推理模型（Reasoning）

export API_KEY="YOUR_API_KEY"

import os
from openai import OpenAI

BASE_URL = "https://api.siflow.cn/model-api"
API_KEY = os.environ["API_KEY"]

client = OpenAI(base_url=BASE_URL, api_key=API_KEY)

messages = [{"role": "user", "content": "Which is the largest anime website in China?"}]

content = ""
reasoning = ""

resp = client.chat.completions.create(
    model="Qwen/Qwen3-32B",
    messages=messages,
    stream=True,
    max_completion_tokens=4096,
    extra_body={"thinking_budget": 1024},
)

for chunk in resp:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if getattr(delta, "content", None):
        content += delta.content
        print(delta.content, end="", flush=True)
    if getattr(delta, "reasoning", None):
        reasoning += delta.reasoning

# Optionally persist the reasoning text for debugging/audit

# Round 2 (continue the conversation)
messages.append({"role": "assistant", "content": content})
messages.append({"role": "user", "content": "Continue"})

resp2 = client.chat.completions.create(
    model="Qwen/Qwen3-32B",
    messages=messages,
    stream=True,
)

for chunk in resp2:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if getattr(delta, "content", None):
        print(delta.content, end="", flush=True)

import os
from openai import OpenAI

BASE_URL = "https://api.siflow.cn/model-api"
API_KEY = os.environ["API_KEY"]

client = OpenAI(base_url=BASE_URL, api_key=API_KEY)

messages = [{"role": "user", "content": "Which is the largest anime website in China?"}]

resp = client.chat.completions.create(
    model="Qwen/Qwen3.5-397B-A17B",
    messages=messages,
    stream=False,
    max_completion_tokens=4096,
    extra_body={"thinking_budget": 1024},
)

content = resp.choices[0].message.content
reasoning = getattr(resp.choices[0].message, "reasoning", "")
finish_reason = resp.choices[0].finish_reason

# Round 2 (continue the conversation)
messages.append({"role": "assistant", "content": content})
messages.append({"role": "user", "content": "Continue"})

resp2 = client.chat.completions.create(
    model="Qwen/Qwen3.5-397B-A17B",
    messages=messages,
    stream=False,
)

print(resp2.choices[0].message.content)