Qwen Plus 0728
VerifiedOpen-weight LLM with a 1M-token context for long text tasks.
About Qwen Plus 0728
The model follows a standard transformer design optimized for text. Its open-weight release lets researchers inspect, fine-tune, and deploy the weights freely. The one-million-token context window stands out as the key architectural feature.
Strengths center on retaining coherence across very long sequences of text. This capability reduces the need for chunking or summarization in preprocessing pipelines. The absence of disclosed parameter counts keeps focus on practical context length rather than scale claims.
Typical usage includes processing full-length reports, maintaining multi-turn technical discussions, and handling large code repositories. Developers integrate it into applications where preserving distant context improves output quality. Academic teams also use it to study long-context behavior in open models.
Capabilities
How Qwen Plus 0728 compares
Qwen Plus 0728 (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Qwen Plus 0728 ranks #34 of 78
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long-Form Document Analysis
The 1,000,000-token context window allows the model to ingest and reason over entire books, legal contracts, or research papers in a single pass without chunking.
Extended Multi-Turn Conversations
Maintains coherence across very long dialogues, making it suitable for ongoing technical support sessions or complex collaborative writing projects.
Large Codebase Understanding
Can process and explain entire repositories or lengthy code files at once, aiding in refactoring, debugging, and architectural reviews.
Strengths & limitations
Strengths
- +Handles up to 1M token contexts
- +Strong Chinese-English bilingual performance
- +Solid general reasoning for an LLM
Limitations
- –Text-only modality
- –No native vision or multimodal support
- –Knowledge cutoff inherent to training data
Cost calculator
Estimate what Qwen Plus 0728 would cost for your usage.
Based on Qwen Plus 0728's $0.26/1M input · $0.78/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "qwen/qwen-plus-2025-07-28",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: qwen/qwen-plus-2025-07-28
Editor's verdict
Qwen Plus 0728 is Alibaba Qwen's open-weight language models with a 1000K-token context window.
At $0.78 per 1M output tokens, it is very cost-efficient for its class.
As an open-weight model you can self-host it or call it through a hosted API.
Best suited to handles up to 1m token contexts and strong chinese-english bilingual performance.
Frequently asked questions
The model supports a context window of 1,000,000 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Qwen models
Sibling versions in the Qwen family from Alibaba Qwen.
Similar models
Other language models worth comparing.