LiteLLM 접속 가이드

import json
import os
from pathlib import Path
from urllib.error import HTTPError, URLError
from urllib.parse import urlencode
from urllib.request import HTTPRedirectHandler, Request, build_opener


class NoRedirect(HTTPRedirectHandler):
    def redirect_request(self, req, fp, code, msg, headers, newurl):
        return None


key = os.environ["CRAZYROUTER_API_KEY"]
if not key:
    raise SystemExit("CRAZYROUTER_API_KEY is empty")
query = urlencode({
    "provider": "openai",
    "models": "claude-opus-5-5,gpt-6-astra,glm-5.3,deepseek-v4.1-flash",
})
request = Request(
    "https://api.crazyrouter.com/v1/litellm/config?" + query,
    headers={"Authorization": "Bearer " + key,
             "User-Agent": "Crazyrouter-LiteLLM-Setup/1.0"},
)
try:
    with build_opener(NoRedirect).open(request, timeout=30) as response:
        payload = json.load(response)
except HTTPError as error:
    raise SystemExit(f"Export failed (HTTP {error.code}); no file written.")
except URLError:
    raise SystemExit("Export connection failed; no file written.")

config = payload["config"]
if not config.get("model_list"):
    raise SystemExit("Export contains no models")
config.setdefault("litellm_settings", {})["drop_params"] = False
config.setdefault("general_settings", {})["master_key"] = "os.environ/LITELLM_MASTER_KEY"
output = json.dumps(config, ensure_ascii=False, indent=2)
if key in output:
    raise SystemExit("Refusing to write a secret")
with Path("crazyrouter.config.json").open("x", encoding="utf-8") as handle:
    handle.write(output + "\n")
print("Saved configuration. Import/reload it in LiteLLM explicitly.")

import json
import os
from urllib.request import Request, urlopen

base = "http://127.0.0.1:4100/v1"
headers = {"Authorization": "Bearer " + os.environ["LITELLM_MASTER_KEY"],
           "Content-Type": "application/json"}

with urlopen(Request(base + "/models", headers=headers), timeout=30) as response:
    models = json.load(response)["data"]
assert any(model["id"] == "gpt-6-astra" for model in models), "Model not registered"

body = {"model": "gpt-6-astra", "max_tokens": 1024,
        "messages": [{"role": "user", "content": "Reply with exactly OK."}]}
with urlopen(Request(base + "/chat/completions", headers=headers,
                     data=json.dumps(body).encode()), timeout=120) as response:
    result = json.load(response)
choice = result["choices"][0]
assert choice["finish_reason"] == "stop", "Incomplete response"
assert (choice["message"].get("content") or "").strip() == "OK", "Check final answer"
assert result.get("usage", {}).get("total_tokens", 0) > 0, "Missing usage"
print("PASS: model registration, final answer, finish reason, usage")