Elicit: how many tokens per task, and what does it cost?
Elicit publishes no per-task cost or token figure in the AgentBurn index. AgentBurn snapshot 2026-10-27. Every figure carries a provenance label: source-backed, derived, or left empty when no public basis exists.
What it is. Literature-review agent that extracts structured data from papers at scale
Elicit runs a systematic-review loop over the academic corpus: it searches papers, screens them against inclusion criteria, extracts chosen columns from each PDF and returns a review table with citations. Researchers use it to turn hundreds of papers into a comparable dataset without reading every abstract by hand.
| Tokens per task | not published | Not published |
|---|---|---|
| Cost per task | not published | Not published |
| Success rate | not published | Not published |
| Cost per solved task | not published | — |
| Tool calls per task | not published | — |
| Retry overhead | not published | — |
| Minutes per task | not published | — |
| Estimated runs per day | 60,000 (model estimate) | Model estimate |
Where the tokens go
This is the per-task split AgentBurn records for Elicit, step by step.
| Step | What happens | Share of tokens | Tool calls |
|---|---|---|---|
| Search corpus | Queries 125M+ papers and ranks candidates | 12% | 4 |
| Screen abstracts | Applies inclusion and exclusion criteria | 26% | 8 |
| Extract columns | Pulls study design, n, outcome and effect size per paper | 40% | 12 |
| Build table | Normalises and deduplicates extracted values | 14% | 4 |
| Cite | Attaches page-level citations to every cell | 8% | 2 |
What each number is based on
AgentBurn labels every field. Source-backed means the cited page states the figure; derived means a formula on this page produced it; not published means no public basis exists and the field is left empty rather than estimated.
| Field | Basis | Note |
|---|---|---|
| tokensPerTask | Not published | Vendor publishes seat/credit pricing, not per-task tokens. |
| costPerTaskUsd | Not published | No per-task cost is published for this product. |
| successRatePct | Not published | No public task success rate. |
| runsPerDay | Model estimate | No public source publishes daily run volume; this is a model estimate from pricing tiers and community reports, shown only in estimated-volume context. |
Frequently asked
How many tokens does Elicit use per task?
No public tokens-per-task figure exists for Elicit; AgentBurn leaves the field empty rather than estimating it.
What does Elicit cost per task?
No public per-task cost exists for Elicit, so it is recorded as not published.
Is this a vendor list price?
No. It is a per-task figure from a cited source, not a rate card; the two are not comparable.
Sources
- Elicit — AI research assistant for systematic reviews (product docs)
- Vendor site: https://elicit.com
- Open dataset: /data/projects.json
- Methodology: how these numbers are built
Cite this page
AgentBurn (2026-10-27). "Elicit". https://getagentburn.com/projects/elicit/
Machine-readable: projects.json · Markdown version