Qwen3.7 Max
Qwen3.7 Max is a text generation model from Qwen with a 1,000,000-token context window and optional deep thinking mode.
Qwen
Alibaba CloudLarge-context reasoning with toggleable deep thinking
Qwen3.7 Max is a large language model developed by Qwen, a team under Alibaba. It is designed for text generation tasks and features a context window of up to one million tokens, allowing it to process and reason over very long documents or conversation histories in a single pass. The model supports an optional deep thinking mode, which can be toggled on or off depending on the task, enabling more deliberate multi-step reasoning when needed.
Qwen3.7 Max is well-suited for tasks that require sustained attention over large bodies of text, such as document analysis, long-form summarization, complex question answering, and multi-step reasoning problems. Its configurable thinking mode makes it adaptable for both quick responses and more thorough analytical tasks. The model accepts text input only and can produce responses of up to 64,000 tokens, making it practical for generating extended outputs.
What Qwen3.7 Max supports
Large Context Window
Processes up to 1,000,000 tokens in a single context, enabling analysis of very long documents or extended conversations without truncation.
Deep Thinking Mode
Offers a toggleable deep thinking input that enables multi-step deliberate reasoning, selectable via a dropdown when configuring the model.
Extended Response Output
Supports a maximum response size of 64,000 tokens, allowing generation of lengthy structured documents, reports, or analyses in a single call.
Multi-Step Reasoning
Tagged as a reasoning model, Qwen3.7 Max is designed to handle complex logical, analytical, and problem-solving tasks that require chained inference steps.
Ready to build with Qwen3.7 Max?
Get Started FreeCommon questions about Qwen3.7 Max
What is the context window size for Qwen3.7 Max?
Qwen3.7 Max has a context window of 1,000,000 tokens, meaning it can process up to one million tokens of input in a single request.
What is the maximum response length this model can produce?
The model supports a maximum response size of 64,000 tokens per output.
Does Qwen3.7 Max support image or video inputs?
No. Qwen3.7 Max is a text-only model and does not support image or video analysis.
What is the deep thinking mode and how do I use it?
Deep thinking is a toggleable input option (enable_thinking) that activates more deliberate, multi-step reasoning. It is configured via a select dropdown when setting up the model in MindStudio.
When was Qwen3.7 Max released?
Qwen3.7 Max was released in May 2026 and became available on MindStudio on June 12, 2026.
Documentation & links
Parameters & options
When enabled, the model performs an internal reasoning process before generating its final answer. This improves performance on complex tasks like programming and long-horizon agentic work, but may increase response time.
Anthropic
Google
MetaStart building with Qwen3.7 Max
No API keys required. Create AI-powered workflows with Qwen3.7 Max in minutes — free.