PHBench
PredictionsSimulaterepoHFdatasetarXiv2605.02974

API Reference

Access weekly Series A predictions for Product Hunt launches.

Authentication

External API requests require an API key passed via the x-api-key header. To request a key, email benchmark@vela.partners.

curl -H "x-api-key: pk_your_key_here" \ https://phbench.com/api/predictions

GET/api/predictions

Returns scored and filtered featured Product Hunt launches, ranked by predicted Series A probability. Only launches verified as not having raised Series A are included.

Query Parameters

ParameterTypeDescription
daysintLook back N days from now. Default: 7
weekstringMonday date in YYYY-MM-DD format. Returns Mon-Sun of that week.

Examples

# Current week curl -H "x-api-key: pk_..." https://phbench.com/api/predictions # Specific week curl -H "x-api-key: pk_..." https://phbench.com/api/predictions?week=2026-05-12 # Last 14 days curl -H "x-api-key: pk_..." https://phbench.com/api/predictions?days=14

Response

{ "count": 9, "from": "2026-05-12", "to": "2026-05-19", "weeks": ["2026-05-12", "2026-05-05"], "posts": [ { "id": 1147034, "name": "Drizz", "slug": "drizz", "tagline": "Build dashboards with natural language", "votes_count": 200, "comments_count": 45, "daily_rank": 4, "weekly_rank": 12, "topics": "Developer Tools|AI", "score": 0.32, "above_baseline": true, "funding_status": "not_funded", "created_at": "2026-05-14T07:01:00+00:00", "website_domain": "drizz.dev" } ] }

Post Fields

FieldDescription
idProduct Hunt post ID
nameProduct name
slugPH URL slug
taglineOne-line product description
votes_countTotal upvotes on launch day
comments_countTotal comments
daily_rankRank on Product Hunt for that day (null if unranked)
weekly_rankRank for the week
topicsPipe-separated category tags
scoreModel probability of Series A within 18 months (0-1)
above_baselineWhether score exceeds the 0.78% base rate
funding_statusnot_funded (verified via Gemini + Google Search)
created_atLaunch timestamp (ISO 8601)
website_domainResolved company domain

Rate Limits

No hard rate limits currently enforced. Please be reasonable -- the data updates once per week. Usage is tracked per API key.

About the Model

Predictions are generated by the PHBench champion model (Top-3 ensemble) trained on 67,292 featured Product Hunt launches from 2019-2025, with 528 verified Series A outcomes from Crunchbase. The model uses 68 engineered features from public launch signals. On held-out test data, it achieves 4.7x lift over random. See the paper for details.

phbench.com · Predictions · arXiv · GitHub