Full text in the API

Abstracts leave out most of what you need: doses, methods, measured values, limitations. The Consensus API uses full text in two places — to find the right papers, and to return the passages inside them that answer your query.

	What it does	Availability
Retrieval	Queries are matched against titles, abstracts, and full text where available, so a paper can rank on what’s in its methods or results. See how search works.	Every request
Excerpts	With `include_full_text_chunks=true`, each eligible result carries the passages from its body most relevant to your query.	Paid plans (Pro, Deep, Teams, Enterprise)

Request excerpts

Add include_full_text_chunks=true to any search. Nothing else about the request changes.

curl -G "https://api.consensus.app/v1/search" -H "x-api-key: $CONSENSUS_API_KEY" \
  --data-urlencode "query=what dose of creatine improves working memory" \
  --data-urlencode "include_full_text_chunks=true"

import os, requests

resp = requests.get(
    "https://api.consensus.app/v1/search",
    headers={"x-api-key": os.environ["CONSENSUS_API_KEY"]},
    params={"query": "what dose of creatine improves working memory", "include_full_text_chunks": True},
    timeout=30,
)
resp.raise_for_status()

for paper in resp.json()["results"]:
    for chunk in paper.get("full_text_chunks") or []:
        section, _, passage = chunk.partition(" | ")
        print(paper["doi"], "·", section.removeprefix("Section: "), "·", passage[:120])

A real response, trimmed to one result with shortened excerpts:

{
  "results": [
    {
      "title": "Creatine and improvement in cognitive function: Evaluation of a health claim pursuant to article 13(5) of regulation (EC) No 1924/2006",
      "journal_name": "EFSA Journal",
      "publish_year": 2024,
      "doi": "10.2903/j.efsa.2024.9100",
      "url": "https://consensus.app/papers/creatine-and-improvement-in-cognitive-function-turck-bohn/7e703e828b815257b31687a25eceac9d/",
      "takeaway": "Creatine supplementation has not been established as a cause-and-effect relationship for improving cognitive function in one or more domains.",
      "full_text_chunks": [
        "Section: Human intervention studies in healthy individuals conducted under normal conditions | Two studies had an initial loading phase of 20 g/day of creatine for 5 days, followed by 5 g/day … A significant improvement in working memory, as measured by the Backwards Digit Span test, was observed only in the study of shorter duration …",
        "Section: Weighing of the evidence | … the acute effect of creatine on working memory reported in some studies at doses of 20 g/day given for 5-7 days … was not observed at lower creatine doses, ranging from 2.2 to 14 g/day …"
      ]
    }
  ]
}

The takeaway gives you the paper’s conclusion. The excerpts give you the doses and study designs behind it, which the abstract doesn’t.

What comes back

Format

full_text_chunks is a list of strings. Each one starts with the section of the paper it came from, then the passage: Section: <heading> | <passage>. Split on the first | to separate them.

How many excerpts

Up to 3 excerpts per paper, and up to 60 per request. Excerpts are the passages most relevant to your query across the whole page of results, so on a large page some eligible papers may carry fewer than 3, or none.

When a paper has none

full_text_chunks is null when a paper isn’t eligible or no passage matched your query. Fall back to abstract and takeaway for those papers.

Which papers have excerpts

Excerpts come from papers with an open-access PDF. Retracted papers never carry them.

Consensus also reads paywalled full text from its publisher partners to power analysis inside the Consensus app. That text improves what the app can do, but it isn’t returned as excerpts through the API.

When excerpts matter more than coverage, add open_access=true so your results are limited to open-access papers.

Plan availability

Excerpts are available on all paid plans: Pro, Deep, Teams, and Enterprise. On a Free plan, a request with include_full_text_chunks=true returns 403 with the code feature_not_allowed. Retrieval over full text works on every plan. The MCP server’s search tool accepts the same option on paid plans, so an assistant can quote passages when you ask for excerpts from the full text.

Get the most out of excerpts

Phrase the query as the thing you want to find. Excerpts are chosen against your query, so “what dose of creatine improves working memory” returns dosing passages where “creatine” returns general ones.
Keep each excerpt with its paper. Store the doi and url alongside every passage so an answer built on it stays citable.
Say which evidence you used. When full_text_chunks is null and you fall back to the abstract, tell the reader.
Read the paper for anything high-stakes. Excerpts are passages, not whole papers. Follow url to the paper.

Extract numbers from full-text papers

A worked example that pulls values and their conditions out of excerpts.

Full text access

Where Consensus’s full text comes from, and how the app uses it.

Search endpoint reference

Every parameter and response field.

What you can build

Internal tools, scientific agents, and research systems built on the API.

Introduction

References

Full text in the API

Request excerpts

What comes back

Which papers have excerpts

Plan availability

Get the most out of excerpts

Extract numbers from full-text papers

Full text access

Search endpoint reference

What you can build

​Request excerpts

​What comes back

​Which papers have excerpts

​Plan availability

​Get the most out of excerpts

​Related

Extract numbers from full-text papers

Full text access

Search endpoint reference

What you can build

Request excerpts

What comes back

Which papers have excerpts

Plan availability

Get the most out of excerpts

Related