Infrastructure & DevOps

Zro

Last updated 2026-07-16 · benchmark measured 2026-08-09 — deterministic & reproducible

Private open-model inference for coding agents, hosted on EU infrastructure.

Is Zro production-ready?

Legit.Show scores Zro 75 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Zro (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 70/100
• Accessibility — 96/100
• Security — 25/100
• Privacy — 75/100
• Reliability — 100/100
• Standards — 92/100
• Discoverability — 70/100

What we measured

• No Content-Security-Policy and no HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 1119 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• Has a reachable privacy policy.
• Sets cookies / loads scripts with no consent prompt.
• Discoverable: sitemap, OpenGraph image.

Who built it

product account @zroai_

Who it's for

Individual developers · Coding agent users · Teams requiring private inference · Multi-agent teams · Enterprises

Pricing

Pro $20/month (~300M tokens), Max $60/month (~1.5B tokens), Enterprise custom; per-model rates: MiniMax M3 $0.60/$2.40 per 1M input/output tokens, GLM-5.2 $1.10/$4.00 per 1M; usage packs $5-$100; web

Visit Zro → · Alternatives to Zro → · How this was measured →