Z.ai

Overview

Z.ai provides the GLM model family (including its coding-focused endpoint) with native multimodal capabilities. Z.ai is OpenAI- and Zhipu-compatible, so through Yunxin its models are accessed via the Chat Completions API format.

Official Website: https://z.ai API Documentation: https://docs.z.ai

Key features

• Multimodal input — Text plus images (image_url) and documents (file_url)
• Thinking/reasoning — Extended reasoning via the thinking parameter
• Function calling — Full tool use support
• Structured output — JSON and schema-constrained responses via response_format
• Embeddings — Text embeddings for semantic search
• Image & video generation — Text-to-image and text-to-video
• Audio — Text-to-speech and speech-to-text
• Streaming — Server-sent events for real-time responses

Using Z.ai with Yunxin

Address Z.ai models using the provider/model convention by prefixing with zai/ (for example, zai/glm-4). Requests use the same Yunxin base URL (https://api.yuhuanstudio.com/v1) and your Yunxin sk- API key.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="zai/glm-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "zai/glm-4",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "zai/glm-4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Multimodal content

Z.ai supports multiple content types within a Chat Completions message. Capabilities vary by model — check the Models API.

Images

{
  "type": "image_url",
  "image_url": {"url": "https://example.com/photo.jpg"}
}

Documents

{
  "type": "file_url",
  "file_url": {"url": "https://example.com/document.pdf"}
}

Thinking/reasoning

Enable extended reasoning for complex tasks:

response = client.chat.completions.create(
    model="zai/glm-4",
    messages=[{"role": "user", "content": "Solve this complex problem..."}],
    extra_body={"thinking": {"type": "enabled"}}
)

Function calling

response = client.chat.completions.create(
    model="zai/glm-4",
    messages=[{"role": "user", "content": "What's the weather?"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather",
            "parameters": {
                "type": "object",
                "properties": {"location": {"type": "string"}},
                "required": ["location"]
            }
        }
    }]
)

Available models

Query the live catalog with the Models API:

curl "https://api.yuhuanstudio.com/v1/models?provider=zai" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Official resources

• Z.ai Documentation
• API Reference