Qwen3.7-Max-2026-05-17

Qwen3.7-Max

Copied!

Try AIAdd to Compare

ReasoningText Generation

Overview

ReasoningText Generation

The early version of the Max model in the Qwen3.7 series supports only the reasoning mode and makes its plain-text capabilities available for experimentation. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric era, with major improvements in coding and agent‑level capabilities. This release is a snapshot as of May 17, 2026.

Input

Text

Output

Text

Features

Prefix Completion

Function Calling

Cache

Structured Outputs

Batches

Web Search

Pricing

Input
$2.5Per 1M tokens
Output
$7.5Per 1M tokens

Context

Max Input

991.80K

Max Output

65.53K

Rate Limits

RPMRequests Per Minute
600
TPMTokens Per Minute
1M

Built-in Tools

code_interpreterResponses API

web_extractorResponses API

web_searchResponses API

API Reference

Get API Key

Copied!

12345678910111213141516171819202122232425262728293031323334353637

import os
from dashscope import Generation
import dashscope
dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1/"

messages = [{"role": "user", "content": "Who are you"}]

completion = Generation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3.7-max-2026-05-17",
    messages=messages,
    result_format="message", 
    stream=True,
    incremental_output=True, 
)

is_answering = False

print("=" * 20 + "Thinking process" + "=" * 20)

for chunk in completion:
    if (
        chunk.output.choices[0].message.content == ""
        and chunk.output.choices[0].message.reasoning_content == ""
    ):
        pass
    else:
        if (
            chunk.output.choices[0].message.reasoning_content != ""
            and chunk.output.choices[0].message.content == ""
        ):
            print(chunk.output.choices[0].message.reasoning_content, end="", flush=True)
        elif chunk.output.choices[0].message.content != "":
            if not is_answering:
                print("\n" + "=" * 20 + "Full response" + "=" * 20)
                is_answering = True
            print(chunk.output.choices[0].message.content, end="", flush=True)

import os
from dashscope import Generation
import dashscope
dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1/"

messages = [{"role": "user", "content": "Who are you"}]

completion = Generation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3.7-max-2026-05-17",
    messages=messages,
    result_format="message", 
    stream=True,
    incremental_output=True, 
)

is_answering = False

print("=" * 20 + "Thinking process" + "=" * 20)

for chunk in completion:
    if (
        chunk.output.choices[0].message.content == ""
        and chunk.output.choices[0].message.reasoning_content == ""
    ):
        pass
    else:
        if (
            chunk.output.choices[0].message.reasoning_content != ""
            and chunk.output.choices[0].message.content == ""
        ):
            print(chunk.output.choices[0].message.reasoning_content, end="", flush=True)
        elif chunk.output.choices[0].message.content != "":
            if not is_answering:
                print("\n" + "=" * 20 + "Full response" + "=" * 20)
                is_answering = True
            print(chunk.output.choices[0].message.content, end="", flush=True)