HOW IT WORKS

Where your requests go, stated plainly.

Most of this page is information other API resellers leave out. We would rather you learn it here than discover it later — including the parts that are inconvenient for us.

The path a request takes

There is no magic in the middle. We are a gateway in front of the model makers' own APIs.

1. Your app api.gloritoken.ai — our gateway, hosted in Singapore
2. Gateway the model maker's official API endpoint, in mainland China
3. The model runs there. Your prompt is processed there.
4. Response back through our gateway your app

Three consequences worth being explicit about:

What we store, and what we don't

  • We do not store the contents of your prompts or completions.
  • We never train on your data — we have no models to train.
  • We keep metadata for billing: timestamp, model name, token counts, status code. That is what your usage dashboard is built from.
  • We cannot promise anything about what the upstream vendor logs or retains. That is their system, governed by their terms.

If retention matters to you, read the upstream policy for the model you plan to use — Alibaba Cloud Model Studio (Bailian), Moonshot, DeepSeek or Zhipu — and decide based on that, not on our summary of it.

Pricing: the same discount, cached or uncached

Every price we charge — normal input, output, and cached input — is the vendor's own rate with the same discount applied. That means the cache maths you already know from going direct carries over unchanged: caching becomes worthwhile at exactly the same point it would with the vendor.

ModelVendor in (miss / hit)gloritoken in (miss / hit)Discount
Qwen 3.8 Max$2.00 / $0.17$1.04 / $0.13~48% / ~24%
Kimi K3$3.00 / $0.30$1.73 / $0.17~42% / ~42%
GLM 5.2$1.40 / (see vendor)$0.74 / $0.18~47%

Per 1M tokens. Vendor list rates as published, August 2026; explicit-cache creation fees follow the same rule.

The two exceptions, stated plainly. deepseek-v4-pro and kimi-k2.7-code-highspeed reach you through the vendors' own direct APIs, where we get no wholesale rate. Both are priced at vendor parity — the same rate you would pay going direct, cached tokens included. We earn nothing on either; they exist so one key covers every lab. If you only ever use these two models, we offer you convenience, not savings — going direct costs the same.

The headline: Qwen 3.8 Max at $1.04 / $3.11 against $2 / $6 on both the official API and OpenRouter — the same model, the same official source, 48% less. You can verify every number here with cn-llm-bench, an open-source tool we maintain that measures us against everyone else and prints the results exactly as measured.

Who should not use us

No vendor writes this section. We think that is why nobody trusts vendors. Do not use gloritoken if any of these apply:

  • You process personal data of EU/UK residents and need GDPR-compatible processing locations or a DPA with an approved transfer mechanism.
  • You work in a regulated industry — healthcare records, financial customer data, government work — with data residency obligations.
  • Your customer contracts prohibit sending data to mainland China, or require you to name and approve every subprocessor.
  • You need SOC 2, ISO 27001 or HIPAA attestations today. We do not have them.
  • You want a Claude, GPT or Gemini relay. We do not do that, at any price. Those vendors' models are not ours to resell.

If one of these is you, use the vendor's own international endpoint. That is the right answer, and we would rather say so than take money we should not have.

Who we are good for

Still unsure whether this is a fit? Email hello@gloritoken.ai and describe your use case. If the answer is "you should go direct", that is what you will get.