ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.

EU-only data on a budget

Find the cheapest offering that runs inference in an EU member state and does not train on customer data.

Worked example as of 2026-09-23, from the public data image.

Inference in the EU, no training; cheapest first.

Requirements

• offering.region in {AT, BE, BG, HR, CY, CZ, DE, DK, EE, ES, FI, FR, GR, HU, IE, IT, LT, LU, LV, MT, NL, PL, PT, RO, SE, SI, SK}: Inference must run in one of the EU's 27 member-state ISO country codes (EU Publications Office Interinstitutional Style Guide, https://style-guide.europa.eu/en/content/-/isg/topic?identifier=annex-a5-list-countries-territories-currencies, checked 2026-09-27).
• offering.data.trains_on_customer_data = No: Customer prompts and outputs must not be available for model training.

Preferences

• -offering.cost_per_task: Prefer the lower task cost after the data-handling gates pass.
• chat_preference: Keep a quality signal so a cheap but poor assistant does not win on cost alone.

Worked answer

Decision status: no_feasible.

No recommendation: the public image has no answer with enough evidence.

Unknown requirements

Some candidates may qualify. Missing facts:

• offering.region

Missing evidence and possible changes

• offering.region in {AT, BE, BG, CY, CZ, DE, DK, EE, ES, FI, FR, GR, HR, HU, IE, IT, LT, LU, LV, MT, NL, PL, PT, RO, SE, SI, SK}

Decision dec_83c43adb457697db57e89656 on public snapshot snap_745a6b4354bbc69a.

What this template teaches

The gates are the same as the other tiers; only the ranking moves toward cost.

The live board uses current data. Its answer can change as evidence changes.

Apply this template on Decide

Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.

Guides · Use-case examples · Model comparisons · How we decide