Know what any part should cost — and why.
ARCNM calculates a part's manufacturing cost from its STEP file and drawing, in seconds. You get the process plan, the times and the unit price for every lot size.
What ARCNM does
ARCNM computes the manufacturing cost of a part from physics. From 3D geometry (STEP/STP/STL), a 2D drawing (PDF) and a lot size, it returns an auditable should-cost. It covers material, setup, cycle time, labour, overhead and the unit cost across a lot-size curve. You also get the full part data it extracted. The same calculation serves a shop's quote and a buyer's should-cost. Physics computes the cost. AI reads the drawing, recognises the features, plans the process and calibrates the result. It works on top of the physics, never instead of it.
Every feature and callout, read from CAD and drawing
ARCNM recognises holes, pockets, faces, bosses, bends, slots, chamfers and threads from the 3D model. AI reads dimensions, tolerances, GD&T and surface finish from the 2D drawing. ARCNM checks them against the drawing standards ISO 286, 1101, 2768, 5459, 13715, 21920 and ASME Y14.5. Every feature and all PMI come back as structured, typed, versioned data. You can reuse this first-class output for master-data management, filling ERP and PLM master data, or similarity search.
Setup and cycle time simulated from physics, per operation
ARCNM identifies the process family from the geometry: milling, turning, sheet metal or tube. Then it plans the operations and machines. It routes on to wire EDM, grinding, laser or waterjet where the features demand it. You get physics-grounded setup and cycle times per operation. You also get a lot-size curve with the unit cost and the machine chosen at every quantity. The curve marks the optimum lot. The result is calibrated to your shop, with a confidence band on the calibrated price.
Built for code and AI agents
One REST call (POST /api/v1/calculations/upload-and-quote) prices the part. AI agents do the same over the MCP server. They upload the part and start the calculation. Then they explain, compare and rank the result. Every calculation is fully auditable, from every euro back to the feature that caused it.
Automate the cost step in every workflow
The same engine is reachable from code and from agents. The REST API comes with an OpenAPI 3.1 spec to generate typed clients from. Signed webhooks tell you when a calculation finishes. You also get OAuth for products and automation platforms, and an MCP server for AI agents. Price every incoming RFQ package on arrival. Re-price each CAD revision in the change review. Fill ERP and PLM master data from the extracted part data. Calibrate from your ERP actuals. You do all of this with the documented recipes, not a connector project.
Pay per calculation. Failed runs are free.
Every plan includes a monthly calculation quota. One calculation is one part costed in one costing environment. Every re-pricing is a new calculation. Past your quota, you pay a flat per-calculation rate. Failed runs are always free. Start free with 10 calculations a month and no card. Pro is €199/mo (300 included). Scale is €1,199/mo (2,500 included). Enterprise is a contracted annual plan with contracted volume and a negotiated rate. Talk to sales.
Frequently asked questions
How do I calculate the manufacturing cost of a part from a STEP file?
Upload the STEP model and, if you have it, the PDF drawing. Choose a lot size and a costing environment: your machines and rates, or a ready-made reference. ARCNM recognises the features and plans the operations and machines. It simulates setup and cycle time from physics. You get an itemised unit cost across the lot-size curve. Use the workspace, one REST call or an AI agent over MCP.
How do I calculate a quote from CAD and a drawing?
Quote calculation: STEP file and drawing in, routing, machines, setup time, run time and unit price per lot size out. ARCNM prices with your own machines and hourly rates. Your overhead and mark-up rates take the unit cost up to the offer price. Every number traces back to the operation behind it.
What is a should-cost?
A should-cost is the price a part ought to have when it is made efficiently at fair rates. It is computed bottom-up from material, cycle time, setup and overhead. It is not taken from a supplier quote. ARCNM computes it from the CAD geometry and the drawing. It is the same calculation a shop runs for its quote, so buyer and supplier compare line by line. Every line traces back to the operation and parameter behind it.
Can I automate quote calculation through an API?
Yes. POST /api/v1/calculations/upload-and-quote, or MCP at https://api.arcnm.io/mcp-server/mcp. You pay only on a 200. AI agents such as Claude, ChatGPT or Cursor connect over MCP. They hand you an upload link or upload the file themselves, then read the result. Every tool answer is typed and carries its source. Calculate manufacturing cost by API
Which manufacturing processes can ARCNM cost?
From physics: CNC milling and turning, sheet metal, wire EDM, grinding, injection moulding and additive manufacturing. Sheet metal covers laser, plasma and waterjet cutting, punching, shearing, press-brake, roll and tube bending. Heat treatment, coating, surface finishing and welding are read from the drawing. They are priced as subcontract steps.
Is ARCNM a black-box AI estimate?
No. Manufacturing physics computes the cost from first principles. AI only reads drawings, recognises geometry, plans the process and calibrates the result on top of the physics. Every figure shows its source: the operation, the parameter and where the value came from. Calibration to your shop adjusts the result. It never changes the physics.
Can ARCNM connect to my ERP, PLM or CAD system?
Yes. Any system that speaks HTTP can use the REST API, signed webhooks, OAuth and the MCP server. The developer docs include field-mapping recipes for SAP S/4HANA, Autodesk Vault, Oracle Fusion and Odoo. Calibration accepts the real costs you export from your ERP. There is no connector to buy.
Does ARCNM train AI models on my parts and prices?
No. We never train on customer data — not identifiable, not anonymised, not aggregated, never across customers. It is contractually binding (Terms § 10b), enforced in the schema and guarded by tests. Your calibration and part data stay yours.