Reasoning

DeepSeek V4.1 Flash 1017 and GLM-5.3 Flash think before they answer. You can read the thinking and choose how much of it to spend.

Thinking and effort

The thinking comes back in choices[0].message.reasoning_content and the answer in choices[0].message.content. Set reasoning_effort to low, high, or max, or to none to skip thinking for faster, cheaper replies.

Python

response = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-uncensored",
    messages=[{"role": "user", "content": "Plan a 3-day trip to Kyoto."}],
    reasoning_effort="high",  # "low", "high", "max", or "none" to skip thinking
)

message = response.choices[0].message
print(getattr(message, "reasoning_content", None))  # the model's thinking
print(message.content)                              # the final answer

With tool calls

Send the assistant message back unchanged, including reasoning_content and tool_calls, followed by the tool results. See Tool calling.

Anthropic and Responses

On those endpoints, effort names map to the nearest level the model has: medium runs as high, and xhigh as max.