AI & Agents
Express API
Last updated 2026-07-28 · benchmark checked 2026-08-09 · unchanged since 2026-08-08 — deterministic & reproducible
Single API endpoint for accessing Chinese AI models including DeepSeek, Kimi, Qwen, and more.
Is Express API production-ready?
Legit.Show scores Express API 66 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Express API (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Performance; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 100/100
- Accessibility — 83/100
- Security — 25/100
- Privacy — 25/100
- Reliability — 75/100
- Standards — 82/100
- Discoverability — 70/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 363 ms to first byte.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: sitemap, OpenGraph image.
Who it's for
AI developers · LLM integrators · Agents · Code generation teams · High-throughput chat applications
Pricing
Pay-as-you-go; models range from $0.0002-$3.00 per 1M input tokens and $0.002-$15.00 per 1M output tokens
Visit Express API → · Alternatives to Express API → · How this was measured →