MODELS

Qwen: Qwen3.5 Plus 2026-04-20

by Qwen / Alibaba

modellead-sourceopenrouter-modelssource:docs.qwencloud.comqwenalibabaqwen-cloudqwen3.5-plusmultimodallong-contextfunction-callingstructured-output

Visit Website Documentation

Overview

Qwen3.5 Plus 2026-04-20 is a Qwen Cloud Qwen3.5-Plus snapshot from Alibaba with a 1M-token context window, multimodal input support, and text output.

Details

Qwen Cloud lists `qwen3.5-plus-2026-04-20` as a Qwen3.5-Plus snapshot in its model releases. Official Qwen Cloud documentation lists the model with text, image, and video input support, text output, a 1M-token context window, 64k maximum output, an 80k thinking budget, function calling, built-in tools, structured output, and explicit cache support. The Qwen Cloud changelog says this snapshot improves agentic coding and inference speed compared with the February 15 snapshot. Qwen documentation identifies Qwen as Alibaba Group’s large language and multimodal model series, and lists Qwen Plus among proprietary Qwen language models.

When to Use

Use for long-context workflows that need up to a 1M-token context window. Use when an application needs text, image, or video inputs with text output through Qwen Cloud. Use for agentic or tool-using applications that need function calling, built-in tools, structured output, or explicit cache support.

Getting Started

Review the Qwen Cloud model release notes for `qwen3.5-plus-2026-04-20`.
Use the Qwen Cloud text-generation model documentation to confirm context length, maximum output, thinking budget, function calling, built-in tools, structured output, and explicit cache support.
Use the Qwen Cloud visual understanding documentation for workflows that include image or video input.
Review Qwen Cloud safety documentation, which states that automatic moderation applies to API requests across supported modalities.

Key Features

•1M-token context window listed in Qwen Cloud documentation.
•64k maximum output and 80k thinking budget listed for the model.
•Supports text, image, and video inputs with text output according to Qwen Cloud documentation.
•Supports function calling, built-in tools, structured output, and explicit cache support.
•Qwen Cloud changelog notes improved agentic coding and faster inference versus the February 15 snapshot.

Capabilities

•text generation
•multimodal input
•long context
•function calling
•structured output
•built-in tools
•explicit caching

Last updated May 31, 2026