Skip to main content
Kaino.dev
Discover
Evals
News
Academics
Insights
Kaino.dev

Discover, evaluate, and compare AI tools, models, and agents.

Explore

  • Discover
  • Evaluations
  • News
  • Academics
  • Insights

Community

  • Twitter
  • YouTube
  • Instagram
Privacy PolicyTerms of Service

© 2026 Kaino.dev. All rights reserved.

Version 1.1.0
Discover/MODELS/Qwen: Qwen3.6 Max Preview
Qwen: Qwen3.6 Max Preview logo

MODELS

Qwen: Qwen3.6 Max Preview

by Qwen

modellead-sourceopenrouter-modelsqwenqwen3.6proprietarypreviewtext-generationlong-contextsource:docs.qwencloud.comqwen3.6-max-previewalibaba-cloudfunction-callingstructured-output
Visit WebsiteDocumentationGitHub

Overview

Hosted proprietary preview text-generation model from Qwen/Alibaba Cloud, available through Qwen Studio and the Alibaba Cloud Model Studio API as qwen3.6-max-preview.

Details

Qwen3.6-Max-Preview is announced by Qwen as a hosted proprietary preview model available through Qwen Studio and the Alibaba Cloud Model Studio API using model ID qwen3.6-max-preview. Qwen Cloud lists it under Qwen3.6 text-generation models with 256k context, 64k max output, a 128k thinking budget, function calling, structured output, and explicit cache support. The official quickstart documents text-generation request structures across OpenAI-compatible Responses, OpenAI-compatible Chat Completions, Anthropic Messages, and DashScope API styles. Qwen Cloud safety documentation states that automatic content moderation is applied to all API requests, screening both inputs and outputs across modalities.

When to Use

Evaluate Qwen’s hosted Qwen3.6 preview model through Qwen Studio or the Alibaba Cloud Model Studio API. Build long-context text-generation workflows that need the documented 256k context window and 64k max output. Prototype applications that need function calling, structured output, or explicit cache support. Compare a Qwen-hosted proprietary preview model against other routed model options using OpenRouter as a discovery reference.

Getting Started

  1. Read the Qwen announcement for Qwen3.6-Max-Preview to confirm preview positioning and access paths.
  2. Open the Qwen Cloud text-generation model documentation and select model ID qwen3.6-max-preview.
  3. Use the Qwen Cloud text-generation quickstart to choose an OpenAI-compatible Responses, OpenAI-compatible Chat Completions, Anthropic Messages, or DashScope API style.
  4. Review the Qwen Cloud pricing page for token pricing before scaling usage.
  5. Review the Qwen Cloud safety documentation because API requests are subject to automatic content moderation.

Key Features

  • •Hosted proprietary preview model from Qwen/Alibaba Cloud.
  • •Model ID: qwen3.6-max-preview.
  • •Available through Qwen Studio and the Alibaba Cloud Model Studio API according to the Qwen announcement.
  • •Listed by Qwen Cloud with 256k context and 64k max output.
  • •Listed by Qwen Cloud with a 128k thinking budget.
  • •Supports function calling, structured output, and explicit cache support according to Qwen Cloud documentation.
  • •Official quickstart documents OpenAI-compatible Responses, OpenAI-compatible Chat Completions, Anthropic Messages, and DashScope API styles.

Capabilities

  • •text-generation
  • •long-context
  • •function-calling
  • •structured-output
  • •explicit-cache
  • •api-access

Last updated Aug 11, 2026

Qwen: Qwen3.6 Max Preview · Discover · Kaino