IteraCompute를 통해 LiteLLM이 포함된 모델을 사용합니다.

import os
from litellm import completion

response = completion(
    model="openai/qwen/qwen3.8-27b",
    api_base="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=512,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(response.choices[0].message.content)

model_list:
  - model_name: itera-model
    litellm_params:
      model: openai/qwen/qwen3.8-27b
      api_base: https://api.iteracompute.com/v1
      api_key: os.environ/ITERACOMPUTE_API_KEY

python -m pip show litellm

# Bash / zsh / WSL; set ITERACOMPUTE_API_KEY in your environment first.
curl --fail-with-body https://api.iteracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","messages":[{"role":"user","content":"Reply with exactly: Hello!"}],"max_tokens":512}'