Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
Supported API features and tools
Text, image and video input with text responses
1M context and 65,536 maximum output
Hybrid thinking enabled by default with an API off switch
Singapore function calling, structured output, search and context caching
Before you choose
Do not treat the generic Qwen3.6 family name as proof of a specific model. This guide explicitly describes the hosted Plus ID.
The published input ceiling is 991,808 without thinking and 983,616 with thinking; leave room for the response.
Tools need configured integrations. Media understanding is not media generation, and no audio modality is claimed.
The reviewed sources do not establish a knowledge cutoff. Supply current evidence for time-sensitive questions; a large context window is not live web access.
Extended thinking
Thinking enabled · defaultThinking disabled
This model supports thinking and non-thinking requests. Alibaba Cloud's enable_thinking switch controls the mode; in the OpenAI Python SDK it belongs in extra_body. The provider's thinking_budget controls reasoning length. These are integration settings, not features a prompt can activate in every app. Thinking is enabled by default for this version. Use a bounded budget and evaluate whether extra reasoning improves the task.
The reviewed alias is functionally equivalent to qwen3.6-plus-2026-04-02. Record the version and deployment scope for comparisons.
The chain-of-thought maximum is separately listed as 81,920 tokens. It is not a promise of extra final-answer tokens or exposed reasoning.
Put it to work
Start with a more useful prompt.
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Extract a document comparison
Keep mixed visual and text evidence traceable.
Compare the supplied document pages and text specification. Create a table of requirement, evidence location, match status and unresolved question. Mark unreadable values rather than guessing. Highlight contradictions and list the smallest follow-up needed to verify each one.
Workflow 02
Draft code from a visual reference
Preserve design while making implementation assumptions explicit.
Using this interface screenshot and component conventions, propose the smallest native component structure that reproduces the visible layout. Preserve colors, typography and spacing. List assumptions about hidden behavior separately and provide a responsive test checklist; do not introduce unrelated features.
Workflow 03
Evaluate thinking on a repeated workflow
Choose settings using measured outcomes.
Design an evaluation for this recurring extraction task with thinking enabled and disabled. Use the supplied examples to define accuracy, evidence quality and failure categories. Include blank columns for measured latency and token use, plus a human-review threshold. Do not invent results or select a winner before testing.
Developer reference
Alibaba Qwen API pricing
These are provider API reference prices, not EZ Ai Assist subscription prices.
Singapore / International API reference · USD per 1,000,000 tokens
Token type
≤ 256Kinput tokens
> 256Kinput tokens
Input
$0.50
$2.00
Output
$3.00
$6.00
Explicit cache creation
$0.625
$2.50
Explicit cache read
$0.05
$0.20
Rates describe the Singapore / International deployment, in USD per million tokens, excluding promotions. Other regions, snapshots and hosting services can have different rates and supported features.
Input-length bands refer to the provider's published prompt-size tiers, not the length of the answer. Check the selected region, resolved model version, cache policy and any additional service charges before estimating cost.
Common questions
A few things worth knowing.
Which Qwen3.6 variant is this?
The hosted qwen3.6-plus model, not an arbitrary open-weight Qwen3.6 family member. The separate Qwen 3.6 catalog label is also mapped to this API ID by the site owner.
Can thinking be disabled?
Yes. This hybrid model defaults to thinking enabled and accepts enable_thinking false in a configured provider integration.
What is the output limit?
65,536 tokens in both documented modes. The context, input and chain-of-thought limits are separate values.
Is the long-prompt rate the same?
No. The Singapore table uses higher input/output and cache rates above 256K input tokens. Verify the region and actual token usage.
Does this page guarantee access in EZ Ai Assist?
No. A catalog entry and provider capability reference do not establish current app access, enabled tools or available settings. Check the model selector and controls in your workspace.
Are these EZ Ai Assist subscription prices?
No. Provider API rates are developer references. Your subscription and any limits shown in the app are separate; use the website pricing page for plans.
How should I verify an answer?
Provide the relevant evidence and acceptance criteria, ask for source references or reproducible checks, and review the result. Distinguish a proposed tool action from a tool action actually executed.
Check the source
Official documentation
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.