Code with Qwen3.8 Max
in AdaL
Alibaba's flagship multimodal long-context model. Use qwen3.8-max in AdaL for reasoning-heavy coding across near-1M-token codebases.
Get StartedRun /model and pick Qwen3.8 Max · $2/M input · $6/M output
Why use Qwen3.8 Max in AdaL
Key capabilities and pricing
Alibaba flagship model
The top-tier Max model in the Qwen line, built for multimodal long-context work.
991K context window
Near-1M-token input budget for large-codebase sessions.
131K max output
Double Qwen3.7 Max's output ceiling for substantial refactors.
Thinking model
Reasoning-capable for multi-step planning, coding, and analysis.
Vision support
Processes images and visual context alongside code.
$2/M input · $6/M output
Cached input at $0.20/M reduces repeat-context cost.
How to pick Qwen3.8 Max
Available in AdaL CLI and Desktop through the model selector
Open AdaL CLI or AdaL Desktop
Use the coding environment where AdaL already understands your repo, tools, and task context.
Run /model
Open the model selector and choose your model from the list.
Start your task
Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.
What to know
Key details about Qwen3.8 Max
"Qwen3.8 Max is the Alibaba flagship for multimodal, long-context work."
Qwen
"Use Qwen3.8 Max when a task needs both a near-1M context window and reasoning support."
AdaL
"991K token input and 131K token output in a single session."
Context
"Available now in AdaL CLI and Desktop."
Availability
Ready to try Qwen3.8 Max in AdaL?
Open AdaL CLI or Desktop, run /model, and choose Qwen3.8 Max.
Get Started with AdaL