Together AI adds Alibaba's Qwen4 Max with a 1M-token context window

Nov 22, 2026
The serverless offering is 30% off through 22 November; Together says the model patched a Tornado bug from the whole repository in one request.

Together AI has made Alibaba's Qwen4 Max available on its serverless inference platform with a one million token context window, the company says. Through 22 November it costs $1.05 per million input tokens, $0.0525 per million cached input tokens and $3.15 per million output tokens, which Together describes as 30% off. Requests have to stream, and thinking is on by default, with thinking tokens counted as output tokens.

To show what the long context window is worth, Together sent the model a bug report and all 344 files of the Tornado Python web framework, 652,519 tokens, in one request with no tools or retrieval step. Together says the reply was complete after 72 seconds and that the patch passes the maintainers' tests. The test is Together's own and covers a single bug.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Market report

2025 Generative AI in Professional Services Report

Thomson Reuters

This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.