Qwen: Qwen-Plus
🧠 AI Modelqwen
High-performance text model with 1M token context, balancing speed and cost.
Qwen-Plus is a large language model developed by Qwen, built upon the Qwen2.5 architecture. It is designed for text-only tasks and supports a context length of 1,000,000 tokens, enabling processing of very long documents. The model achieves a balanced combination of performance, speed, and cost efficiency. It supports common LLM features including max_tokens, presence_penalty, response_format, seed, temperature, tool_choice, tools, and top_p. Pricing is set at $0.26 per million input tokens and $0.78 per million output tokens, making it a cost-effective option for large-scale text generation and comprehension. The model is available via OpenRouter with the full ID qwen/qwen-plus.
💡Highlights
- ├─1M token context length
- ├─Balanced speed and cost
- └─Qwen2.5 foundation model
🎯For
- ├─AI developers
- ├─researchers
- └─businesses