01
LV matching
Match bill-of-quantities line items across projects and catalogues, even when wording differs.
Relevant for TradesConstruction firmsWholesalersManufacturers
- GAEB-LV
- Position
- Teilleistung
- Titel
- Mengenansatz
- IFC / BIM
- IfcWall
- IfcSlab
- IfcBeam
- IfcSpace
- Ökobaudat
- GWP
- EPD
- Lebenszyklus
- Datensatz
- Cost data
- Kostenkennwert
- Kostengruppe
- Standardposition
- KG 300
- Rohbau
- Bodenplatte
- Stütze
- Geschossdecke
- Fundament
- Brandschutz
- Brandabschnitt
- Entrauchung
- F90
- Sprinkler
- Bewehrung
- Betonstahl
- Bewehrungsmatte
- Bügel
- Stabstahl
- Trockenbau
- Ständerwand
- Gipskarton
- Abhangdecke
- Vorsatzschale
- TGA
- Lüftung
- Heizung
- Sanitär
- Elektro
- Estrich
- Zementestrich
- Anhydritestrich
- Dämmschicht
- Randstreifen
- Mauerwerk
- Kalksandstein
- Ziegel
- Porenbeton
- Mörtel
- Dämmung
- Mineralwolle
- EPS
- Perimeterdämmung
- WLG 035
Vertical Foundation Model · API
The embedding API for the construction industry
flinq is a cross-modal embedding model for the European construction industry. It brings heterogeneous construction data such as BIM models (IFC), tenders (GAEB), manufacturer products, construction-site images and further construction-project data together in one shared semantic space. Access is via an API.
curl https://api.flinq.ai/v1/embeddings \
-H "Authorization: Bearer $FLINQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flinq-embed",
"input": "Stahlbeton C25/30, Bodenplatte d=25 cm"
}'Conceptual example. Runnable examples live in the docs.
Available as a cloud API, optionally on-premise (GDPR-compliant)
+30%
better product retrieval than OpenAI
nDCG 0.78 vs. 0.60
ρ 0.71 #1
understands units of measure better than the whole field
vs. ρ 0.57 (best model in the field)
83%
recognises components by their 3D shape
82.9% accuracy; text-only models: 6.3%
Supported by partners and programmes from the ecosystem.
What flinq reads
One model for all construction data, one shared vector space
flinq reads different kinds of construction data, each in its common file formats, and maps them into one shared vector space. Semantically similar objects sit close together in it, regardless of data type, format and source.
GAEB Bills of quantities, Line items
IFC BIM models, Building elements, 3D geometry
JPG / PNG Site photos, Plans
PDF Tender texts, Datasheets, Standards
CSV Cost data, Manufacturer products
flinq embedding model cross-modal
Shared vector space format- and source-independent
Cross-modal: a bill-of-quantities line item and the matching IFC component sit on nearby vectors, searchable across formats and sources.
The advantage
Why an embedding model?
For search, matching and RAG over construction data, an embedding model has clear advantages over a generative LLM — in cost, speed and reliability.
Up to 100× cheaper than running an LLM for the task
You embed each object once and store the vector. Search and matching are then pure vector math — no costly model call per query like an LLM.
Real-time answers, even across millions of objects
Vector search over precomputed embeddings returns in milliseconds. An LLM call takes seconds.
Reproducible, defensible results
Same input, same vector — every time. Traceable for costing and tenders, where LLM output varies.
No hallucination
Embeddings retrieve real, existing objects — an actual bill-of-quantities item, a real product — rather than inventing an answer.
Fewer false matches, less rework
Trained on construction data: BauSatz nDCG 0.78 vs 0.60. Higher domain accuracy saves manual correction.
See the benchmarkOne integration, many features
The same vectors power search, matching, RAG, deduplication and clustering — several features from one embedding call.
Connect data across format boundaries
Match a bill-of-quantities item, an IFC component and a datasheet cross-modally — connections that were previously manual or impossible.
Your data stays in the EU
GDPR-compliant in the EU, on-premise on request — without a detour via a US LLM provider.
Cost comparison against generative LLMs on retrieval and matching tasks; depends on the model and query volume.
Access
Access via an HTTP API
Access to the model is via an HTTP API. A request embeds one or more construction objects, and the response returns the corresponding vectors.
{
"model": "flinq-embed",
"input": [
"Stahlbeton C25/30, Bodenplatte d=25 cm",
"Bewehrungsstahl BSt 500 S, Mattenbewehrung"
]
}A request embeds a bill-of-quantities line item.
{
"model": "flinq-embed",
"data": [
{ "index": 0, "embedding": [0.0131, -0.0427, 0.0588, …] },
{ "index": 1, "embedding": [0.0204, -0.0119, 0.0731, …] }
]
}The response returns the vector and the model id. Vector truncated.
These are conceptual examples that show the format. The full reference and runnable examples live in the docs.
Go to the API reference What you build
Applications made possible with flinq
On the embedding API you build search, matching and RAG applications over construction data. The examples below show one possible workflow per application. These are applications made possible with flinq, not products flinq ships.
02
Early-phase cost prediction
Derive cost figures from semantically similar line items and reference projects that have already been costed.
Relevant for Planners/ArchitectsConstruction firms
03
RAG & knowledge management over construction data
Retrieval-augmented generation for company-wide knowledge management: search standards, bills of quantities and project documents with reliable hits.
Relevant for Planners/ArchitectsTradesConstruction firmsWholesalersManufacturers
Working examples with real code live in the docs.
More applications
Further applications built on the same embeddings. Filter by audience.
Benchmark
BauSatz: flinq small (0.6B) vs. the field
flinq small is a single 0.6B model. On the BauSatz benchmark it leads on six of eight tasks against larger, zero-shot models.
