Qwen Plus 0728 (thinking)
retiredAlibaba · Released Sep 2025
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.
- Strengths
- Handles both straightforward tasks and complex multi-step reasoning without significant speed penalties due to its hybrid architecture.
- Best for
- Applications requiring extended context windows and reasoning tasks where latency matters, such as document analysis, research synthesis, and code generation with dependencies.
- Limitations
- The hybrid reasoning approach may not match specialized reasoning-only models on pure reasoning benchmarks, and the full capabilities at extreme context window sizes are not well characterized yet.
Input / 1M
$0.26
Output / 1M
$0.78
Cached input / 1M
—
Context window
1M
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 35.0% out decreased 35.0%
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 15 Aug 2026 | $0.26 | $0.78 | — | Imported from OpenRouter | openrouter.ai |
| 29 Jul 2026 | $0.4 | $1.20 | — | Imported from OpenRouter | openrouter.ai |
| 29 Jun 2026 | $0.26 | $0.78 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.26 | $0.78 | — | Imported from OpenRouter | openrouter.ai |