Qwen: Qwen VL Plus

Text input Image input Text output
Author's Description

Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for image input. It delivers significant performance across a broad range of visual tasks.

Key Specifications
Cost
$$$
Context
7K
Released
Feb 04, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Response Format Seed Top P Max Tokens Temperature Presence Penalty
Features

This model supports the following features:

Response Format
Performance Summary

Qwen VL Plus, an enhanced large visual language model from Qwen, demonstrates a balanced performance profile with notable strengths in specific areas. The model typically performs in the top tier for speed, ranking in the 68th percentile across benchmarks, indicating efficient processing. It also offers cost-effective solutions, with a price ranking in the 65th percentile. Reliability is a significant strong point, with an 87% success rate across benchmarks, suggesting consistent and usable responses. In terms of specific benchmarks, Qwen VL Plus excels in Ethics, achieving 97.0% accuracy, and shows strong performance in Email Classification (93.0%). Its Instruction Following capabilities are moderate at 52.0% accuracy. However, the model exhibits weaknesses in General Knowledge (70.2% accuracy), Mathematics (44.4% accuracy), Reasoning (44.0% accuracy), and Coding (68.0% accuracy), where it ranks in the lower percentiles. Notably, its hallucination rate is relatively high at 84.0% accuracy, indicating a tendency to provide answers rather than acknowledge uncertainty. The model's ability to handle ultra-high pixel resolutions and extreme aspect ratios, as highlighted in its description, positions it well for detailed visual tasks, despite some of its general knowledge and reasoning limitations.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.21
Completion $0.63

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen-vl-plus 7K $0.21 / 1M tokens $0.63 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen