Zhipu AI (智谱)
Zhipu AI / BigModel GLM series — bilingual models with multimodal and tool capabilities.
Overview
Zhipu AI (智谱AI) is one of China's leading AI companies and a spin-off from Tsinghua University. Its BigModel platform serves the GLM (General Language Model) series, with strong bilingual Chinese-English performance.
Official Website: https://open.bigmodel.cn API Documentation: https://open.bigmodel.cn/dev/api
Key features
- Bilingual — Optimized for Chinese with strong English support
- Vision & video understanding — Image and video analysis
- Embeddings — Text embeddings for semantic search
- Image & video generation — Text-to-image and text-to-video
- Audio — Text-to-speech and speech-to-text
- Web search & code execution — Built-in tools for grounded answers
- Knowledge base — Retrieval over uploaded documents
- Thinking mode — Extended reasoning for complex problems
Using Zhipu AI with Yunxin
Address Zhipu models using the provider/model convention by prefixing with zhipu/ (for example, zhipu/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="zhipu/glm-4",
messages=[
{"role": "user", "content": "你好,请介绍一下智谱AI"}
]
)
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: "zhipu/glm-4",
messages: [{ role: "user", content: "你好,请介绍一下智谱AI" }],
});
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": "zhipu/glm-4",
"messages": [{"role": "user", "content": "你好,请介绍一下智谱AI"}]
}'Available models
Query the live catalog with the Models API:
curl "https://api.yuhuanstudio.com/v1/models?provider=zhipu" \
-H "Authorization: Bearer $YUNXIN_API_KEY"Capabilities and pricing are tracked per model. Use GET /v1/models?provider=zhipu and each model's capabilities array as the authoritative source rather than relying on a hardcoded list.
Official resources
How is this guide?