Shown is the primary metric per task, ×100. Higher is better. flinq small is the best of v9b/v10. The comparison models are zero-shot. Source: BauSatz public leaderboards, June 2026.
| Task | flinq small | OpenAI | Qwen3-8B | Mistral | Gemma2 | BGE-M3 |
|---|---|---|---|---|---|---|
| Product retrieval | 78.4 | 59.5 | 56.8 | 40.3 | 58.6 | 36.8 |
| Unit semantics | 70.9 | 55.8 | 58.7 | 52.5 | 57.8 | 48.6 |
| Spec reranking | 78.5 | 72.6 | 64.9 | 70.7 | 61.8 | 68.9 |
| IFC name matching | 71.2 | 13.3 | 22.2 | 19.1 | 13.5 | 49.7 |
| Trade clustering | 36.1 | 33.1 | 31.3 | 29.1 | 30.5 | 24.3 |
| Equivalence pairs | 97.1 | 96.1 | 96.1 | 96.1 | 96.1 | 96.1 |
| Section classification | 72.8 | 71.5 | 73.2 | 60.7 | 72.4 | 69.5 |
| Position matching | 85.2 | 87.1 | 85.7 | 87.2 | 86.1 | 86.9 |
Deployment and trust
As a cloud API or on-premise
flinq is available as a cloud API and, on request, on-premise. Operation is GDPR-compliant and hosting is in the EU.
Cloud API
Direct access via the hosted API. No infrastructure to run yourself.
On-premise
On request, in your own data centre or VPC. Your data stays in your environment.
GDPR-compliant
Data processing follows the requirements of the GDPR.
EU hosting
The hosted API runs in the EU.
Team
The team behind flinq
flinq is built by a team with backgrounds in architecture, BIM, machine learning and construction economics.
Valentina Mayer-Steudte
Co-Founder, CEO
Company leadership, strategy & brand
M.Sc. Architecture: strategic planning, BIM, business development, branding.
Experience: Co-Founder Wertstudent, Bez+Kock Architekten, cruu architecture (BIM)
Matthias Hornung
Co-Founder, CTO
Technical architecture, ML integration & systems
M.Sc. ITECH and M.Sc. Architecture: BIM, graph ML, robotics & software.
Experience: Design-to-Production, Transsolar, Blocher und Partners/Schwarz Architekten
Lukas Simon
Co-Founder, CPO
Product strategy, data pipelines & sales
cand. M.Sc. Economics: data analysis, financial modeling, process optimization.
Experience: Mercedes Benz, ZEW
News & updates
Latest developments
Stay up to date with new features, insights and best practices.
flinq at the ZIA PropTech breakfast at S-TEC
Invited by the ZIA at S-TEC and Fraunhofer IAO: the conversations confirmed that companies are not looking for yet another off-the-shelf tool, but technology that understands their workflows and fits in. An announcement on this follows in the coming weeks.
Read on LinkedInflinq at the TGA Fachforum in Viega World
Two intense days in Attendorn: Lukas Simon pitched how flinq supports AI-driven tendering in building services (TGA). A clear takeaway — manufacturers and wholesalers want to match line items automatically too.
Read on LinkedInflinq at “Bauindustrie meets Startups 2026” in Munich
In dialogue with the board and members of the Bavarian Construction Industry Association: construction meets its challenges best with openness to technology and a collaborative spirit of innovation.
Read on LinkedIn FAQ
Frequently asked questions
What is flinq?
flinq is the embedding API for the European construction industry. A cross-modal model maps heterogeneous construction data into one shared vector space, from bills of quantities and BIM models to site photos, manufacturer products, cost data and standards. These document types exist across Europe in different national formats; today flinq supports the German formats such as GAEB most deeply. Access is via an API.
Is flinq a SaaS product or an API?
flinq is an API service. The product is the model behind an API, not a finished application. Bill-of-quantities matching, cost prediction and RAG are examples of what you build on the API, not features flinq ships.
Which data and file formats does flinq support?
flinq reads common construction file formats and the domain content they carry. These are GAEB, IFC, PDF, JPG, PNG and CSV. From them the model recognises, among others, bills of quantities and tender texts, BIM models and building elements (including 3D geometry), site photos, manufacturer products, cost data and standards. GAEB here is the German format for bills of quantities, one national instance of a document type found across Europe, whereas IFC is an international BIM standard. Support is deepest today for the German formats. All are embedded into the same vector space.
How do I access the model?
Via an HTTP API. You send construction objects as a request and receive embedding vectors in return. The full reference and runnable examples live in the docs.
What can I build on flinq?
Typical examples are matching bill-of-quantities line items, early-phase cost prediction and RAG over construction data. Building on that, you can identify VOB-compliant tender texts or price bills of quantities via external cost databases. Further examples are pricing tendered line items via an internal cost database, matching manufacturer products to line items, classifying products by ETIM, and retrieving the relevant national standards, such as DIN. You build these applications on the API; flinq provides the embedding model, not the finished application.
What sets flinq apart from generic embedding models?
flinq is trained on domain-specific tasks. On the BauSatz benchmark, flinq small (0.6B) reaches nDCG 0.78 on product retrieval versus 0.60 for OpenAI, and recognises components by their 3D shape with 82.9% accuracy, while text-only models reach 6.3%.
Can I run flinq on-premise?
Yes. flinq is available as a cloud API and, on request, on-premise. Your data then stays in your environment.
Is flinq GDPR-compliant?
Yes. flinq is GDPR-compliant and hosted in the EU.
What is the quality of the embeddings based on?
On a curated, cross-modal dataset of matched construction objects. This dataset is the defensible core. The model backbone is swappable.