A privacy-first inference gateway that proxies multiple LLM providers behind a single key. Metadata-only logging — we never store your prompts or responses. Billing by Stripe. Built to stay in the shadows.
Gatekeeping access to AI models, while staying in the shadows.
One key to rule them all. Generate, revoke and rotate keys from a single dashboard — no more scattering provider keys across your stack.
Route to local and cloud LLMs through one consistent interface. Switch models without rewriting your integration.
We log timestamps, model and usage counts for billing — never your content. No persistence of prompts or responses. No profiling.
Simple, transparent monthly plans. Payments processed securely by Stripe, in Australian dollars.
Clear usage dashboards so you know what you’re paying for, with no hidden data collection on the side.
The no-retention guarantee isn’t a policy line — it’s how the gateway is engineered.
Start free to try, upgrade when you’re ready. Billed monthly in AUD via Stripe.
Prices in AUD. See the full pricing page for details and the refund policy.
One key, one endpoint.
# Set your key once
export SHADOWGATE_API_KEY=sk_live_...
# Call any model through one endpoint
curl https://api.thetechcave.net/v1/inference \
-H "Authorization: Bearer $SHADOWGATE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"hi"}]}'Pick a plan, connect via Stripe, and start shipping in minutes.