LinkedIn Viral Post Predictor

Beta

think-reason-learn/linkedin-viral-post-predictor

Predicts whether a LinkedIn post will be a hit or go viral, and explains what pulled the score up or down.

Scores a LinkedIn post draft (text, optionally with its image) for its chance to be a hit (top 5% of posts by reactions among authors with a similar following) or to go viral (top 1%).

Returns a level (bottom half / 50-75th / 75-90th / 90-98th / top 2%), the probability of a hit and of going viral next to the base rate, and the checks that pulled the score up or down. The reasons are written to feed straight back into a writing loop: draft → score → rewrite.

Built with ThinkReasonLearn: hundreds of plain-language checks answered by a language model, combined by a trained, auditable scorer. On authors it never saw in training it ranks viral posts at 0.79 AUC; its top 2% of posts go viral 10% of the time against 1% at random.

Send the post as the user message (plain text, or a JSON object with text, media, quote), with an optional image part. The reply is a JSON object.

Quality

Viral AUC, unseen authors: 0.79
Viral rate in top 2%: 10.1%; vs 1.0% at random

Limits

Where the model was trained, and where to trust it less.

Trained on posts by authors with 1k-20k followers about startups, AI and venture capital, July-October 2026. Outside that range the response carries a warning.
Pulled up / pulled down are what the model noticed, not advice.

Input

Field	Type	Description
textrequired	text	Post. Up to 3,000 characters.
media	select	Attachment. `textimageimagesvideodocument`
image	image	Image or video frame.
quote	checkbox	Quotes another post.

Output

The output object of POST /v1/predict. Over chat completions, the same JSON is the reply content.

Field	Type	Description
level	string	bottom half \| 50-75th \| 75-90th \| 90-98th \| top 2%
chance_hit	number	Probability of a hit: top 5% of posts by reactions among authors with a similar following.
chance_viral	number	Probability of going viral: top 1%.
base_chance_hit, base_chance_viral	number	The base rates, for comparison.
content_score	number	0-1 score of the content alone.
pulled_up, pulled_down	array	Up to 5 checks each: {check, answer, effect}. What the model noticed, not advice.
image_reading	string \| null	How the image was read. Send it back as image_reading to rescore edits without the image.
warnings	string[]	E.g. the author is outside the training range.

Call it

POST /v1/predict with your API key, any OpenAI SDK pointed at our base URL, or OpenRouter under the same id.

curl https://api.thinkreasonlearn.com/v1/predict \
  -H "Authorization: Bearer $TRL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "think-reason-learn/linkedin-viral-post-predictor",
  "input": {
    "text": "We almost ran out of money in month 9.\n\nHere'\''s the one decision that saved the company — and why I'\''d make it again:\n\nWe stopped selling to everyone and picked 1…"
  }
}'