Qwen 3.6 Max Preview

by Qwen · chat

Qwen 3.6 series most capable model. Coding SOTA leading SWE-bench Pro, Terminal-Bench 2.0, SkillsBench. Text-only, 256K context.

Pricing

Input: .261314/M tokens · Output: $7.567883/M tokens

Capabilities

Function Calling, JSON Mode, Streaming, Reasoning

Context: 262K tokens

Max output: 66K tokens

Routes: 1/1 healthy

Performance

TTFT: 1445ms · Latency: 9635ms · Throughput: 21.3 tok/s