Qwen: Qwen Plus 0728 (thinking)
Analysis Summary
Qwen Plus 0728 Thinking is a text model with a one-million-token context window, tool use, and function calling. The supplied data does not include benchmark results, so its reasoning strength, instruction following, and coding performance cannot be established from this record. Its extended context is a useful product feature, but not proof of accurate long-document analysis.
The combination of large context and tools is worth evaluating for document-heavy workflows, such as searching and synthesizing lengthy client materials. Since there are no measured quality results here, keep it out of unsupervised client-facing work until it passes evaluation for factual consistency, output structure, and tool reliability. Image input is not listed.
Low listed token prices make a pilot practical. Adopt only after comparing its long-context performance and thinking-mode latency with a proven model on representative tasks.
Assessed September 23, 2026
Editorial notes
Score capped at 45: no benchmark data available for this model.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Score capped at 45: no benchmark data available for this model.
How Qwen: Qwen Plus 0728 (thinking) compares
Its 1M-token context window is larger than 86% of the models we list. At $0.26 per million input tokens it is cheaper than 45% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.26 | $0.000260 |
| Output | $0.78 | $0.000780 |
What would Qwen: Qwen Plus 0728 (thinking) cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 697 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Qwen: Qwen Plus 0728 (thinking) for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout Qwen: Qwen Plus 0728 (thinking)
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
Frequently asked questions about Qwen: Qwen Plus 0728 (thinking)
How much does Qwen: Qwen Plus 0728 (thinking) cost?
Qwen: Qwen Plus 0728 (thinking) costs $0.26 per million input tokens and $0.78 per million output tokens.
What is the context window of Qwen: Qwen Plus 0728 (thinking)?
Qwen: Qwen Plus 0728 (thinking) has a context window of 1,000,000 tokens (1M).
What can Qwen: Qwen Plus 0728 (thinking) do?
Qwen: Qwen Plus 0728 (thinking) supports tool use and function calling.
Who created Qwen: Qwen Plus 0728 (thinking)?
Qwen: Qwen Plus 0728 (thinking) is developed by Qwen and was released on September 8, 2025.