What Is Z.ai? GLM Models, Features, Pricing & How It Works
Z.ai is an artificial intelligence platform built around the GLM family of AI models. Its ecosystem includes a consumer AI chatbot, developer APIs, AI coding tools, multimodal models, and the ZCode development environment.
If you are discovering Z.ai for the first time, the number of products and GLM model names can make the platform look more complicated than it really is. This guide explains what Z.ai is, how its main products fit together, what its current pricing looks like, and where ZCode and the GLM Coding Plan fit into the ecosystem.
Quick Answer
Z.ai is an AI platform built around the GLM model family. It offers a consumer chatbot, developer APIs, multimodal AI models, the ZCode agentic development environment, and the GLM Coding Plan for coding-agent usage.
What Is Z.ai?
Z.ai is the international AI platform associated with Zhipu AI and the GLM family of artificial intelligence models. For everyday users, the most visible entry point is the official Z.ai chatbot, which currently describes itself as powered by GLM-5.3-Flash.
For developers, Z.ai provides APIs for language models, vision models, image generation, video generation, audio transcription, web search, web reading, and agent-style workflows. Developers can explore the current model lineup and endpoints in the official Z.ai developer documentation.
What Can You Do With Z.ai?
Z.ai is broader than a single chatbot. Depending on the product or API you use, the platform can support general AI chat, coding, long-context work, image understanding, video understanding, image generation, video generation, audio transcription, web search, structured output, function calling, and agent-based automation.
| Part of Z.ai | Main purpose |
|---|---|
| Z.ai Chat | Consumer AI chatbot |
| GLM models | Language, reasoning and multimodal AI |
| Z.ai API | Developer access to models and tools |
| GLM Coding Plan | Subscription for coding-agent usage |
| ZCode | Agentic development environment |
Z.ai GLM Models Explained
GLM is the model family behind much of the Z.ai ecosystem. The lineup changes as new models are released, but GLM-5.3 and GLM-5.3-Flash are two of the most important current models for users following Z.ai in 2026.
GLM-5.3
GLM-5.3 is a flagship model focused heavily on coding, reasoning and longer agentic tasks. According to current Z.ai API documentation, it supports a context window of up to 1 million tokens and a maximum API output of up to 128,000 tokens.
Its reasoning mode remains enabled rather than being completely disabled. Users can instead adjust reasoning effort. GLM-5.3 is particularly relevant to developers working with coding agents and complex software tasks.
GLM-5.3-Flash
GLM-5.3-Flash is Z.ai’s first native multimodal model in the GLM-5 series. It accepts text, images, video and files as input and returns text output. Z.ai positions it as a lower-cost model for multimodal work, visual programming, computer-use tasks and other agentic applications.
For a deeper look at pricing, multimodal support, FlashX and Coding Plan availability, see our GLM-5.3-Flash guide.
GLM-5.3-FlashX
GLM-5.3-FlashX is a faster variant of GLM-5.3-Flash. Z.ai currently lists inference speeds of up to 200 tokens per second for FlashX. It has separate API pricing and, according to current documentation, is not included in the GLM Coding Plan in the same way as GLM-5.3-Flash.
What Is ZCode?
ZCode is Z.ai’s AI-focused development environment. Z.ai describes it as an Agentic Development Environment, or ADE, designed around GLM-5.3.
Rather than functioning only as code autocomplete, ZCode includes an AI agent that can plan, edit files, run tasks, interact with development tools and iterate on projects. Current features include Goal Mode, Browser Control, subagents, memory, remote development, plugins, skills, MCP support, Git integration and automations.
ZCode currently supports Windows, macOS and Linux, although Linux is labeled Beta. For the full product breakdown, read our What Is ZCode? guide.
What Is the GLM Coding Plan?
The GLM Coding Plan is Z.ai’s subscription for people who use GLM models through coding agents and development tools. Z.ai changed the plan from prompt-count quotas to a credits-based system on July 30, 2026, so older articles that focus only on prompt limits may now be outdated.
| Plan | Monthly price | 5-hour credits | Weekly credits |
|---|---|---|---|
| Lite | $18 | 2,000 | 10,000 |
| Pro | $80 | 12,000 | 60,000 |
| Max | $168 | 28,000 | 140,000 |
Because credit multipliers, off-peak usage and supported coding tools need more explanation than fits in this overview, we cover them in our Z.ai Coding Plan Lite vs Pro vs Max comparison.
Does Z.ai Work With Claude Code?
