☕
Cupang Proxy
Curated OpenAI-compatible gateway. 14 live models, key-pool powered, latency tracked.
14Models
1291Total Requests
63.6MTokens Served
2In Flight
OpenAICompatible API

Endpoint

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

Auth: Authorization: Bearer YOUR_API_KEY

Bring your own key (Authorization: Bearer YOUR_API_KEY). Recommended: cp/glm-4.7-flash (fast + tool-calling) · balanced agentic cp/glm-5.2 · long-context/code cp/deepseek-v3.2.

Available Models (14)

waiting for live data…

Latency by model — fastest first

warming up…
ModelLive Latency warming
cp/deepseek-v3.2 7.7s
cp/deepseek-v4-flash 43.1s
cp/deepseek-v4-pro 108.5s
cp/glm-4.7-flash 17.9s
cp/glm-5.1 38.3s
cp/glm-5.2 50.0s
cp/gpt-oss-120b 2.7s
cp/kimi-k2.5 13.7s
cp/kimi-k2.6 warming
cp/kimi-k2.7-code warming
cp/minimax-m2.7 warming
cp/minimax-m3 warming
cp/nemotron-3-super-120b 5.8s
cp/step-3.5-flash warming

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/glm-4.7-flash",
    "messages": [{"role":"user","content":"Hello!"}]
  }'

Client Config

{
  "base_url": "https://cupangproxy.tailfab3a7.ts.net/v1",
  "api_key": "YOUR_API_KEY",
  "model": "cp/glm-4.7-flash"
}