Back to models
Chat Models

Z.ai

GLM-4.7

Best Overall

Previous-generation text model with 200K context, turn-level thinking and coding-oriented tool workflows.

ReasoningFlagship
Open AppBrowse All Models

At a glance

Know the model before you prompt.

Z.ai API specifications
Context window
200K
Maximum output
128K
Inputs → output
Text → Text
Knowledge cutoff
Not verified

API model ID: glm-4.7

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

  • 200K context and 128K maximum text output
  • Turn-level thinking control introduced with GLM-4.7
  • Interleaved reasoning around tool results
  • Preserved reasoning history when supported and configured by the integration

Before you choose

  • 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.
  • This is a text-input guide. Supply extracted text for document analysis; do not assume the model can directly inspect images, videos or attached files just because other GLM models can.
  • 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.

  • When thinking is enabled, the API describes GLM-4.7 as reasoning rather than dynamically skipping it. Disable thinking explicitly for a non-thinking request.
  • Preserved thinking is separate from turn-level enable/disable. Its standard-API and Coding Plan defaults differ; retain original reasoning history when enabling preservation.
  • 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

Choose thinking by task

Design a per-turn evaluation without guessing results.

Classify these supplied support and engineering tasks by the evidence and reasoning they require. Propose an evaluation comparing thinking enabled and disabled on the same prompts, with correctness, latency and usage metrics. Explain which results would justify each setting without inventing performance numbers.

Workflow 02

Inspect an agent transcript

Find where a tool loop lost evidence.

Review this transcript of assistant messages, tool calls and tool results. Identify unsupported conclusions, missing results and places where the next action contradicts earlier evidence. Cite the relevant turn, propose the smallest correction and list checks the runtime should enforce before executing another action.

Workflow 03

Repair an edge-case design

Use explicit inputs to test reasoning.

Review this function contract and edge-case examples. Find inconsistent outcomes, propose a minimal corrected contract and write a table of boundary tests. Explain assumptions about missing requirements instead of silently choosing behavior. Do not claim the implementation has been changed or verified.

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$2.20
  • 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.

What is turn-level thinking?

Each request can enable or disable thinking independently. That helps compare heavier reasoning turns with simpler responses, without making every task use the same setting.

Is preserved thinking enabled everywhere?

No. The documented defaults differ between Coding Plan and standard API endpoints. The latter requires explicit preservation settings and complete, unmodified reasoning history.

Is GLM-4.7 still the newest flagship?

No. This page describes this specific generation rather than repeating its launch-era newest-model positioning. Evaluate newer GLM entries separately.

Are Flash and FlashX the same price?

No. The official table lists free token rates for Flash and paid rates for FlashX. Their shared family page does not make the commercial terms identical.

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.