Qwen: Qwen Plus 0728 (thinking)
Qwen Plus 0728 (thinking) is an AI model capable of handling text inputs with an expansive context length of up to 1 million tokens and supports reasoning, making it suitable for complex tasks that require deep understanding and logical processing. It can integrate tools for enhanced functionality but does not support structured output directly. Given its pricing at $0.4 per million input tokens and $1.2 per million output tokens, Qwen Plus 0728 may be a cost-effective choice for projects requiring substantial text analysis or reasoning capabilities, especially when budget is a consideration. While lacking independent benchmark coverage currently, this model shines in scenarios where extensive text processing and tool integration are paramount.
- Model ID
- qwen/qwen-plus-2025-07-28:thinking
- Vendor
- qwen
- Released
- September 2025
- Tokenizer
- Qwen3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.40/M input and $1.20/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.26 |
| A month of a busy support chatbot | 5M in / 2M out | $4.40 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-07-30 | $0.40 | $1.20 | 1,000,000 |
| 2026-07-17 | $0.26 | $0.78 | 1,000,000 |
Similar models
Qwen: Qwen3 Next 80B A3B Thinking
Qwen: Qwen3 VL 235B A22B Instruct
Qwen: Qwen3 VL 8B Instruct
Qwen: Qwen3 VL 30B A3B Instruct
Qwen: Qwen3 235B A22B Thinking 2507
Qwen: Qwen3.7 Flash
Quick answers
- How much does Qwen: Qwen Plus 0728 (thinking) cost?
- $0.40 per million input tokens and $1.20 per million output tokens.
- What is Qwen: Qwen Plus 0728 (thinking)'s context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Qwen: Qwen Plus 0728 (thinking) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Qwen: Qwen Plus 0728 (thinking) process images?
- No, it is text-only on the input side.