Trial Pipeline Shape API: Trials and enrollment by phase, status and study type for a condition — ClinicalTrials.gov

Trials and enrollment by phase, status and study type for a condition or sponsor, with leading sponsors and an active-trial count. One call instead of paging and tallying the registry. Free, no key.

Free — no key, no signup, rate-limited to 60 calls per minute per client.

How do you call it?

GET /v1/trials/pipeline — product id trials_pipeline. Over MCP, call answerpool_get with product_id=trials_pipeline.

curl "https://answerpool.io/v1/trials/pipeline?condition=melanoma"

Live call: https://answerpool.io/v1/trials/pipeline?condition=melanoma · JSON sample: /v1/samples/trials_pipeline

What does the answer look like?

A representative response, the same static sample served at /v1/samples/trials_pipeline.

by_phase

{
 "as_of": "2026-09-03T16:00:00Z",
 "query": {
  "query.cond": "melanoma"
 },
 "trials_analyzed": 200,
 "by_phase": [
  {
   "key": "PHASE2",
   "trials": 71,
   "enrollment_total": 8420
  }
 ],
 "by_status": [
  {
   "key": "COMPLETED",
   "trials": 96,
   "enrollment_total": 11200
  }
 ],
 "by_study_type": [
  {
   "key": "INTERVENTIONAL",
   "trials": 181,
   "enrollment_total": 19800
  }
 ],
 "top_sponsors": [
  {
   "key": "National Cancer Institute (NCI)",
   "trials": 14,
   "enrollment_total": 2100
  }
 ],
 "active_trials": 63,
 "total_enrollment": 21450,
 "note": "Distributions are computed over the sample of trials matching the query (capped by `sample`), newest registry order \u2014 a shape of the pipeline, not a registry census. Enrollment is the registered target or actual count as submitted.",
 "source": "Source: National Library of Medicine (ClinicalTrials.gov)",
 "refresh_after": "2026-09-18T00:00:00.000Z"
}

How fresh is it, and where does the data come from?

The fastest source behind this answer can change daily, so every response carries a refresh_after timestamp — right now it would be 2026-09-18T00:00:00.000Z. Schedule the next call on that value rather than on a guess.

• ClinicalTrials.gov (NIH National Library of Medicine) (US federal public domain) — upstream: https://clinicaltrials.gov/api/v2

Method version 0.1.0 · serving cache 1 day · every response carries a result_id you can resolve at /v1/provenance.

When should you use it?

You want the distribution across a therapeutic area or a sponsor's portfolio.

What you skip building

• registry paging
• phase and status tallying
• enrollment summing

When should you not use it?

Individual trial records — /v1/trials/search.

Where else can you find this?

• Catalog entry (JSON, free)
• OpenAPI schema — input and output types, prices, the 402 flow
• llms.txt — every product in one plain-text document