Qwen3.7-Flash
复制成功！
立即体验加入对比
概述
Qwen3.7原生视觉语言系列Flash模型，相较3.6-Flash全面提升多模态理解与Agent执行能力。重点强化多模态基础能力、万物识别能力更强，真实世界感知与空间智能进一步提升，Search Agent、CI Agent等多模态Agent场景能力显著升级、端到端任务执行更稳定，多模态Coding能力优化、vibe coding 体验更加流畅。该版本为2026年7月15日快照。
输入
图像文本视频
输出
文本
功能
定价
- 输入¥0.2/M tokens
- 输出¥0.8/M tokens
- 输入（缓存命中）¥0.04/M tokens
- 输入（Batch File）¥0.1/M tokens
- 输出（Batch File）¥0.4/M tokens
- 显式缓存创建¥0.25/M tokens
- 显式缓存命中¥0.02/M tokens
- 输入（Batch Chat)限时5折¥0.2¥0.1/M tokens
- 输出（Batch Chat)限时5折¥0.8¥0.4/M tokens
- 输入¥0.2/M tokens
- 输出¥0.8/M tokens
- 输入（缓存命中）¥0.04/M tokens
- 输入（Batch File）¥0.1/M tokens
- 输出（Batch File）¥0.4/M tokens
- 显式缓存创建¥0.25/M tokens
- 显式缓存命中¥0.02/M tokens
- 输入（Batch Chat)限时5折¥0.2¥0.1/M tokens
- 输出（Batch Chat)限时5折¥0.8¥0.4/M tokens
速率限制与上下文
- 最大输入991K
- 最大输出131K
- 最大输入（思考模式）983K
- 最大输出（思考模式）131K
- 上下文1M
- 最大思维链262K
- TPM每分钟 Token 数5M
- 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://dashscope.aliyuncs.com/compatible-mode/v1",
)
messages = [{"role": "user", "content": "你是谁"}]
completion = client.chat.completions.create(
model="qwen3.7-flash-2026-07-15", # 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://dashscope.aliyuncs.com/compatible-mode/v1",
)
messages = [{"role": "user", "content": "你是谁"}]
completion = client.chat.completions.create(
model="qwen3.7-flash-2026-07-15", # 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)