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 understanding with text output
1M context and 131,072 maximum output in both modes
Hybrid thinking enabled by default
Singapore API function calling, structured outputs, search and caching support
Before you choose
No native audio input or image/video generation is established by this model table.
Understanding a screen does not mean the model can operate the app without a separate tool integration.
Singapore batch inference and fine-tuning are listed as unsupported. Other deployment scopes can also differ on structured output and search.
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 overview maps the alias to qwen3.7-plus-2026-05-26. Pin and test a snapshot when repeatability matters.
Maximum input is 991,808 without thinking or 983,616 with thinking. The separately published chain-of-thought ceiling is 262,144, not the final-answer limit.
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
Turn a screen into implementation requirements
Describe a visible interface without guessing behavior.
Use this screenshot and product brief to write implementation requirements for the visible interface. Specify layout relationships, controls, content and responsive questions. Separate directly visible facts from assumptions, preserve the supplied branding, and include acceptance tests without inventing hidden screens.
Workflow 02
Compare a video with a procedure
Locate evidence and missing steps.
Compare this recorded workflow with the written procedure. For each requirement, cite the visible timestamp or mark it not demonstrated. Identify unclear transitions and possible failure points. Recommend three targeted interactive tests rather than claiming the video proves every step works.
Workflow 03
Review a visual code change
Connect code and rendered evidence.
Review this UI diff together with before-and-after screenshots and the acceptance criteria. Identify concrete visual or behavioral risks and cite the matching code and screenshot evidence. Keep proposed changes minimal, distinguish inferred behavior from observations, and list the tests needed before approval.
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
$0.40
$1.20
Output
$1.60
$4.80
Input · implicit cache
$0.08
$0.24
Explicit cache creation
$0.50
$1.50
Explicit cache read
$0.04
$0.12
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.
Does it accept images and video?
Yes in the documented provider API. Outputs are text; this does not establish media-upload availability in EZ Ai Assist.
Is thinking on by default?
Yes. Alibaba Cloud documents a hybrid switch so an integration can disable thinking for bounded tasks. Measure the quality impact.
When does the higher rate apply?
The Singapore reference table separates inputs up to 256K from inputs above 256K through 1M. This is a prompt-size billing boundary, not an output threshold.
Can it navigate my application?
The provider describes visual-agent capabilities, but real interaction requires configured tools, permissions and an execution environment. Screenshots alone cannot grant that access.
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.