Category Models

Qwen3.8 Max Preview: Verified Specs, Access and Status

Qwen logo with Qwen3-8-Max model name on a white background

Last verified: July 26, 2026 Independent and unofficial: Qwen AI Chat is not affiliated with, endorsed by or operated by Alibaba Cloud, QwenCloud or the Qwen team. This page verifies public information against official sources. Any chat demo on this…

Qwen3.6 Flash: Lower-Cost 1M-Context Model Guide

Qwen3.6 Flash

Last verified: July 21, 2026. This independent guide is not operated by or affiliated with Alibaba Cloud or the Qwen team. Verify prices, quotas, limits, and regional availability in the provider documentation before production use. Qwen3.6 Flash is Alibaba Model…

Qwen3.7 Plus: Multimodal 1M-Context Model Guide

Qwen3.7 Plus

Last verified: July 21, 2026. This is an independent technical guide and is not operated by or affiliated with Alibaba Cloud or the Qwen team. Confirm availability, billing, and regional requirements in the provider documentation before deployment. Qwen3.7 Plus is…

Qwen3.7 Max: 1M-Context Reasoning Model Guide

Qwen3.7 Max

Last verified: July 21, 2026. This independent guide is not operated by or affiliated with Alibaba Cloud or the Qwen team. Model specifications, availability, and prices should be checked against the linked provider documentation before production use. Qwen3.7 Max is…

Qwen3-Omni: Inputs, Outputs, Checkpoints, and Local Use

Qwen3-Omni

Qwen3-Omni is an open-weight multimodal model family developed by the Qwen team. It can understand text, images, audio, and video, but its outputs depend on the checkpoint you select. The Instruct checkpoint can return text and natural speech, while the…

Qwen3 Max: 256K Context, API Status, and Migration

Qwen3-Max

Qwen3 Max, identified in Alibaba Model Studio as qwen3-max, is a hosted commercial text-generation model with a 256K context window. It is different from qwen3.7-max, which is a separate 1M-context model. Last verified: July 21, 2026. Lifecycle notice: Alibaba schedules…

Qwen2.5-Max

Qwen2.5-Max

Qwen2.5-Max is a general-purpose Large Language Model (LLM) developed by the Qwen team at Alibaba Cloud. It stands out for its scale and capabilities: built with a mixture-of-experts (MoE) transformer architecture comprising 325 billion parameters and trained on over 20…

Qwen2-VL

Qwen2-VL

Qwen2-VL is Alibaba’s next-generation multimodal large language model that combines vision and language understanding. As an advanced Qwen vision model, it can accept both text and visual inputs (images – and even videos – alongside prompts) and generate detailed textual…

Qwen3-Next: Instruct vs Thinking, Context, and Setup

Qwen3-Next

Qwen3-Next is an open-weight, text-only mixture-of-experts model family. Its public release uses separate Instruct and Thinking checkpoints. It is not one downloadable checkpoint that switches dynamically between the two behaviors. Last verified: July 21, 2026. Checkpoint rule: Select Qwen/Qwen3-Next-80B-A3B-Instruct for…

Qwen3-Coder: Open Models, Coder-Next, API, and Setup

Qwen3-Coder

Qwen3-Coder is a family of text-based coding language models developed by the Qwen team. It includes large mixture-of-experts Instruct checkpoints, the separate Qwen3-Coder-Next architecture, downloadable model variants, and hosted Alibaba Cloud Model Studio IDs. Last verified: July 21, 2026. The…

Qwen2.5-Math

Qwen2.5-Math

Qwen2.5-Math is an open-source series of large language models specialized in advanced mathematics and symbolic reasoning. Developed as part of Alibaba’s Qwen family in late 2024, Qwen2.5-Math comes in multiple model sizes (1.5B, 7B, and 72B parameters) and includes both…

Qwen3-VL: Models, Inputs, Context, and Local Setup

Qwen3‑VL

Qwen3-VL is an open-weight vision-language model family that accepts text, images, and video and produces text. Qwen publishes Dense and mixture-of-experts sizes, with separate Instruct and Thinking checkpoints for every core size. Last verified: July 21, 2026. Model-ID correction: Qwen/Qwen3-VL-7B-Instruct…

