要求#
Python 3.11 或更高版本。无需额外包。将 WEIGHTSAPI_API_KEY 设置为您的密钥。AI 访问需要登录、一次至少 100 美元的确认充值、一个已授权的 API 密钥以及足够的可用余额。每次后续充值的最低金额也为 100 美元；较小的剩余余额在足以支付请求时仍可使用。余额需要交易验证。发送流量前请查看服务状态 了解模型可用性。
运行该配方#
import os, json, urllib.request
BASE = os.environ.get("WEIGHTSAPI_BASE_URL", "https://weightsapi.com/v1")
KEY = os.environ["WEIGHTSAPI_API_KEY"]
def chat(messages, model="Qwen/Qwen3-32B", **options):
payload = dict(model=model, messages=messages, max_tokens=512, **options)
req = urllib.request.Request(BASE+"/chat/completions", json.dumps(payload).encode(),
{"Authorization": "Bearer "+KEY, "Content-Type": "application/json"})
with urllib.request.urlopen(req, timeout=120) as response:
return json.load(response)
question = input("Question: ")
complex_task = len(question) > 300 or any(w in question.lower() for w in ("prove", "derive", "analyze", "debug"))
model = "deepseek-ai/DeepSeek-R1-0528" if complex_task else "meta-llama/Llama-3.1-8B-Instruct"
response = chat([{"role":"user","content":question}], model=model)
print("Selected:", model)
print(response["choices"][0]["message"]["content"])
print("Usage:", response.get("usage"))
上线前#
该路由规则是一种透明的启发式方法，并非经过验证的难度分类器。在依赖其节省成本之前，请根据您的工作负载对其进行评估。