Qwen: Qwen3.6 Max Preview
Analysis Summary
Qwen3.6 Max Preview is a high-capability model from Qwen with an intelligence index of 40, placing it in the very strong tier just below frontier. Its agentic index of 69.9 is competitive with top-tier models, and instruction following (ifbench 0.77) and long-context reasoning (lcr 0.70) are among the strongest in this batch. Tool use and function calling are supported, with a 262K context window enabling long-document and codebase-level tasks.
For businesses, this model is well suited to autonomous agentic workflows, complex document analysis, and structured content generation where instruction precision matters. The absence of a dedicated coding index is a gap, but the scicode score of 0.469 and strong agentic performance suggest meaningful coding capability. The preview label warrants some caution around production stability.
At $1.04/1M input and $6.24/1M output, it is priced at the premium end for its intelligence tier. Teams needing strong agentic and instruction-following capability without paying for absolute frontier performance will find it a capable option, provided they account for the preview status.
Assessed June 30, 2026
Editorial notes
Qwen3.6 Max Preview from Qwen delivers an intelligence index of 40 with strong agentic performance at 69.9, tool use, function calling, and a 262K context window, though output pricing at $6.24/1M is steep for its tier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3.6 Max Preview compares
Qwen: Qwen3.6 Max Preview ranks #32 of 385 AI models we track for overall intelligence, #16 of 293 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $1.04 per million input tokens it is cheaper than 23% of comparable models.
About Qwen: Qwen3.6 Max Preview
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..
Capabilities
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3.6 Max Preview stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3.6-max-preview
|
| Provider | qwen |
| Release Date | April 27, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 65,536 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.04 | $0.001040 |
| Output | $6.24 | $0.006240 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3.6 Max Preview
How much does Qwen: Qwen3.6 Max Preview cost?
Qwen: Qwen3.6 Max Preview costs $1.04 per million input tokens and $6.24 per million output tokens.
What is the context window of Qwen: Qwen3.6 Max Preview?
Qwen: Qwen3.6 Max Preview has a context window of 262,144 tokens (262K).
What can Qwen: Qwen3.6 Max Preview do?
Qwen: Qwen3.6 Max Preview supports tool use and function calling.
Who created Qwen: Qwen3.6 Max Preview?
Qwen: Qwen3.6 Max Preview is developed by Qwen and was released on April 27, 2026.
