Question 1

What is Qwen3.6 Max Preview?

Accepted Answer

Qwen3.6 Max Preview is a model from Qwen, released on Apr 20, 2026. 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.

Question 2

How much does Qwen3.6 Max Preview cost?

Accepted Answer

On the Respan gateway, input starts at $1.03 per 1M tokens on OpenRouter, and output starts at $6.16 per 1M tokens on OpenRouter, after gateway discounts. Averaged across 2 providers, it costs $1.17 per 1M input tokens and $7.02 per 1M output tokens.

Question 3

Which providers serve Qwen3.6 Max Preview on Respan?

Accepted Answer

2 providers serve Qwen3.6 Max Preview: OpenRouter and EmpirioLabs.

Question 4

What is Qwen3.6 Max Preview's context window?

Accepted Answer

Qwen3.6 Max Preview accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Qwen3.6 Max Preview with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3.6-max-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Qwen3.6 Max Preview?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 43 tokens per second, and the lowest response latency was 6.5 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does Qwen3.6 Max Preview rank on the Respan Index?

Accepted Answer

Qwen3.6 Max Preview scores 38.1 out of 100 on the Respan Index v1.1, ranking #51 of 138 models. By category: Coding 18.9, Agents 53.2, Reasoning 28.2, Knowledge & language 51.9, and Human preference 52.2. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Qwen3.6 Max Preview score on benchmarks?

Accepted Answer

Qwen3.6 Max Preview has 17 published benchmark scores, including SWE-bench Verified 76.7%, QwenClawBench 59%, and GPQA Diamond 87.4%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
OpenRouter`openrouter/qwen/qwen3.6-max-preview`	262K	$1.03/M	$6.16/M
EmpirioLabs`empiriolabs/qwen3-6-max-preview`	256K	$1.31/M	$7.88/M

Qwen3.6 Max Preview

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding5

Apps