Qwen Plus 0728 (thinking)

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-08-25. The figures below are the last recorded values.
Input price
$0.26
/ 1M tokens
Output price
$0.78
/ 1M tokens
Context
1M tokens
Max output 33K tokens

Overview

Alibaba's Qwen Plus 0728 is positioned as a premium reasoning specialist model within the Qwen family, targeting complex workloads requiring deep understanding and extensive context. It is designed for advanced analytical tasks, supported by its "thinking" capability and vast context window.

Strengths

  • Exceptional 1,000,000 token context window for extensive document processing.
  • "Thinking" capability indicates strong performance in complex reasoning tasks.
  • Supports function-calling for seamless integration with external tools and APIs.
  • Offers JSON mode for reliably structured and machine-readable output.
  • Generous 32,768 token maximum output for detailed, comprehensive responses.

Best use cases

  • Deep analysis of very long legal, technical, or research documents.
  • Orchestrating multi-step workflows requiring logical problem-solving and external calls.
  • Code analysis, debugging, and generation across large projects.
  • Complex data extraction and structured reporting from unstructured text.
  • Advanced chatbot or agent development needing sophisticated reasoning.

Pricing position

At $0.26/1M input and $0.78/1M output, Qwen Plus 0728 is Alibaba's most premium offering by price, significantly more expensive than other Qwen models like Qwen3.5-Flash ($0.065/$0.26). Its input price is competitive with peers like GPT-5 Mini and Claude 3 Haiku ($0.25/M), and its output price is generally lower than most of these peers, though higher than DeepSeek V3.2 ($0.378/M).

Caveats

This model does not offer a free tier. For less demanding tasks or shorter contexts, significantly cheaper Qwen models like Qwen3.5-9B or Qwen3.5-Flash are available and would be more cost-effective. Vision capabilities are not listed, potentially limiting its use in multimodal applications.

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

Key facts

Max output
33K tokens
Tracked since
2026-05-08
Last updated
2026-08-25

Features

Function callingJSON outputReasoning

Price history

  • 2026-08-25 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.07
1M (small app) 1 0.5 $0.65
10M (mid scale) 10 5 $6.50
100M (large) 100 50 $65.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API