AI & Agents
OpenRouter
Last updated 2026-08-03 · benchmark measured 2026-08-03 — deterministic & reproducible
A unified API providing access to 400+ AI language models from 70+ providers.
Is OpenRouter production-ready?
Legit.Show scores OpenRouter 90 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on OpenRouter (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Performance. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 61/100
- Accessibility — 96/100
- Security — 100/100
- Privacy — 100/100
- Reliability — 75/100
- Standards — 100/100
- Discoverability — 100/100
What we measured
- Security headers present: CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 144 ms to first byte.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who it's for
AI developers · API users · Teams · Enterprises · LLM applications
Pricing
Free tier with 25+ models; Pay-as-you-go with 5% fee; Enterprise plans available; 5.5% fee discount option