Qwen3.7-Max

qwen3.7-max

Qwen series

Overview

1M ContextDocument analysisMultilingualCreative writing

Qwen3.7-Max is the Max tier of the Qwen3.7 series at 720B parameters, positioned as a general-purpose flagship. It ranks at the top for complex knowledge reasoning, long-document comprehension, professional writing and cross-lingual tasks, with native million-token context and tiered thinking modes. It can serve as an enterprise knowledge hub or, at the higher Token Plan tier, as the primary model for development and production — covering everything from research to large-scale deployment.

720B flagship scale

The top parameter tier of the Qwen3.7 series, covering the hardest knowledge-reasoning and multilingual tasks.

Deep reasoning

Thinking mode can be toggled to handle complex multi-step reasoning and long-chain decision tasks.

Million-token context

A near-million-token context window (991.8K) covers long documents, extended reports and multi-turn tasks.

Stable at high concurrency

RPM 30K / TPM 5M sustains steady output for high-traffic online workloads.

Features

Prefix completion✓

Context caching✓

Structured output✓

Batch✓

Web search✓

Vision✕

Fine-tuning✕

Pricing

Input¥12/M tokens

Output¥36/M tokens

Input (cache hit)¥1.2/M tokens

Cache write¥15/M tokens

Built-in Tools (billed per call)

web_search¥0.01/call

code_interpreter¥0.02/call

web_extractor¥0.01/call

Rate Limits & Context

Context Window1M

Max Output64K

RPM (requests/min)30K

TPM (tokens/min)5M

Built-in Tools

web_search

Responses API

code_interpreter

Responses API

web_extractor

Responses API

API Reference

ENDPOINT

POST https://api.tokenfab.cn/v1/chat/completions

Request Example

curl https://api.tokenfab.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKENFAB_API_KEY" \
  -d '{
    "model": "qwen3.7-max",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "写一段关于秋天的现代诗。"}
    ]
  }'

import os
from dashscope import Generation
import dashscope

dashscope.base_http_api_url = 'https://dashscope.aliyuncs.com/api/v1'

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': '写一段关于秋天的现代诗。'}
]
response = Generation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3.7-max',
    messages=messages,
    result_format='message',
    enable_thinking=True,
)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOKENFAB_API_KEY,
  baseURL: "https://api.tokenfab.cn/v1"
});

const response = await client.chat.completions.create({
  model: "qwen3.7-max",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "写一段关于秋天的现代诗。" }
  ]
});

console.log(response.choices[0].message.content);

Response Example

JSON

{
  "id": "chatcmpl-q3m7x2p8",
  "object": "chat.completion",
  "created": 1784950000,
  "model": "qwen3.7-max",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "我是 Qwen3.7-Max，720B 参数规模的旗舰通用大模型，支持百万级上下文与多档思考模式，适合复杂知识推理与高质量生成任务。"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 16,
    "completion_tokens": 48,
    "total_tokens": 64
  }
}

Request Parameters

Parameter	Type	Required	Description
model	string	✓	Model ID, e.g. qwen3.7-max
messages	array	✓	List of chat messages, each with role and content
temperature	float	—	Sampling temperature, 0–2, default 0.7
top_p	float	—	Nucleus sampling, 0–1, default 0.9
max_tokens	int	—	Maximum output tokens
stream	bool	—	Whether to stream the response, default false
tools	array	—	Tool definitions for function calling
tool_choice	string	—	Tool choice policy: auto / none / a named function