Qwen Plus 0728
Neural Network
Qwen Plus 0728 is a hybrid reasoning model from Qwen with 1M token context, Qwen Plus API for code and long documents.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Qwen Plus 0728?
Qwen Plus 0728 is built on the Qwen3 base model and operates in hybrid mode: it responds quickly or enables step-by-step reasoning when the task requires it. The 1 million token context window allows you to hold entire large codebases, documentation, and long dialogues without splitting them into fragments. The balance of quality, speed, and cost makes it convenient for streaming tasks. Through BotHub, the model is available without a VPN or foreign card: pay with Russian cards in rubles as you go, for consumed tokens, and they do not expire. With over 250 neural networks in one window, you can compare answers and switch between them, while a single OpenAI-compatible API eliminates the need to rewrite integrations. Correspondence is encrypted via AES-GCM, and companies have access to contracts, invoices, electronic document management, and an admin panel with limits. Simple scenarios: analyze a large repository, refactor a module, and find a bug in code; summarize hundreds of pages of documents and correspondence; maintain an assistant with a long dialogue history; check reasoning in STEM tasks.Frequently asked questions about Qwen Plus 0728
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
qwen-plus-2025-07-28 works with text, documents, and images as input: it analyzes long reports, writes and refactors code, and answers questions about uploaded files. The million-token context allows you to keep an entire codebase or voluminous documentation in a single dialogue.
The maximum length of a single response is 32,768 tokens. This is enough for a voluminous article, a detailed document analysis, or a large code file. If you need more, just ask it to continue: the model remembers the entire previous dialogue thanks to the million-token context.
A separate step-by-step reasoning mode is not noted in our data for this version — this is not a denial, just that there is no such label. In practice, the model handles it well if you explicitly ask it to break down the task step-by-step and show the solution process before the final conclusion.
Yes. The model supports function calling and structured JSON output, making it easy to integrate into agents, chatbots, and internal services. In BotHub, this works via a single OpenAI-compatible API: you describe the tool schema in the usual way, and the model returns a response ready for parsing.
Images and documents — yes: you can send a screenshot, diagram, table, or file and ask it to analyze the content. Audio and video input is not noted in our data. If you need to work with sound or clips, switch to a specialized model in the same BotHub window.
Qwen is a multilingual line of models, and it processes Russian queries in the same way as other languages. The most accurate way to check this is with your own tasks: send a typical prompt and compare the result with a neighboring model in the same BotHub window — switching takes a second.