts to analyze from the search. Range:
1-100. Defaults to 20.
Credits can return fewer.string
The
next_cursor of the page before. Send the same search with it.string[]
Up to 100 texts of your own, such as drafts. Each must contain words. Reads
nothing from X.
object[]
Rows of an earlier answer to compare with, up to 10,000, such as its
results. Each needs the post’s id, or tweet.id, and its answers. Each
new result’s monitor says whether the post is new, changed, or unchanged.
The comparison costs nothing extra.object
Optional settings. Leave it out to ask the route’s own questions.
Headers
string
Full account API key. An OAuth bearer token also works.
string
Send
Bearer xq_your_guest_key_here for an active paid_reads guest key.string
required
Must be
application/json. The body can be up to 256 KB.Response
200 OK
object[]
Each analyzed post with its answers. Each row costs 2 credits.
object[]
Each post without an analysis. These cost nothing.
object
Totals of the answers across the analyzed posts.
boolean
Whether the search has more posts. Always
false for tweetIds and texts.string
Send it as
cursor with the same search for the next page. Empty when there is none.400 Invalid input
401 Unauthenticated
Anonymous requests getWWW-Authenticate: Bearer and a guest wallet checkout action. This is not a Payment challenge.
x-api-key header value.
402 Payment required
Full account keys can receiveno_subscription, subscription_inactive, no_credits, or insufficient_credits with account payment options. Guest keys receive only the guest top-up action.
The failed request creates no checkout. Ask the user to confirm before calling any checkout or top-up route.
403 Protected account
502 X API unavailable
503 Service busy
Retry-After header, then send the request again.
The request costs nothing.
429 Rate limit exceeded
Retry-After header before retrying.
424 Dependency failed
Tweet viral score API questions
How do I check if a tweet will go viral?
Send the draft intexts. viralScore rates its wording from 0 to 100,
and viralVerdict says whether to post it, edit it, or wait.
Does the score predict likes or views?
No. It rates the wording only. Timing, followers, and X’s ranking decide the reach.viralAlgorithmScore shows how a posted tweet actually performed.
Why did my draft score low?
Readanswers. A low hook or clarity costs the most points. viral.stops
names any hard stop, such as spam or ragebait, that capped the score.
Can I score someone else’s posts?
Yes. Send their handle inusername, post IDs in tweetIds, or a search in
query.
How much does the viral score cost?
Each analyzed post or draft costs 2 credits. Posts inunanalyzed and refused
requests cost nothing.
Does this replace X’s official API?
No. This page documents Xquik, an independent third-party service. It does not document X’s official API.Next steps. Classify posts asks your own questions, or Sentiment analysis reads the attitude of posts.