Qwen: Qwen Plus 0728 (thinking)Model25/100 via “explicit chain-of-thought reasoning with thinking tokens”
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.
Unique: Unlike standard CoT prompting which exposes reasoning in the output, Qwen Plus 0728 uses hidden thinking tokens that allow the model to reason internally before responding. This architecture is similar to OpenAI's o1 approach but integrated into a general-purpose model with 1M context, enabling reasoning-enhanced responses without cluttering the output or requiring post-processing to extract logic.
vs others: Provides reasoning capabilities comparable to o1 but with 8x larger context window (1M vs 128K) and lower latency, making it suitable for both reasoning-heavy tasks and long-context applications simultaneously