Qwen3.6-Flash
复制成功！
概述
Qwen3.6原生视觉语言系列Flash模型，模型效果相较3.5-Flash显著提升。本模型重点提升agentic coding能力（在多项代码智能体基准上大幅超越前代）、数学推理和代码推理能力；视觉方面在空间智能能力上显著增强，物体定位与目标检测提升尤为突出。
输入
图像文本视频
输出
文本
功能
定价
- 输入¥1.2/M tokens
- 输出¥7.2/M tokens
- 输入（Batch File）¥0.6/M tokens
- 输出（Batch File）¥3.6/M tokens
- 显式缓存创建¥1.5/M tokens
- 显式缓存命中¥0.12/M tokens
- 输入（Batch Chat)¥1.2/M tokens
- 输出（Batch Chat)¥7.2/M tokens
速率限制与上下文
- 最大输入991K
- 最大输出65K
- 最大输入（思考模式）983K
- 最大输出（思考模式）65K
- 上下文1M
- 最大思维链131K
- TPM每分钟 Token 数10M
- RPM每分钟请求数30K
内置工具
API 参考
调用API复制成功！
123456789101112131415161718192021222324252627282930
from openai import OpenAI
import os
client = OpenAI(
# 如果没有配置环境变量，请用阿里云百炼API Key替换：api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://maas.qianwenaiapi.com/compatible-mode/v1",
)
messages = [{"role": "user", "content": "你是谁"}]
completion = client.chat.completions.create(
model="qwen3.6-flash", # 您可以按需更换为其它深度思考模型
messages=messages,
extra_body={"enable_thinking": True},
stream=True
)
is_answering = False # 是否进入回复阶段
print("\n" + "=" * 20 + "思考过程" + "=" * 20)
for chunk in completion:
if not chunk.choices:
continue
delta = chunk.choices[0].delta
if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
if not is_answering:
print(delta.reasoning_content, end="", flush=True)
if hasattr(delta, "content") and delta.content:
if not is_answering:
print("\n" + "=" * 20 + "完整回复" + "=" * 20)
is_answering = True
print(delta.content, end="", flush=True)123456789101112131415161718192021222324252627282930
from openai import OpenAI
import os
client = OpenAI(
# 如果没有配置环境变量，请用阿里云百炼API Key替换：api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://maas.qianwenaiapi.com/compatible-mode/v1",
)
messages = [{"role": "user", "content": "你是谁"}]
completion = client.chat.completions.create(
model="qwen3.6-flash", # 您可以按需更换为其它深度思考模型
messages=messages,
extra_body={"enable_thinking": True},
stream=True
)
is_answering = False # 是否进入回复阶段
print("\n" + "=" * 20 + "思考过程" + "=" * 20)
for chunk in completion:
if not chunk.choices:
continue
delta = chunk.choices[0].delta
if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
if not is_answering:
print(delta.reasoning_content, end="", flush=True)
if hasattr(delta, "content") and delta.content:
if not is_answering:
print("\n" + "=" * 20 + "完整回复" + "=" * 20)
is_answering = True
print(delta.content, end="", flush=True)