QUICK START

Set up in 5 minutes

One key works across every tool. Pick yours below. The API is live and self-serve — sign up, create a key, and you're running in minutes.

Claude Code
Cline / Roo Code
Cursor
Python / Node SDK
  1. Get your API key — sign up and create a key in the console; new accounts get free trial credits.
  2. Set two environment variables — add the lines on the right to ~/.zshrc, ~/.bashrc, or PowerShell.
  3. Run claude — you are now coding on Qwen 3.7 Max. Switch models anytime with /model.
shell
export ANTHROPIC_BASE_URL="https://api.gloritoken.ai"
export ANTHROPIC_AUTH_TOKEN="sk-your-key"
export ANTHROPIC_MODEL="qwen3.7-max"
  1. Install the extension — Cline or Roo Code from the VS Code marketplace.
  2. Choose provider — set API Provider to OpenAI Compatible.
  3. Fill three fields — base URL, API key, model ID (right). Save and go.
settings
Base URL: https://api.gloritoken.ai/v1
API Key:  sk-your-key
Model ID: qwen3.7-max
  1. Open model settings — Cursor → Settings → Models.
  2. Override the OpenAI endpoint — enable Override OpenAI Base URL and paste the address on the right; use your gloritoken key.
  3. Add a custom model — add qwen3.7-max to the model list and enable it.
settings
OpenAI Base URL: https://api.gloritoken.ai/v1
OpenAI API Key:  sk-your-key
Custom model:    qwen3.7-max
  1. Zero-rewrite migration — any OpenAI SDK code works; change base_url and api_key.
  2. Full feature support — streaming, function calling, JSON mode, long context.
  3. Billing you can audit — the usage field in every response is exactly what you are charged.
python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.gloritoken.ai/v1",
    api_key="sk-your-key",
)
resp = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[{"role":"user","content":"Write an LRU cache"}],
)
MODEL IDS

Model quick reference

One key, pick per request by model name. Every listed model is the maker's official API, priced 5% below the vendor's own rate.

ModelTypeNotesIn /1MOut /1M
qwen3.7-maxFlagshipAlibaba's newest trillion-parameter flagship, 1M ctx$1.19$3.56
qwen3.7-plusFlagshipMultimodal, best value, 256K ctx$0.30$1.22
kimi-k3FlagshipMoonshot 2.8T, 1M ctx, native vision$2.85$14.25
deepseek-v4-proFlagshipAll-round reasoning flagship, 1M ctx$0.41$0.83
deepseek-v4-flashValueCheapest high-volume option, 1M ctx$0.13$0.27
glm-5.2FlagshipZhipu's newest, coding + general, 128K ctx$1.33$4.18
qwen3-coder-flashCodingFast, low-cost coding, 1M ctx$0.19$0.93
kimi-k2.7-codeCodingMoonshot dedicated coder, 256K ctx$0.72$3.04
kimi-k2.7-code-highspeedExclusive~180–260 tok/s, no international reseller carries it$3.06$12.71
qwen-longExclusive10M-token context, document-scale jobs$0.19$0.47
qwen-maxGeneralProven all-round Qwen flagship, 256K ctx$1.19$3.56
qwen-turboLightweightCheapest lightweight option, 1M ctx$0.05$0.19

* Prices are flat per 1M tokens as billed by our gateway. All listed models are live now — official, full-quality builds from the makers' own APIs.

FAQ

Everything else

Where does my code go?

Your requests are processed on our Singapore gateway; inference runs on the model makers' official APIs, served from mainland China — stated plainly. We don't store prompt contents and never train on your data; we keep only usage metadata for billing. We do not relay Claude, GPT or Gemini.

Do you store or train on my prompts?

No. We keep only the usage metadata needed for billing (token counts, model, timestamps). Prompt and completion contents are not stored and never used for training.

Does Claude Code really work natively?

Yes. We expose a real Anthropic-protocol endpoint (/v1/messages), so Claude Code connects with two environment variables — no proxy hacks, no wrapper. Streaming, tool use and long context all work.

How do I pay?

Signing up gets you free trial credit. To add more, email hello@gloritoken.ai with (1) your account email and (2) the amount you'd like to add. We'll reply with our USD bank-transfer details and a payment reference. Once funds arrive we credit your balance — or send a redemption code (Console → Wallet → Redeem) — within one business day; your API key never changes. Invoice available on request. Billed in USD by Gloritoken (HK) Limited; credits never expire.

Do you offer Claude / GPT / Gemini?

No, and we never will — we are Chinese-frontier-model specialists, first-hand supply only. No gray-market relays, no "mirrors". That focus is exactly why you can trust the models you get are what they claim to be.