Qwen2.5: Model Sizes, Context, Licenses, and Local Setup

Qwen2.5

Qwen2.5 is a September 2024 generation of dense, decoder-only language models from the Qwen team. The core family contains seven text-model sizes, each published in Base and Instruct forms. Last verified: July 21, 2026. Core Qwen2.5 checkpoints are text-in, text-out…

Qwen3: Model Sizes, Thinking Modes, Context, and Setup

Qwen 3

Qwen3 was released on April 29, 2025 as a family of dense and mixture-of-experts language models. The April release is also identified as Qwen3-2504 to distinguish it from later dated checkpoints. Last verified: July 21, 2026. The official core lineup…

Qwen2.5-Omni: Inputs, Outputs, Checkpoints, and Licenses

Qwen2.5-Omni

Qwen2.5-Omni is an open-weight multimodal model family from the Qwen team. It can process text, images, audio, and video, then generate a text response and, when the Talker component is enabled, synthesized speech. It does not generate images or videos.…

Qwen2-Math

Qwen2-Math

Qwen2-Math is a specialized large language model (LLM) focused on mathematical reasoning. Part of the Qwen2 model family from Alibaba, Qwen2-Math was introduced in mid-2024 as a series of math-specific models based on the Qwen2 architecture. It comes in multiple…

Qwen2.5-Coder: Models, Context, Licenses, and Setup

Qwen2.5-Coder

Qwen2.5-Coder is a 2024 open-weight model family specialized for code generation, code explanation, code repair, and related text-based programming tasks. It is based on Qwen2.5 and is preserved here as a historical coding generation. Last verified: July 21, 2026. Qwen2.5-Coder…

Qwen2: Model Sizes, Context Windows, Licenses, and Setup

Qwen 2

Qwen2 is a 2024 generation of open-weight language models developed by the Qwen team. It includes dense and mixture-of-experts checkpoints in several sizes, but its context limits and licenses are not identical across the family. Last verified: July 21, 2026.…

Qwen-VL

Qwen-VL

Qwen-VL is a large multimodal model (LMM) developed by Alibaba Cloud that can process both images and text in a unified framework. It extends the base Qwen language model (LLM) by adding a visual encoder (often called a “visual receptor”)…

Qwen2.5-VL

Qwen2.5-VL

Qwen2.5-VL is the latest vision-and-language large model from Alibaba Cloud’s Qwen series, designed to understand images (and even videos) and generate text responses. It is an open-source model (Apache 2.0 license) available in 3 sizes – approximately 3B, 7B, and…

Qwen Max Models: IDs, Context, and Availability

Qwen Max

Qwen Max is a hosted model tier, not one permanent model or a downloadable 72B checkpoint. The exact identifier matters: qwen-max, qwen-max-2025-01-25, qwen3-max, and qwen3.7-max refer to different hosted entries or snapshots. For a new Max integration verified on July…

QwQ-32B: Reasoning Model, Context, License, and Local Setup

Qwen QwQ

Accuracy note: QwQ-32B is not documented as an AI companion or character model. The official sources do not attribute persistent memory, an emotional state, a permanent persona, consciousness, or cross-session recall to the checkpoint. An application may supply conversation history,…

Qwen Turbo

Qwen Turbo

Qwen Turbo is a high-speed, cost-efficient large language model (LLM) developed by Alibaba Cloud as part of its Tongyi Qianwen Qwen AI model family. It stands out for its exceptionally large context window – capable of handling up to 1…

Qwen Flash

Qwen Flash

Qwen Flash is a large language model (LLM) from Alibaba Cloud’s Tongyi Qianwen (Qwen) family, engineered for ultra-fast inference, efficiency, and massive context handling. It’s the fastest and most cost-effective model in the Qwen lineup, tuned to deliver quick responses…

Qwen Plus: Hosted API, 1M Context, and Migration

Qwen Plus

Qwen Plus, identified as qwen-plus in Alibaba Model Studio, is a legacy hosted text-generation model with a 1M context window. It is a commercial API model, not a downloadable checkpoint intended for local deployment. Last verified: July 21, 2026. Important…