Z.ai

Z.ai is the home of the GLM model family, offered as a conversational assistant, a developer API, and a coding subscription. The chat app runs on GLM-5.3-Flash, a multimodal model that accepts text, images, video, and files, while the API exposes the flagship GLM-5.3 model with a one-million-token context window. Teams can use the product as a general assistant, add it to coding tools through the GLM Coding Plan, or call the API to build their own applications. Pricing combines a free chat tier, prepaid token usage, and monthly coding plans.

Key Features

• Chat assistant powered by GLM-5.3-Flash, with support for text, image, video, and file inputs.
• GLM-5.3 flagship model with a one-million-token context window for long documents and codebases.
• An agent mode for multi-step tasks, alongside thinking controls in the chat interface.
• GLM Slide and Poster Agent, which researches a topic and produces a finished deck or poster as a PDF.
• A translation agent and a web search tool that can be called from the API.
• Image generation, video generation, OCR, and document layout parsing through separate endpoints.
• A GLM Coding Plan that works with popular coding tools and includes usage across the models.

Who is it for

• Developers who want an OpenAI-compatible style API backed by the GLM model family.
• Coding teams that want a subscription plan for use inside editors and coding agents.
• Analysts and office workers who need help with documents, research, and presentations.
• Builders who need image, video, OCR, or search capabilities from a single provider.

What can you do with Z.ai

• Chat with GLM-5.3-Flash and attach images, video, PDFs, or office files.
• Ask the assistant to work through a multi-step task in agent mode.
• Generate a slide deck or poster from a short description and download it as a PDF.
• Translate text or documents with the translation agent.
• Call the API for chat completions, web search, image generation, or video generation.
• Connect the Coding Plan to an editor or coding tool and work against your repository.

How does Z.ai work

1. Open the chat and sign in, or create an API key in the developer console.
2. Choose the model or tool for the task, such as chat, an agent, slides, or translation.
3. Provide a prompt and attach files, images, or video when the task needs them.
4. Review the output, adjust the request, and export the result or copy it into your work.
5. For production use, call the API or subscribe to a coding plan with the usage level you need.

Pricing

• GLM Coding Plan Lite: $18 per month, or $14.40 per month quarterly and $12.60 per month yearly, with 10,000 credits per week.
• Coding Plan Pro: $80 per month, or $64 quarterly and $56 yearly, with six times the Lite usage.
• Coding Plan Max: $168 per month, or $134.40 quarterly and $117.60 yearly, with fourteen times the Lite usage.
• GLM-5.3 API: $1.40 per million input tokens and $4.40 per million output tokens, with cached input at $0.26 per million.
• GLM-5.3-Flash API: $0.15 per million input tokens and $0.50 per million output tokens.
• Usage bundles are also sold separately for API consumption.

FAQ

Is Z.ai free to use?

The chat has a free tier, and the pricing page lists free models on the international platform. Paid coding plans and API usage are billed separately.

What models does Z.ai offer?

The current lineup includes GLM-5.3, GLM-5.3-Flash, GLM-5.2, GLM-4.6V, and GLM-OCR, covering text, vision, and document tasks.

What is the GLM Coding Plan?

It is a subscription for using GLM models inside coding tools, with weekly credit allowances and discounts for quarterly or yearly billing.

Can I generate slides with Z.ai?

Yes. The GLM Slide and Poster Agent turns a short request into a slide deck or poster, researches the topic, and exports a PDF.

Does Z.ai have an API?

Yes. The platform provides API access to language, vision, video, image, OCR, search, and agent capabilities, with usage-based pricing.

Can I use my own coding tool?

The Coding Plan is described as compatible with popular coding tools, so you can connect it to the editor or agent you already use.