Qwen: Qwen4 Max

Image input Text input Video input Text output
Author's Description

Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....

Key Specifications
Cost
$$$$$
Context
1M
Released
Nov 15, 2026
Speed
★★★
Ability
★★★★★
Reliability
★★★★★
Supported Parameters

This model supports the following parameters:

Presence Penalty Frequency Penalty Top P Max Tokens Seed Tools Include Reasoning Temperature Logprobs Stop Top Logprobs Response Format Tool Choice Structured Outputs Reasoning
Features

This model supports the following features:

Reasoning Tools Structured Outputs Response Format
Performance Summary

Qwen4 Max, Alibaba's flagship multimodal model, delivers strong all-around performance highlighted by premier technical capabilities. In benchmark evaluations, the model excelled in the coding category, registering a stellar 96.0% accuracy on comprehensive programming assessments to place in the 94th percentile. This demonstrates exceptional problem-solving depth across varied programming languages and algorithmic tasks. From an operational standpoint, Qwen4 Max exhibits exceptional reliability, maintaining a flawless 100% success rate without technical failures or interrupted runs. In terms of latency, the model demonstrates competitive response times, positioning it around the median at the 55th percentile. It also features moderate pricing, placing it in the 32nd percentile among comparable alternatives. The model's primary strengths include its elite code intelligence, rock-solid operational dependability, and an expansive 1-million-token context window with built-in reasoning. Although its average response speeds and pricing profile indicate it is less suited for low-latency or ultra-budget micro-tasks, Qwen4 Max stands out as a highly capable and dependable solution for complex developer workflows, multimodal analysis, and demanding enterprise applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.43
Completion $4.28
Input Cache Read $0.0713
Input Cache Write $1.78

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen4-max-20261115 1M $1.43 / 1M tokens $4.28 / 1M tokens
Novita
Novita | qwen/qwen4-max-20261115 1M $1.43 / 1M tokens $4.28 / 1M tokens
DeepInfra
DeepInfra | qwen/qwen4-max-20261115 1M $1.43 / 1M tokens $4.28 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen