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.
export ANTHROPIC_BASE_URL="https://api.gloritoken.ai" export ANTHROPIC_AUTH_TOKEN="sk-your-key" export ANTHROPIC_MODEL="qwen3.7-max"
Base URL: https://api.gloritoken.ai/v1 API Key: sk-your-key Model ID: qwen3.7-max
OpenAI Base URL: https://api.gloritoken.ai/v1 OpenAI API Key: sk-your-key Custom model: qwen3.7-max
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"}], )
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.
| Model | Type | Notes | In /1M | Out /1M |
|---|---|---|---|---|
| qwen3.7-max | Flagship | Alibaba's newest trillion-parameter flagship, 1M ctx | $1.19 | $3.56 |
| qwen3.7-plus | Flagship | Multimodal, best value, 256K ctx | $0.30 | $1.22 |
| kimi-k3 | Flagship | Moonshot 2.8T, 1M ctx, native vision | $2.85 | $14.25 |
| deepseek-v4-pro | Flagship | All-round reasoning flagship, 1M ctx | $0.41 | $0.83 |
| deepseek-v4-flash | Value | Cheapest high-volume option, 1M ctx | $0.13 | $0.27 |
| glm-5.2 | Flagship | Zhipu's newest, coding + general, 128K ctx | $1.33 | $4.18 |
| qwen3-coder-flash | Coding | Fast, low-cost coding, 1M ctx | $0.19 | $0.93 |
| kimi-k2.7-code | Coding | Moonshot dedicated coder, 256K ctx | $0.72 | $3.04 |
| kimi-k2.7-code-highspeed | Exclusive | ~180–260 tok/s, no international reseller carries it | $3.06 | $12.71 |
| qwen-long | Exclusive | 10M-token context, document-scale jobs | $0.19 | $0.47 |
| qwen-max | General | Proven all-round Qwen flagship, 256K ctx | $1.19 | $3.56 |
| qwen-turbo | Lightweight | Cheapest 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.
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.
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.
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.
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.
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.