Qwen3 Max Thinking

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-10-09. The figures below are the last recorded values.
Input price
$0.78
/ 1M tokens
Output price
$3.90
/ 1M tokens
Context
262K tokens
Max output 66K tokens

Overview

Alibaba's Qwen3 Max Thinking is positioned as a reasoning specialist model, likely a flagship tier offering, designed for complex analytical workloads. It targets applications requiring deep cognitive capabilities, extensive context processing, and sophisticated output generation.

Strengths

  • Advanced 'thinking' capabilities for complex problem-solving and analysis.
  • Very large 262,144 token context window for extensive document processing.
  • Generous 32,768 token maximum output for detailed, comprehensive responses.
  • Supports function-calling and JSON mode for structured agentic workflows.

Best use cases

  • Complex data analysis requiring deep conceptual understanding and reasoning.
  • Processing and synthesizing information from very long documents or dialogues.
  • Developing advanced AI agents with structured output and function-calling needs.
  • Generating comprehensive, detailed responses for high-stakes analytical tasks.

Pricing position

At $0.78/1M tokens for input and $3.9/1M tokens for output, Qwen3 Max Thinking is the most premium model within the Qwen family, significantly more expensive than models like Qwen3.5-9B ($0.04/M in). Its pricing aligns closely with Claude 3.5 Haiku ($0.8/M in, $4/M out) and GPT-5.4 Mini ($0.75/M in, $4.5/M out), placing it in the upper-mid range for advanced models.

Caveats

This model does not offer a free tier, which might be a consideration for initial development or low-volume testing. Its higher cost makes it less optimal for simpler, high-volume tasks that could be handled more cost-effectively by other Qwen models such as Qwen3.5-9B. Vision capabilities are not listed for this model, suggesting it may be limited to text-based inputs.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
66K tokens
Tracked since
2026-05-08
Last updated
2026-10-09

Features

Function callingJSON outputReasoning

Price history

  • 2026-10-09 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.27
1M (small app) 1 0.5 $2.73
10M (mid scale) 10 5 $27.30
100M (large) 100 50 $273.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API