Yes. Claude Code is currently listed as an officially supported GLM Coding Plan tool. Z.ai provides an Anthropic-compatible endpoint so Claude Code can route supported requests to GLM-5.3 or GLM-5.3-Flash while using Coding Plan quota.
The setup requires the correct Z.ai endpoint and model configuration. Z.ai currently documents helper-based, automated and manual setup methods, along with a 1 million-token context option for supported GLM configurations.
Is Z.ai Free?
There are several free entry points into the Z.ai ecosystem, but they should not all be treated as the same thing. Current Z.ai documentation lists some API models with free input and output pricing, while ZCode offers a five-day trial for new users.
The GLM Coding Plan itself should not be confused with the ZCode trial. Current documentation does not describe the Coding Plan as having a standard free trial. Promotions and temporary campaigns can also change, so users should check current terms before relying on a limited-time offer.
Z.ai API Features
Z.ai provides developer access to a broader set of models and services beyond its consumer chatbot. Current API capabilities include text models, vision and OCR, image generation, video generation, audio transcription, web search, web reading, layout parsing and specialized agent endpoints.
| Category | Examples |
|---|---|
| Language models | GLM text and reasoning models |
| Vision | Multimodal models and OCR |
| Image generation | GLM-Image and CogView |
| Video | CogVideoX |
| Audio | GLM ASR |
| Web tools | Web Search and Web Reader |
| Developer features | Function calling, structured output and caching |
How Much Does the Z.ai API Cost?
API pricing varies by model. Current pricing makes GLM-5.3 substantially more expensive per token than GLM-5.3-Flash, while FlashX sits between the two in price and focuses on higher inference speed.
The Coding Plan is also separate from normal pay-as-you-go API pricing. A developer comparing them should consider workload, cache usage, supported tools and expected token consumption rather than assuming one option is always cheaper.
Is Z.ai Available in the United States?
Z.ai provides English-language documentation and pricing in U.S. dollars, and its billing documentation references payment methods such as cards and PayPal. However, the source material reviewed for this guide does not include an official statement guaranteeing that every Z.ai service is available without restriction throughout the United States.
For that reason, users should check the current signup or product page for any account, payment or regional restrictions that may apply to the specific service they want to use.
Z.ai and New AI Features
Z.ai’s ecosystem is changing quickly. Recent developments include GLM-5.3, GLM-5.3-Flash, FlashX, Coding Plan changes and frequent ZCode updates.
One newer ZCode feature is dynamic workflows, which can orchestrate multiple subagents and save reusable workflows. We cover that separately in our ZCode Dynamic Workflows explainer.
Is Z.ai the Same as ZCode?
No. Z.ai is the broader AI platform and ecosystem. ZCode is one product within that ecosystem, focused on agentic software development.
| Product | Purpose |
|---|---|
| Z.ai | Overall AI platform |
| Z.ai Chat | Consumer chatbot |
| GLM models | Models powering AI services |
| Z.ai API | Developer model access |
| GLM Coding Plan | Subscription for coding-agent usage |
| ZCode | Agentic development environment |
Who Is Z.ai For?
Z.ai may appeal to general AI users, developers, programmers using coding agents, and people interested in multimodal AI. The chatbot is the simplest entry point, while developers can use the API platform and coding-focused users can explore ZCode or the GLM Coding Plan.
Frequently Asked Questions
What is Z.ai?
Z.ai is an artificial intelligence platform built around the GLM model family. It provides consumer AI chat, developer APIs, AI coding tools, multimodal models and the ZCode development environment.
What model does Z.ai Chat use?
The current Z.ai chat product identifies GLM-5.3-Flash as the model powering its chatbot experience.
Is Z.ai free?
Some parts of Z.ai can be accessed without a paid Coding Plan. ZCode offers a new-user trial, and Z.ai lists several free API models. Paid plans and API charges apply to other usage.
What is ZCode?
ZCode is Z.ai’s Agentic Development Environment designed for AI-assisted software development with GLM models and other supported providers.
Does Z.ai work with Claude Code?
Yes. Z.ai currently lists Claude Code among the tools supported by its GLM Coding Plan.
Is Z.ai available in the USA?
Z.ai provides English-language documentation and U.S.-dollar pricing, but the source material reviewed does not include an official guarantee that every Z.ai service is available without restriction throughout the United States.
Final Thoughts
Z.ai is more than a single chatbot. Its ecosystem combines GLM language and multimodal models, consumer chat, developer APIs, the GLM Coding Plan and ZCode. As new models and features are released, pricing, quotas and product details can change quickly, so current official documentation is especially important for time-sensitive details.
4 Comments