Qwen3.6 Max Preview pricing & benchmarks
Qwen3.6 Max Preview is available from Alibaba at $1.03 per million input tokens and $6.16 per million output tokens ($2.31 blended at 3:1). It accepts up to 262,144 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$1.03
Output$6.16
Blended (3:1)$2.31
Specification
qwen/qwen3.6-max-preview
Context window262K
Max output66K
ReleasedApr 2026
LicenceProprietary
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 87.4% ±2.4 | thinking effort | 2026-08-07 | Independently run · Epoch AI |
| SWE-bench Verified | 76.7% ±1.9 | thinking effort | 2026-05-28 | Independently run · Epoch AI |
| SimpleQA Verified | 56.9% ±1.6 | thinking effort | 2026-05-15 | Independently run · Epoch AI |
| OTIS Mock AIME | 91.1% ±4.3 | thinking effort | 2026-08-07 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−95%) | 91.0% | Compare → |
| GPT-5.6 Luna | OpenAI | $0.225 (−90%) | 91.6% | Compare → |
| GLM 5.2 | Zhipu AI | $0.387 (−83%) | 91.9% | Compare → |
| DeepSeek V4 Pro | DeepSeek | $0.544 (−76%) | 90.9% | Compare → |
| Qwen3.6 Plus | Alibaba | $0.731 (−68%) | 88.4% | Compare → |
Compare Qwen3.6 Max Preview
FAQ
How much does Qwen3.6 Max Preview cost?
Qwen3.6 Max Preview costs $1.03 per million input tokens and $6.16 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $2.31 per million tokens.
What is Qwen3.6 Max Preview's context window?
Qwen3.6 Max Preview accepts up to 262,144 tokens of context, and can generate up to 65,536 output tokens.
How good is Qwen3.6 Max Preview on benchmarks?
Qwen3.6 Max Preview scores 87.4% on GPQA Diamond, independently run and published by Epoch AI. 4 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Qwen3.6 Max Preview?
Yes — 5 models in our catalogue cost less per token than Qwen3.6 Max Preview and score at least as high on the same benchmark. The cheapest is DeepSeek V4 Flash 0731 at $0.113 per million tokens blended.