Compound-level flavor data, with the receipts
OAV with confidence bands, key-aroma flags, peer-reviewed citations per compound, open methodology — not a black box you have to take on faith.
Pro $12/mo per scientist · Enterprise for team licenses + bulk data
Three things flavor R&D teams use this for
Concrete workflows with the endpoint and shape of what comes back.
Substitute for a discontinued aroma chemical
A flavor house loses access to an ingredient (regulatory, supply, cost). The engine returns ingredients with the closest compound profile — ranked by molecular overlap, not popularity.
The workflow: Reformulating around a supply, cost, or regulatory shock — screen candidates by compound overlap before committing bench time.
And the cost: candidates are ranked on flavour fit and priced from a curated book where every row carries its source, date and unit. A price we cannot stand behind comes back unknown, with a reason — never an estimate, never a neighbour’s price, never zero. See the cost endpoint →
curl "https://compkitchen.com/api/sub?ingredient=butter&top_n=5"
# IDF-weighted Jaccard over shared VOLATILES only:
# → milk (55) cream cheese (32) cheese (52)
# cheddar cheese (46) swiss cheese (41)
# Each result carries shared_compound_count + the compounds themselves.
Patent landscape for a target compound
Researching prior art for a novel formulation. The SureChEMBL cross-reference exposes which patents cite a given compound — useful surface scan before deeper attorney review.
The workflow: Prior-art surface scan — narrow the compound list before a deeper attorney review.
GET /api/compound/vanillin
{
"compound": "vanillin",
"pubchem_cid": 1183,
"surechembl_patents": 2476, // patents citing this CID
"key_aroma_in": ["vanilla", "chocolate", ...],
"papers_cited": 47
}
OAV-driven sensory panel design
Building a descriptor panel for a product? Pull the top compounds by OAV in the target ingredient — those are the ones panelists actually perceive. Filter out the “present but below threshold” noise.
The workflow: Descriptor-panel design — rank by OAV so the panel tests what is actually perceivable.
import requests
r = requests.get("https://compkitchen.com/api/pair",
params={"ingredients": "cinnamon", "top_n": 1})
compounds = r.json()["results"][0]["compound_details"]
key_aromas = [c for c in compounds if c.get("max_oav", 0) > 1]
# → cinnamaldehyde, eugenol, linalool, caryophyllene
What’s in the data layer
Every claim traces back to a peer-reviewed paper. Confidence tiers are visible per row so you know whether a value is matrix-validated, paper-cited, or modeled.
OAV with confidence bands
Three tiers: ✓ matrix-validated, 📄 paper-cited, ⚡ significant contributor. Sourced from the GC-MS corpus and the Rychlik & Schieberle (1998) licensed compilation.
Compound & recipe scoring
IDF-weighted Jaccard on shared volatiles (chemistry) + NPMI on ingredient co-occurrence across the 432,799-recipe scoring subset (culinary reality) — the portion of our 612,557-recipe browsable corpus whose ingredient lists parse cleanly enough to co-occurrence-score. Two different numbers, on purpose: you browse 612,557, we score against 432,799. Novel mode filters for high-chemistry / low-culinary.
Linked papers per compound
44,648 GC-MS papers indexed. Each compound page lists the papers that cite it; each ingredient page lists its top-contributing institutions via OpenAlex.
Pricing for R&D
Pro is the right entry point for an individual scientist. Move to Enterprise when your team needs API integration, bulk data, and SLA.
Cancel anytime
- ✓ Full site access — 300 req/min signed in (programmatic
/api/*access is a separate developer plan) - ✓ OAV, thresholds, key-aroma flags, CAS, PubChem CIDs
- ✓ CSV exports from every tool
- ✓ Citation blocks (Plain + BibTeX)
- ✓ Per-compound institution affiliations
Scoped to team size and needs
- ✓ Everything in Pro, team-wide
- ✓ Bulk JSON dumps of all corpora
- ✓ Custom endpoints for IP & regulatory work
- ✓ SLA, dedicated support, data alerts
- ✓ Academic discount for research groups
Working through a university? The Educator and Classroom tiers are priced separately.
Worked examples
Each one is a real analysis against live data, in the vocabulary of the team that would buy it.
CPG
Product development
Novel extensions, gap-filling, internal compatibility for a formula.
Retail
Assortment review
Where the flavour gaps are in a range, across ten families.
Shelf
Cross-aisle recommender
Recommend on shared chemistry rather than on co-purchase.
Beverage
Non-alcoholic portfolio
Match a customer's picks to the rest of a non-alc line.
Graph
Flavor graph explorer
Configure, draw and explain the compound graph directly.
Platform
Recipe platform
How pairing and substitution enrich a recipe page.
Run it against your own formulations
A pilot is scoped to one question you already have. You keep the analysis whether or not it goes further.
Start with one compound
Pick a compound you work with regularly — vanillin, eugenol, linalool. See the OAV, paper citations, patent count, and which ingredients carry it.