Qwen3.6 Max Preview
Review Qwen3.6 Max Preview on key metrics including price, context length, throughput, and model features.
AuthorQwen
Context Length262.1k
Supports Tools
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning traces across multi-turn conversations and supports structured output and function calling. Access is available exclusively through the Alibaba Cloud Model Studio and Qwen Studio APIs; no open weights are provided.
Activity
Last 14 daysPrompt
288Completion
4KTotal
5KStartup
Startup
Latency (p50)-
Throughput (p50)40.5 tok/s
Pricing
Input$0.51/M tokens
Output$3.08/M tokens
Features
Input Modalitiestext
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools