Infrastructure & DevOps
Baseten
Last updated 2026-08-03 · benchmark measured 2026-08-03 — deterministic & reproducible
Baseten is a production inference platform for deploying and scaling AI models on GPUs.
Is Baseten production-ready?
Legit.Show scores Baseten 74 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Baseten (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Performance. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 39/100
- Accessibility — 83/100
- Security — 65/100
- Privacy — 70/100
- Reliability — 100/100
- Standards — 76/100
- Discoverability — 85/100
What we measured
- Security headers present: CSP, HSTS, X-Frame-Options.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 331 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, canonical URL.
Who built it
product account @baseten
Who it's for
ML engineers · AI product teams · enterprises · startups
Pricing
Basic: $0/month pay-as-you-go; Pro: volume discounts available; Enterprise: custom pricing. Model APIs from $0.028-$3.00 per 1M tokens input. GPU instances from $0.01/min (T4) to $0.17/min (B200)