☕
Cupang Proxy
Curated OpenAI-compatible gateway. 14 live models, key-pool powered, latency tracked.
14Models
745Total Requests
19.7MTokens Served
4In 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/mimo-v2.5 (fast + tool-calling); fast agentic: cp/glm-5.2; coding: cp/qwen3-coder-next.

Available Models (14)

ModelLive Latency warming
cp/deepseek-v3.2 3.5s
cp/deepseek-v4-flash 1.5s
cp/deepseek-v4-pro 34.8s
cp/glm-4.7-flash 9.9s
cp/glm-5.1 2.2s
cp/glm-5.2 43.6s
cp/gpt-oss-120b 4.0s
cp/kimi-k2.5 4.1s
cp/kimi-k2.6 60.2s
cp/kimi-k2.7-code 4.4s
cp/minimax-m2.7 10.0s
cp/minimax-m3 12.5s
cp/nemotron-3-super-120b 2.7s
cp/step-3.5-flash 5.3s

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/mimo-v2.5",
    "messages": [{"role":"user","content":"Hello!"}]
  }'

Client Config

{
  "base_url": "https://cupangproxy.tailfab3a7.ts.net/v1",
  "api_key": "YOUR_API_KEY",
  "model": "cp/mimo-v2.5"
}

Rate Limits