Artificial Intelligence

Z.ai
API integration

Ship Artificial Intelligence features without building the integration. Full Z.ai API access via Proxy and 10+ MCP-ready tools for AI agents — extend models and mappings to fit your product.

Talk to us

Use Cases

Why integrate with Z.ai

Common scenarios for SaaS companies building Z.ai integrations for their customers.

Embed multimodal AI generation into your product

Offer your users a single connection to Z.ai that powers text, image, video, and audio generation natively inside your app. Instead of integrating four separate AI vendors, you ship one Z.ai integration via Truto and expose any modality your roadmap demands.

Power document intelligence workflows

SaaS platforms handling contracts, invoices, or regulatory PDFs can use Z.ai's layout parsing to extract structured markdown and bounding boxes, then chain into chat completions for extraction and classification. Truto handles the auth and request plumbing so your team focuses on the parsing pipeline.

Ship brand-compliant AI translation

Localization and content platforms can let customers upload glossary files to Z.ai and trigger translation agents that respect proprietary terminology. This becomes an upsell tier above generic LLM translation, with Truto managing the file upload and agent invocation.

Add web-grounded AI features without scrapers

Sales enablement, research, and content tools can ground AI outputs in real-time data using Z.ai's web search and URL reader endpoints. Your users get fresh, cited responses instead of stale model knowledge — no scraping infrastructure required.

Offer conversational asset creation

Marketing and presentation tools can plug into Z.ai's agent endpoints to generate slides, posters, and special-effects videos, then let end users iterate conversationally. Truto's connection layer lets your customers bring their own Z.ai account and consumption budget.

What You Can Build

Ship these features with Truto + Z.ai

Concrete product features your team can ship faster by leveraging Truto’s Z.ai integration instead of building from scratch.

Async video generation with polling

Trigger video generation jobs via Z.ai and poll the async result endpoint to surface a 'rendering' state in your UI until the final asset is ready.

PDF-to-structured-markdown pipeline

Run uploaded documents through Z.ai's layout parsing to extract markdown, tables, and layout coordinates, then feed the output into chat completions for downstream extraction.

Glossary-anchored translation agent

Upload customer terminology files via the Z.ai file endpoint and invoke the translation agent so brand names and technical terms render consistently across languages.

First-and-last-frame video interpolation

Let users supply two reference frames and a prompt to generate smooth branded transitions or product showcase videos without manual editing.

Web-augmented chat answers

Combine Z.ai's web search and URL reader endpoints with chat completions to deliver grounded, real-time answers inside your assistant or copilot feature.

Audio-to-action-items workflow

Transcribe meeting or call audio through Z.ai's transcription endpoint and pipe the transcript into chat completions to extract action items, summaries, and CRM updates.

SuperAI

Z.ai AI agent tools

Comprehensive AI agent toolset with fine-grained control. Integrates with MCP clients like Cursor and Claude, or frameworks like LangChain.

create_a_z_ai_chat_completion

Create a chat completion in zai that generates AI replies for a given conversation history. Supports multimodal inputs (text, image, video, file), function calling via tools, and both streaming and non-streaming output modes. Returns the completion object including id, model, choices, and usage. Required: model, messages.

create_a_z_ai_videos_generation

Create a video generation task in Z.AI using CogVideoX or Vidu models from a text prompt, image URL, or pair of first/last frame images. Supports text-to-video, image-to-video, and first/last-frame-to-video workflows. Returns the created generation task. Returns: model, id, request_id, task_status. Required: model.

get_single_z_ai_paas_async_result_by_id

Get the result of an asynchronous request in zai by task id. Returns the async result object with task-type-specific fields — either an AsyncVideoGenerationResponse or AsyncImageGenerationResponse depending on the originating task; consult the zai upstream docs for field-level details. Required: id.

create_a_z_ai_images_generation

Generate a high-quality image from a text prompt using GLM-Image series models in zai. Returns: url, id, created_at. Required: model, prompt.

create_a_z_ai_audio_transcription

Transcribe an audio file into text in zai using the GLM-ASR-2512 model, supporting multiple languages and optional real-time streaming output. Returns: id, created, request_id, model, text. Required: model.

create_a_z_ai_paas_tokenizer

Tokenize text input using a specified model in zai to calculate token counts, suitable for text length evaluation, model input estimation, dialogue context truncation, and cost calculation. Returns: created, id, request_id, usage. Required: model, messages.

create_a_z_ai_paas_layout_parsing

Submit a layout parsing request in zai using the GLM-OCR model to extract text content and layout information from a document image or PDF. Returns: id, created, model, md_results, layout_details, layout_visualization, data_info, usage, request_id, attributes. Required: model, file.

create_a_z_ai_paas_web_search

Perform a web search using the zai LLM-optimized Web Search API, which enhances intent recognition to return results better suited for large language model processing, including webpage titles, URLs, summaries, site names, and favicons. Returns: id, created, search_result.

create_a_z_ai_paas_reader

Create a web reader request in zai to read and parse the content of a specified URL. Returns: id, created, request_id, model, reader_result, url, content. Required: url.

