In the news
Qwen4 Max is live on Together AI
Together AI · Published · 3 min read
In 30 seconds
- What happened
- Alibaba's Qwen4 Max model is now available on Together AI with a 1M-token context window and automatic prompt caching.
- Why it matters
- Matters for engineers handling large codebases or long-context tasks who need cost-effective inference with fast cached-request performance.
- Watch out
- Requests must use streaming mode, thinking is enabled by default and counts as output tokens, and the model is serverless-only without fine-tuning support.
- qwen
The patterns behind this
- Context Editing & Tool-Result Clearing
- Agentic Context Engineering (Evolving Playbook)
- Automatic Prompt Optimization
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.