Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Z.AI with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Access the full Z.AI platform from any AI agent. chat completions with GLM models, image and video generation, audio transcription, OCR, web search, and agent

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 12 capabilities

The complete Z.AI capability set.

These are the exact actions your AI can choose when you ask it to work with Z.AI.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Z.AI.

  1. 01

    Generate image

    Returns image URLs (temporary, expire after 30 days). Specify model, prompt, and optional size/quality. GLM-Image recommended sizes: 1280x1280, 1568x1056, 1056x1568, 1472x1088, 1088x1472, 1728x960, 960x1728. Generate high-quality images from text prompts using GLM-Image models

  2. 02

    Agent chat

    AI agents including: general_translation (multilingual translation with 40+ languages, auto-detection, glossary support), slides_glm_agent (one-click slide/poster generation from natural language), and vidu_template_agent (special effects video generation). Pass the full agent request body as JSON including agent_id and messages. Run Z.AI agents for translation, slide generation, or poster creation

  3. 03

    Audio transcription

    AI's ASR model. Supports .wav and .mp3 files up to 25MB and 30 seconds. Can provide hotwords for domain-specific vocabulary and context prompts for long-form transcription. Supports streaming output. Transcribe audio files to text using the GLM-ASR-2512 model

  4. 04

    Generate image async

    Use get_async_result with the task ID to check status and retrieve the generated image. Only supports glm-image model. Use this for long-running generation tasks. Generate images asynchronously. returns a task ID for later retrieval

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Z.AI.

  1. 05

    Generate video

    Supports text-to-video, image-to-video, and first/last frame-to-video. Returns a task ID. use get_async_result to check status and retrieve the video URL. Specify model, prompt, and optional quality/size/fps/duration. Generate videos from text prompts or images using CogVideoX or Vidu models

  2. 06

    Get async result

    Returns task_status (PROCESSING, SUCCESS, FAIL) and the generated image or video URLs when complete. Use this after generate_image_async or generate_video returns a task ID. Retrieve the result of an asynchronous image or video generation task

  3. 07

    Get conversation history

    Only supports slides_glm_agent. Use the conversation_id from a prior agent_chat response. Retrieve the conversation history for a Z.AI slide agent session

  4. 08

    Layout parsing

    Returns recognized text in Markdown format, detailed layout information (bounding boxes for text, images, formulas, tables), and optional visualization results. Supports PDF, JPG, PNG formats. PDF up to 50MB/30 pages, images up to 10MB. Parse document layouts and extract text using the GLM-OCR model

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Z.AI.

  1. 09

    Tokenize

    Returns prompt_tokens, image_tokens, video_tokens, and total_tokens. Useful for text length evaluation, model input estimation, context truncation, and cost calculation. Supports glm-4.6, glm-4.6v, and glm-4.5 models. Count tokens for given messages using Z.AI models

  2. 10

    Chat completion

    2, GLM-4.7, or other available models. Supports multimodal inputs (text, images, audio, video, files), configurable parameters (temperature, max_tokens, capabilities), and both streaming and non-streaming modes. Pass the full request body as JSON including model, messages, and optional parameters. Generate AI chat completions using Z.AI GLM models

  3. 11

    Web reader

    Supports markdown and text output formats, cache control, image retention, and optional summaries for images and links. Read and parse the content of a web page URL

  4. 12

    Web search

    Supports filtering by domain whitelist and time range (oneDay, oneWeek, oneMonth, oneYear, noLimit). Returns up to 50 results per search. Search the web using Z.AI's LLM-optimized search engine

Observed, not estimated

939ms average. Fast in production.

Z.AI is checked daily against the live service.

Daily averagePeak 1137ms
Aug 20Today
Fastest day
792ms
Slowest day
1137ms
14-day trend
Slowing+14%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Z.AI, so you can see the experience inside your AI.

It does not authenticate your account with Z.AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Z.AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_YbDoY2kX4ZG9rzJgMpkdkPO2uOhqn2U6SvelxeRg/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Z.AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "zai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_YbDoY2kX4ZG9rzJgMpkdkPO2uOhqn2U6SvelxeRg/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Z.AI owners ask.

  • 01

    How do I get my Z.AI API key?

    Visit the Z.AI API Keys page to create or manage your API key. Once created, copy it and paste it into the API key field in the setup wizard. The key is used as a Bearer token in the Authorization header for all API requests.

  • 02

    Which Z.AI models are available?

    The MCP supports all Z.AI models: GLM-5.2, GLM-5.1, GLM-5-Turbo, GLM-4.7, GLM-4.7-flash, GLM-4.6, GLM-4.5 series for chat; GLM-Image and CogView-4 for image generation; CogVideoX-3 and Vidu for video generation; GLM-ASR-2512 for audio transcription; GLM-OCR for layout parsing; and search-prime for web search.

  • 03

    Can my AI generate images and videos?

    Yes! Use generate_image for synchronous image generation (returns URLs immediately), or generate_image_async for long-running tasks (returns a task ID. use get_async_result to retrieve). For video, use generate_video which always runs asynchronously. call get_async_result with the returned task ID to check status and get the video URL when complete.

  • 04

    Does the Z.AI MCP support multimodal inputs?

    Yes. The chat_completion capability supports multimodal inputs including text, images (image_url), video (video_url), and files (file_url) when using vision models like GLM-5V-Turbo. Pass the full messages array as JSON with the appropriate content types. The layout_parsing capability also supports both image and PDF inputs for OCR.

  • 05

    What is the base URL for Z.AI API calls?

    All Z.AI API calls are sent to https://api.z.ai/api. The engine automatically appends the correct path prefix (e.g. /paas/v4/ for platform APIs, /v1/ for agent APIs). When using the GLM Coding Plan, you may need to configure a dedicated endpoint. refer to the Z.AI documentation for details.

  • 06

    Can I use the Z.AI agents for translation and slide generation?

    Yes. The agent_chat capability supports three agent types: general_translation (multilingual translation with 40+ languages, auto-detection, glossary support), slides_glm_agent (one-click slide/poster generation from natural language), and vidu_template_agent (special effects video generation). After running the slides agent, use get_conversation_history with the conversation_id to retrieve generated file URLs.

  • 07

    Is there a rate limit on Z.AI APIs?

    Yes, Z.AI enforces rate limits that vary by model and subscription tier. Check the Z.AI Rate Limits page for your specific limits. If you exceed the rate limit, the API returns an error and the engine surfaces the error message. For high-volume use cases, consider using async endpoints and spacing out requests.

Explore

More in Developer Tools

Suggestions