token
thinking_budget
Qwen3
max_tokens
context_length
finish_reason
length
from openai import OpenAI url = 'https://api.siliconflow.cn/v1/' api_key = 'your api_key' client = OpenAI( base_url=url, api_key=api_key ) # 发送带有流式输出的请求 content = "" reasoning_content="" messages = [ {"role": "user", "content": "奥运会的传奇名将有哪些?"} ] response = client.chat.completions.create( model="Pro/deepseek-ai/DeepSeek-R1", messages=messages, stream=True, # 启用流式输出 max_tokens=4096, extra_body={ "thinking_budget": 1024 } ) # 逐步接收并处理响应 for chunk in response: if chunk.choices[0].delta.content: content += chunk.choices[0].delta.content if chunk.choices[0].delta.reasoning_content: reasoning_content += chunk.choices[0].delta.reasoning_content # Round 2 messages.append({"role": "assistant", "content": content}) messages.append({'role': 'user', 'content': "继续"}) response = client.chat.completions.create( model="Pro/deepseek-ai/DeepSeek-R1", messages=messages, stream=True )
from openai import OpenAI url = 'https://api.siliconflow.cn/v1/' api_key = 'your api_key' client = OpenAI( base_url=url, api_key=api_key ) # 发送非流式输出的请求 messages = [ {"role": "user", "content": "奥运会的传奇名将有哪些?"} ] response = client.chat.completions.create( model="Pro/deepseek-ai/DeepSeek-R1", messages=messages, stream=False, max_tokens=4096, extra_body={ "thinking_budget": 1024 } ) content = response.choices[0].message.content reasoning_content = response.choices[0].message.reasoning_content # Round 2 messages.append({"role": "assistant", "content": content}) messages.append({'role': 'user', 'content': "继续"}) response = client.chat.completions.create( model="Pro/deepseek-ai/DeepSeek-R1", messages=messages, stream=False )