☕
Cupang Proxy
OpenAI-compatible LLM gateway. 20 native tool-calling models, ready to use.
20Models
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).

Available Models (20)

ModelLive Latency 10m
cp/deepseek-v4-flash 1.3s
cp/deepseek-v4-pro 1.8s
cp/gemma-4-31b warming
cp/glm-5 0.4s
cp/glm-5.1 0.5s
cp/glm-5.2 warming
cp/gpt-oss-120b warming
cp/kimi-k2-thinking warming
cp/kimi-k2.5 warming
cp/kimi-k2.6 warming
cp/kimi-k2.7-code warming
cp/minimax-m2.5 warming
cp/minimax-m2.7 21.8s
cp/minimax-m3 0.5s
cp/nemotron-3-super-120b warming
cp/qwen3-coder-480b warming
cp/qwen3-coder-next warming
cp/qwen3.5-397b warming
cp/qwen3.6-35b warming
cp/qwythos-9b-claude-mythos-5-1m 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/deepseek-v4-flash",
    "messages": [{"role":"user","content":"Hello!"}]
  }'

Client Config

{
  "base_url": "https://cupangproxy.tailfab3a7.ts.net/v1",
  "api_key": "YOUR_API_KEY",
  "model": "cp/deepseek-v4-flash"
}

Rate Limits