☕
Cupang Proxy
Curated OpenAI-compatible gateway. 15 live models, key-pool powered, latency tracked.
15Models
60Total Requests
0In Flight
OpenAICompatible API

Endpoint

POST https://cupangproxy.tailfab3a7.ts.net/v1/chat/completions

Auth: Authorization: Bearer YOUR_API_KEY

🔑 Request an API key from the admin. Public keys are rate-limited (30 req/min, 2K req/day by default). Recommended default: cp/qwen3.5-397b; fast agentic: cp/glm-5.2; coding: cp/qwen3-coder-next.

Available Models (15)

ModelLive Latency 10m
cp/deepseek-v4-flash 2.4s
cp/deepseek-v4-pro 18.2s
cp/gemma-4-31b 0.3s
cp/glm-5.1 0.5s
cp/glm-5.2 0.5s
cp/gpt-oss-120b 0.4s
cp/kimi-k2.6 0.6s
cp/kimi-k2.7-code 6.1s
cp/minimax-m2.5 0.3s
cp/minimax-m2.7 5.8s
cp/minimax-m3 0.7s
cp/nemotron-3-super-120b 3.2s
cp/qwen3-coder-next 2.1s
cp/qwen3.5-397b 15.5s
cp/qwen3.6-35b 16.2s

Example (curl)

curl -X POST https://cupangproxy.tailfab3a7.ts.net/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cp/qwen3.5-397b",
    "messages": [{"role":"user","content":"Hello!"}]
  }'

Client Config

{
  "base_url": "https://cupangproxy.tailfab3a7.ts.net/v1",
  "api_key": "YOUR_API_KEY",
  "model": "cp/qwen3.5-397b"
}

Rate Limits