AI & Agents
ModelHub
Last updated 2026-06-08 · benchmark measured 2026-06-10 — deterministic & reproducible
Single API gateway to 45 Chinese AI models, including DeepSeek and GLM-4.
Is ModelHub production-ready?
Legit.Show ran its deterministic 7-Frame production-readiness benchmark on ModelHub (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. The per-frame breakdown is public on the Legit.Show listing; the single overall production-readiness score is reserved for the verified maker.
The 7 Frames
- Performance — 89/100
- Accessibility — 84/100
- Security — 25/100
- Privacy — 100/100
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 85/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 135 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Discoverable: sitemap, OpenGraph image, canonical URL.
Who it's for
Developers · AI researchers · Cost-conscious API users · Organizations needing Chinese models · Businesses seeking alternatives to GPT
Pricing
Free tier with $5 credit and 1,000 requests; Starter $15/month (60M tokens); Pro $65/month (280M tokens); Enterprise custom pricing