MODELS
by Qwen
Qwen3.7-Plus is a Qwen multimodal agent model that supports text and image input with text output.
Qwen3.7-Plus is described in official Qwen and Alibaba Cloud materials as a multimodal agent model that unifies vision and language. The Qwen Cloud model page lists qwen3.7-plus with reasoning, text generation, and visual understanding capabilities, image/text/video input, text output, a 1M context window, 65.53K max output, built-in tools, and API examples. Qwen Cloud docs show it can be called through an OpenAI-compatible chat completions endpoint using model="qwen3.7-plus".
Use when you need a Qwen model for prompts that combine visual understanding with language generation. Use when you want a model listed for reasoning text generation and visual understanding through Qwen Cloud. Use when you need OpenAI-compatible API examples for calling qwen3.7-plus.
Last updated Jun 4, 2026