Qwen: Qwen Plus 0728

Text input Text output
Author's Description

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.

Key Specifications
Cost
$$
Context
1M
Parameters
20B (Rumoured)
Released
Sep 08, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Response Format Temperature Seed Tool Choice Structured Outputs Max Tokens Top P Presence Penalty Tools
Features

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Qwen Plus 0728, a 1 million context hybrid reasoning model based on the Qwen3 foundation, demonstrates a balanced profile of performance, speed, and cost. Created on September 8, 2025, this model performs among the fastest models, typically ranking in the top tier for speed (63rd percentile). It also offers competitive pricing, placing in the 59th percentile across benchmarks. Notably, Qwen Plus 0728 exhibits exceptional reliability, achieving a 100% success rate across all evaluated benchmarks, indicating consistent and stable operation with minimal technical failures. In terms of specific benchmark performance, Qwen Plus 0728 excels in acknowledging uncertainty, achieving perfect accuracy (100.0%) in the Hallucinations (Baseline) test. This makes it the most accurate model at its price point and among models of comparable speed for this task. However, its performance in the Email Classification (Baseline) task is less impressive, with 94.1% accuracy, placing it in the 27th percentile. Similarly, its Instruction Following (Baseline) capability shows room for improvement, with 50.0% accuracy, ranking in the 41st percentile. Key strengths include its outstanding reliability and its ability to avoid hallucinations, making it a strong candidate for applications requiring high certainty and stable operation. Its primary weakness lies in its accuracy for classification and complex instruction following tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.26
Completion $0.78

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen-plus-2025-07-28 1M $0.26 / 1M tokens $0.78 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen