Back to models
Chat Models

Z.ai

GLM-4.5V

Visual reasoning model for images, video and documents with 64K context, 16K output and switchable thinking.

Vision64K context
Open AppBrowse All Models

At a glance

Know the model before you prompt.

Z.ai API specifications
Context window
64K
Maximum output
16K
Inputs → output
Text + Images + Video + Files → Text
Knowledge cutoff
Not verified

API model ID: glm-4.5v

Capabilities & boundaries

What it supports. Where the limits are.

Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.

Supported API features and tools

  • Image, video, text and file understanding
  • 64K context in the official model overview
  • 16K maximum text output in the model guide and API
  • Switchable thinking for visual reasoning and quick responses

Before you choose

  • The current vision API documents native function tools for the GLM-4.6V and GLM-5.3-Flash families, not GLM-4.5V. GUI examples in its guide do not establish native tool-call support.
  • Context and output limits use the provider's published K/M units. They are capacity ceilings, not a guarantee of complete recall or a final answer of that length. A model-specific knowledge cutoff was not verified.
  • Visual and file inputs support understanding with text output, not native image, video or audio generation. File format, size and ingestion requirements depend on the endpoint and app integration.
  • Answers and proposed code still need validation. A tool call is a request for an integration to execute an action, not proof it ran. Keep approvals around consequential changes and check results against source evidence.

Extended thinking

enabled · defaultdisabled

The model reasons whenever thinking is enabled, rather than dynamically skipping reasoning for a simple request. Use thinking.type disabled for the non-thinking path. Thinking is enabled by default; compare both modes on your own tasks and do not copy GLM-5.3 effort levels into this model.

  • Use the dedicated GLM-4.5V guide. The text GLM-4.5 family's 128K context and 96K output do not apply: this model has 64K context and 16K output.
  • Thinking can be enabled or disabled. The API describes enabled GLM-4.5V thinking as mandatory within that enabled path, unlike dynamic text-family thinking.
  • Select the exact API identifier shown here. Website slugs use hyphens for URLs and are not substitutes for dotted API model names. API access and the GLM Coding Plan endpoint have different entitlements.
  • For supported interleaved-thinking tool loops, retain the returned reasoning_content with the tool history. Preserved thinking uses thinking.clear_thinking false and unmodified history; its documented defaults differ between the standard API and Coding Plan endpoints. Check model support before enabling it.

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

Read a chart with caveats

Report only values the visual source supports.

Inspect these chart screenshots and extract the axes, units, labeled values and main comparisons. Cite the chart and region for each observation. Mark unreadable or estimated values clearly and avoid extrapolating beyond the shown range. End with questions that require the underlying data.

Workflow 02

Describe a document layout

Make visual structure useful for a reviewer.

Review the supplied document pages and describe their structure, key tables and visible inconsistencies. Reference page numbers and headings, flag cropped or low-resolution regions, and distinguish transcription from interpretation. Do not invent content from pages that were not provided.

Workflow 03

Create a screenshot acceptance checklist

Turn visual evidence into testable requirements.

Using this interface screenshot and the written requirements, draft an acceptance checklist for layout, labels and content hierarchy. Separate visually observable checks from keyboard, loading and interaction checks that need a running app. Preserve the design and do not claim to have clicked any control.

Developer reference

Z.ai API pricing

These are Z.ai direct API reference prices, not EZ Ai Assist subscription prices.

View EZ Ai Assist plans
Standard processing · USD per 1,000,000 tokens
Token typePrice
Input$0.60
Cached input$0.11
Output$1.80
  • Input and output are billed separately per 1,000,000 tokens. Compare actual task usage, retries and latency rather than the input rate alone. These rates are not guaranteed reseller or app prices.
  • Only eligible cache hits receive the cached-input rate. Cached-input storage is listed as limited-time free, not permanently free. Recheck the provider table for storage terms and future changes.
  • The pricing page separately lists built-in Web Search at $0.01 per use. This is a service fee when that tool is used, not a charge on every prompt or a promise that this model or your workspace has automatic search.

Common questions

A few things worth knowing.

Why is its context only 64K here?

The official overview lists 64K for GLM-4.5V. It is not the same model as the GLM-4.5 text family, which lists 128K.

Does it support native function tools?

The reviewed vision API does not include GLM-4.5V in its supported function-tool families. Do not infer that feature from visual GUI examples.

How much output can it produce?

The dedicated guide and API list 16K maximum text output. Larger text-family limits must not be copied to this model.

Can thinking be disabled for simple visual tasks?

Yes. The dedicated guide describes a thinking switch. Evaluate accuracy on your images before favoring the faster non-thinking path.

Does the context window guarantee complete recall?

No. A large context is a capacity limit, not an accuracy guarantee. Label sources, split unrelated material, ask for evidence references and test whether important details were omitted. Output also has its own ceiling.

Are these prices the cost of my EZ Ai Assist plan?

No. This is a dated reference to direct Z.ai API token pricing. EZ Ai Assist subscriptions, Z.ai's GLM Coding Plan, optional tools and third-party hosting are separate products with their own terms.

Are all of these capabilities available in the app?

Not necessarily. The guide describes provider documentation, not workspace entitlements or an integration test. Check your model picker, accepted inputs and available controls. None of these examples runs tools or changes external systems by itself.

Check the source

Official documentation

Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.

Same provider

More from Z.ai

Z.ai

GLM-5.3

Text-only flagship for complex coding and agent workflows with 1M context and always-on reasoning.

Z.ai

GLM-5.3-Flash

Native multimodal GLM-5 model for images, video, files and text with 1M context and low API token rates.

Z.ai

GLM-5.3-FlashX

Faster-serving GLM-5.3-Flash tier with native multimodal inputs, 1M context and separately priced API access.

Z.ai

GLM-5.2

Text model for long-horizon engineering with 1M context, 128K output and configurable thinking.