create_a_z_ai_paas_file

Upload an auxiliary file (such as a glossary or terminology list) to zai to enhance translation accuracy and consistency. Returns the uploaded file record including id, object, bytes, filename, purpose, and created_at. Required: purpose, file. File size limit is 100 MB; accepted formats are pdf, doc, xlsx, ppt, txt, jpg, and png.

create_a_z_ai_agent

Create a zai agent task for one of three agent types: General Translation (multilingual text translation with auto-detection and glossary support), Popular Special Effects Videos (AI video generation from an image and prompt via a template), or GLM Slide/Poster (slide or poster generation from natural language instructions). Returns: id, agent_id, choices, usage, status, async_id.

create_a_z_ai_agents_async_result

Query the result of an asynchronous zai agent request. Returns: status, agent_id, async_id, choices, id, usage. Required: async_id.

create_a_z_ai_agents_conversation

Query conversation history for a zai slides_glm_agent (the only supported agent type). Returns id, agent_id, choices (with messages containing role and content, and finish_reason), and usage token statistics for synchronous responses, or status and async_id for asynchronous responses.

create_a_z_ai_async_images_generation

Create an async image generation job in zai using the GLM-Image model. Returns: model, id, request_id, task_status. Required: model, prompt.

Why Truto

Why use Truto’s MCP server for Z.ai

Other MCP servers give you a static tool list for one app. Truto gives you a managed, multi-tenant MCP infrastructure across 550+ integrations.

Auto-generated, always up to date

Tools are dynamically generated from curated documentation — not hand-coded. As integrations evolve, tools stay current without manual maintenance.

Fine-grained access control

Scope each MCP server to read-only, write-only, specific methods, or tagged tool groups. Expose only what your AI agent needs — nothing more.

Multi-tenant by design

Each MCP server is scoped to a single connected account with its own credentials. The URL itself is the auth token — no shared secrets, no credential leaking across tenants.

Works with every MCP client

Standard JSON-RPC 2.0 protocol. Paste the URL into Claude, ChatGPT, Cursor, or any MCP-compatible agent framework — tools are discovered automatically.

Built-in auth, rate limits, and error handling

Tool calls execute through Truto’s proxy layer with automatic OAuth refresh, rate-limit handling, and normalized error responses. No raw API plumbing in your agent.

Expiring and auditable servers

Create time-limited MCP servers for contractors or automated workflows. Optional dual-auth requires both the URL and a Truto API token for high-security environments.

How It Works

From zero to integrated

Go live with Z.ai in under an hour. No boilerplate, no maintenance burden.

Link your customer’s Z.ai account

Use Truto’s frontend SDK to connect your customer’s Z.ai account. We handle all OAuth and API key flows — you don’t need to create the OAuth app.

We handle authentication

Don’t spend time refreshing access tokens or figuring out secure storage. We handle it and inject credentials into every API request.

Call our API, we call Z.ai

Truto’s Proxy API is a 1-to-1 mapping of the Z.ai API. You call us, we call Z.ai, and pass the response back in the same cycle.

Unified response format

Every response follows a single format across all integrations. We translate Z.ai’s pagination into unified cursor-based pagination. Data is always in the result attribute.

FAQs

Common questions about Z.ai on Truto

Authentication, rate limits, data freshness, and everything else you need to know before you integrate.

How does authentication work for end users connecting their Z.ai account?

Z.ai uses API key authentication. Through Truto, your end users provide their Z.ai API key during the connection flow, and Truto securely stores and injects it on every request — your application never has to handle or persist the raw credential.

Which Z.ai operations are available through Truto today?

Truto exposes the full set of Z.ai endpoints needed for production workflows: chat completions, image generation (sync and async), video generation, audio transcription, layout parsing, tokenizer, web search, URL reader, file upload, agent invocation, agent conversations, and async result polling.

How do long-running jobs like video and image generation work?

Z.ai's video and async image endpoints return a task ID immediately. Your app polls the async result endpoint via Truto until the job completes. Truto passes through the task IDs and response payloads without modification, so you can implement polling or backoff logic on your side.

Are there unified APIs available for Z.ai?

Not yet. Z.ai is currently available as a direct passthrough integration, meaning you call Z.ai's native endpoints through Truto's unified connection and auth layer. If you need a unified AI API across multiple providers, contact Truto — these are built on request.

Can we upload files like glossaries or documents through the integration?

Yes. The Z.ai file endpoint accepts files (including formats like .xlsx and .txt up to Z.ai's documented size limits) and Truto proxies the upload. The returned file reference can then be bound to translation or other agents in subsequent calls.

How are rate limits and errors handled?

Truto passes Z.ai's native rate limit headers and error responses back to your application unchanged, so you can implement retry and backoff logic based on Z.ai's published limits. Per-end-user quotas are governed by each user's own Z.ai account and plan.

Z.ai

Get Z.ai integrated into your app

Our team understands what it takes to make a Z.ai integration successful. A short, crisp 30 minute call with folks who understand the problem.