主流大模型，生产级 API

from openai import OpenAI

client = OpenAI(base_url="https://api.monkey.ceo/v1", api_key="sk-…")
r = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "你好"}],
)
print(r.choices[0].message.content)
# 你好！今天想做点什么？
# r.usage → {"prompt_tokens": 9, "completion_tokens": 12, ...}复制

$ curl -N https://api.monkey.ceo/v1/chat/completions \
    -H "Authorization: Bearer sk-…" \
    -d '{"model":"gpt-4o-mini","stream":true,
         "messages":[{"role":"user","content":"你好"}]}'

data: {"choices":[{"delta":{"content":"你好"}}]}
data: {"choices":[{"delta":{"content":"！今天想"}}]}
data: {"choices":[{"delta":{"content":"做点什么？"}}]}
data: {"usage":{"prompt_tokens":9,"completion_tokens":12}}
data: [DONE]复制

HTTP/1.1 429 Too Many Requests
retry-after: 12

{"error": {
  "type": "rate_limit_error",
  "code": "requests_per_minute_exceeded",
  "message": "该 Key 每分钟请求数上限 (60) 已超出，请 12 秒后重试。"
}}复制

$ curl https://api.monkey.ceo/v1/dashboard/billing/subscription \
    -H "Authorization: Bearer sk-…"

{
  "object": "billing_subscription",
  "hard_limit_usd": 24.9991,
  "has_payment_method": true,
  "access_until": 0
}复制