Trust & data
What we store (not your prompts), how we source models compliantly, and the measured-savings pledge.
Where your money and your code go.
A gateway sits between you and the model, so it is worth knowing exactly what it does with your data and where the models come from. Here is the whole policy, in plain language.
Is my code retained or trained on?
The gateway meters tokens, not content. Each usage record holds counts, the model that answered, timing, and a routing signal vector — never the text of your prompts or completions. There is no prompt log to leak, subpoena or train on, because it does not exist.
Where does my money sit?
Balances are prepaid and processed by the payment provider you choose — bKash, Nagad, UPI or card. We do not store card or wallet credentials. Consumed tokens are non-refundable; unused balance stays on your account. Prices are shown tax-inclusive where local rules require it.
Where do the models come from?
Open-weight Chinese models are the price leaders, and we serve them carefully. GLM is routed through US-based inference hosts rather than a single origin, which is the industry-standard, compliance-aware way to serve it. We keep a diverse catalogue — GLM, DeepSeek, Qwen — so no single supplier is a point of failure, and we remove any model whose supply or compliance status is unsettled, which is why Kimi is not currently listed.
Can I verify the savings claim?
This market is full of invented “tokens saved” counters. We do not do that. Every savings figure we show is computed from the metering ledger for your actual traffic, and the routing methodology is public. If a number cannot be measured, we do not display it — which is why there is no site-wide savings percentage anywhere on this site yet.
If a sourcing question ever affects availability, we would rather drop a lane than quietly serve something we should not. Catalogue changes are visible on the models page.