ai-agents-claude-thinking-para-when-using-claude-3-7-sonnet-model-with-thinking-p-b78206b3

THEN Remove the 'litellm_proxy/' prefix from the model name when using the proxy base URL, or set `litellm.drop_params=True` in your code or `drop_params: true` in the proxy config. Additionally, when thinking is enabled, ensure `budget_tokens` is at least 1024 and `temperature` is set to 1.

response = litellm.completion(
    api_key="sk-************",
    base_url="http://localhost:4000",
    model='claude-3-7-sonnet-20250219',
    messages=[{"role": "user", "content": "How can I solve world hunger?"}],
    max_tokens=2001,
    temperature=1,
    thinking={
        "type": "enabled",
        "budget_tokens": 2000
    }
)