z-ai-api

Standardize access to Z.ai GLM chat, vision, media, and retrieval APIs.

1|Updated Dec 30, 2025

Search Tags:#api #multimodal #generate #web-search #function-calling #glm #zai

Ready to run

npx skills add https://github.com/jrajasekera/claude-skills --skill z-ai-api

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: z-ai-api
Source: https://github.com/jrajasekera/claude-skills/tree/main/skills/z-ai-api
Command: npx skills add https://github.com/jrajasekera/claude-skills --skill z-ai-api

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Enable developers to access and orchestrate Z.ai's diverse AI capabilities (chat, image, video, transcription, translation, web search, and function calling) from a single API surface, simplifying integration and experimentation.

Core Features & Use Cases

Unified access to GLM chat models, vision/video generation models, and retrieval tools via the Z.ai API.
Supports text, multimodal inputs, image/video generation, audio transcription, web search, and function calling to automate complex workflows.
Use cases include building an AI assistant that chats, generates media, translates content, and retrieves information in a single application.

Quick Start

Create a Z.ai client and call the chat completions endpoint with model glm-4.7 to begin a conversation.

Frequently Asked Questions about z-ai-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I integrate Z.ai multimodal APIs into my application?▼

To integrate Z.ai multimodal APIs, use this Skill to standardize access to GLM chat, vision, media, and retrieval endpoints. You can orchestrate chat completions, media generation, and web search within a single application interface.

What is the unified Z.ai API surface used for?▼

The unified Z.ai API surface is used to access diverse AI capabilities like text chat, image and video generation, audio transcription, translation, and function calling from a single standardized interface.

Which GLM models are supported for chat completions and video generation?▼

Supported models include glm-4.7 and glm-4.6v for chat and vision, cogview-4 and glm-image for image generation, and cogvideox-3 and viduq1-text for video generation tasks.

Can I use function calling and web search together in a single Z.ai workflow?▼

Yes, you can use function calling and web search together to automate complex workflows. The Skill supports combining these retrieval tools with multimodal inputs to build interactive AI assistants.

What's the best way to handle errors when calling Z.ai generation endpoints?▼

The best way to handle Z.ai endpoint errors is to follow the parameter guidance and error handling schemas defined by the Skill. This ensures correct model selection and request formatting across chat, media, and retrieval APIs.

Does Z.ai API support audio transcription and translation?▼

Yes, the Z.ai API supports audio transcription and translation. Developers can access these capabilities alongside chat, vision, and media generation by utilizing the defined endpoints and parameter schemas.