Developer Tools
Nace
Last updated 2026-10-09 · benchmark measured 2026-10-09 — deterministic & reproducible
Nace provides document intelligence and decision models through a single API.
Nace at a glance
Nace is a single API that gives developers document intelligence (NDI) for reading and extracting data from files and a decision model (Drex) that assigns calibrated probabilities to automated decisions.
Good for
- Extracting and grounding data from many file types with source citations for an AI agent or workflow
- Adding a probability-scored decision step (such as routing, ranking, or classification) into an automated workflow
- Integrating document reading and decision-making through one API key instead of separate tools
Questions people ask
What does Nace actually do?
It offers two models under one API: NDI, which parses, classifies, and extracts data from documents with source citations, and Drex, which assigns calibrated probabilities to decisions.
Who is Nace built for?
Developers, enterprise automation teams, finance and procurement teams, AI agents, and workflow builders.
What file types can NDI read?
NDI reads 36 file types and uses OCR and transcription to process them.
What tools and languages does Nace work with?
Nace works with TypeScript, Python, a CLI, and MCP.
Can I run Nace's models myself instead of using the API?
Yes, the models can be self-hosted; weights are available on GitHub and Hugging Face, including Drex 1.5.
Written by Legit.Show from nace.ai on 2026-10-10. It does not change the score.
Are you the maker of Nace? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/nace-ai/2026-10-09. That address never changes; this page moves with every re-measure.
Legit.Show scored Nace 72/100 on 2026-10-09, measured across all 7 frames from its public surface. legit.show/s/nace-ai/2026-10-09
Is Nace production-ready?
Legit.Show scores Nace 72 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Nace (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 73/100
- Accessibility — 96/100
- Security — 45/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 0/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 141 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
product account @NaceAI
Who it's for
Developers · Enterprise automation teams · Finance & procurement teams · AI agents · Workflow builders
Sources and updates
- Description
- Taken from nace.ai's own website on 2026-10-09.
- Operator
- Nace.AI, as named in nace.ai's terms, privacy page or footer.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-10-09.
Put together from public information, without Nace's involvement. If anything here is wrong, tell us and a person will check it.
Visit Nace → · Alternatives to Nace → · How this was measured →