Developer Tools
gm
Last updated 2026-07-27 · benchmark measured 2026-07-27 — deterministic & reproducible
Privacy-focused API gateway for Claude, GPT, Gemini, and other frontier models.
Is gm production-ready?
Legit.Show ran its deterministic 7-Frame production-readiness benchmark on gm (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Privacy. 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 — 84/100
- Accessibility — 100/100
- Security — 80/100
- Privacy — 25/100
- Reliability — 100/100
- Standards — 86/100
- Discoverability — 85/100
What we measured
- Security headers present: CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- No HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 571 ms to first byte.
- Returns a proper 404 for unknown routes.
- 2 of 2 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
AI developers · AI application builders · Teams using Cursor or Cline · Privacy-conscious AI users · Enterprises
Pricing
Per-token pricing: claude-opus $5.00 input/$25.00 output per million tokens; claude-sonnet $3.00/$15.00; gpt-5.5 $5.00/$30.00; gemini-2.5-flash $0.30/$2.50 (varies by model); no subscription fees