Qwen Plus 0728 (thinking) Model Specs, Costs & Benchmarks (July 2026)
Qwen Plus 0728 (thinking), developed by Qwen, features a context window of 1M tokens. The model costs $0.26 per million tokens for input and $0.78 per million tokens for output. It was released on September 8, 2025, and has achieved impressive scores in various benchmarks.
Access Qwen Plus 0728 (thinking) & 210+ other AI models all in one platformTry Magica for free
Overview
 Qwen Plus 0728 (thinking) | |
|---|---|
Model Provider The organization behind this AI's development | Qwen |
Input Context Window Maximum input tokens this model can process at once | 1M tokens |
Output Token Limit Maximum output tokens this model can generate at once | 32.8K tokens |
Release Date When this model first became publicly available | September 8, 2025 10 months ago September 8th, 2025 |
Knowledge Cutoff Latest training-data date reported by the provider | March 31, 2025 |
Pricing
| Qwen Plus 0728 (thinking) | |
|---|---|
Short Context Pricing Base rates before a long-context threshold applies | |
Input Token Cost Cost per million input tokens | $0.26 per million tokens |
Output Token Cost Cost per million output tokens | $0.78 per million tokens |
Cache Write Cost Cost to write input tokens to the cache | $0.33 per million tokens |
Long Context Pricing Rates for prompts with 256,000 or more tokens | |
Input Token Cost Long-context input cost per million tokens | $0.78 per million tokens |
Output Token Cost Long-context output cost per million tokens | $2.34 per million tokens |
Cache Write Cost Long-context cache write cost per million tokens | $0.97 per million tokens |
Capabilities & Features
| Qwen Plus 0728 (thinking) | |
|---|---|
Input Types Supported input formats | text |
Output Types Supported output formats | text |
Tokenizer Text encoding system | Qwen3 |
Key Features Advanced capabilities | ✓ Function Calling✓ Structured Output✓ Reasoning Mode |
Reasoning Controls Defaults and configurable reasoning effort | Optional |
Compare This Model
See how Qwen Plus 0728 (thinking) compares with other top models
Compare Qwen Plus 0728 (thinking) with top models in each category:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks
