Qwen: Qwen3 Max Thinking

Text input Text output
Author's Description

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.

Key Specifications
Cost
$$$$$
Context
262K
Released
Feb 09, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Tools Response Format Reasoning Structured Outputs
Performance Summary

Qwen3 Max Thinking, released by qwen in February 2026, is positioned as a flagship reasoning model for complex cognitive tasks. It demonstrates competitive response times, ranking in the 41st percentile for speed across benchmarks. Its pricing is moderate, falling into the 27th percentile. A standout feature is its exceptional reliability, achieving a perfect 100% success rate across all evaluated benchmarks, indicating consistent and usable responses. The model exhibits significant strengths in several key areas. It achieves perfect accuracy in Hallucinations (Baseline) and Ethics (Baseline), indicating strong alignment with factual integrity and ethical principles, often at competitive price points and speeds. Its performance in Coding (96.0% accuracy, 97th percentile) and Mathematics (96.0% accuracy, 93rd percentile) is particularly impressive, showcasing advanced capabilities in these technical domains. While its Instruction Following (70.0% accuracy, 74th percentile) and Reasoning (88.0% accuracy, 69th percentile) are solid, its General Knowledge (84.5% accuracy, 23rd percentile) is a relative weakness, suggesting room for improvement in breadth of factual recall. Overall, Qwen3 Max Thinking excels in tasks requiring deep reasoning and precision, making it well-suited for high-stakes applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.78
Completion $3.9

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen3-max-thinking-20260123 262K $0.78 / 1M tokens $3.9 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen