Qwen3.6 Max Preview

Qwen · qwen/qwen3.6-max-preview

← Back to leaderboard

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...

Qwen3.6 Max Preview ranks #24 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $3.59 blended per million tokens, it is cheaper than 24% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens). A quality index of 79.9 places it at #24 of 41 models with an Arena Elo signal.

texttext->text

Context

Max context: 262144
Max output: 65536

Pricing

Input / 1M: 1.03
Output / 1M: 6.16
Blend / 1M: 3.59

Quality

Quality index: 79.9

Provider

Provider: Qwen
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $3.59per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$3.59
10,000,000$35.95
100,000,000$359.45

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Qwen

Closest API price

Closest quality index