ZhipuAI / ChatGLM / BigModel

Use ZhipuAI’s GLM models through Portkey for advanced Chinese and multilingual AI.

Quick Start

Get started with ZhipuAI in under 2 minutes:

Python

from portkey_ai import Portkey

# 1. Install: pip install portkey-ai
# 2. Add @zhipu provider in model catalog
# 3. Use it:

portkey = Portkey(api_key="PORTKEY_API_KEY")

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

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

import Portkey from 'portkey-ai'

// 1. Install: npm install portkey-ai
// 2. Add @zhipu provider in model catalog
// 3. Use it:

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY"
})

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

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

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL

# 1. Install: pip install openai portkey-ai
# 2. Add @zhipu provider in model catalog
# 3. Use it:

client = OpenAI(
    api_key="PORTKEY_API_KEY",  # Portkey API key
    base_url=PORTKEY_GATEWAY_URL
)

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

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

import OpenAI from "openai"
import { PORTKEY_GATEWAY_URL } from "portkey-ai"

// 1. Install: npm install openai portkey-ai
// 2. Add @zhipu provider in model catalog
// 3. Use it:

const client = new OpenAI({
    apiKey: "PORTKEY_API_KEY",  // Portkey API key
    baseURL: PORTKEY_GATEWAY_URL
})

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

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

# 1. Add @zhipu provider in model catalog
# 2. Use it:

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "model": "@zhipu/glm-4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Image Generation

ZhipuAI supports image generation through the CogView model family. Use the standard OpenAI-compatible images API:

Python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.images.generate(
    model="@zhipu/cogview-4-250304",
    prompt="A serene mountain landscape at sunset",
    size="1024x1024"
)

print(response.data[0].url)

import Portkey from 'portkey-ai'

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY"
})

const response = await portkey.images.generate({
    model: "@zhipu/cogview-4-250304",
    prompt: "A serene mountain landscape at sunset",
    size: "1024x1024"
})

console.log(response.data[0].url)

curl https://api.portkey.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "model": "@zhipu/cogview-4-250304",
    "prompt": "A serene mountain landscape at sunset",
    "size": "1024x1024"
  }'

Supported Parameters:

Parameter	Type	Description
prompt	string	The text prompt for image generation (Required)
model	string	Model to use, e.g. cogview-4-250304 (Required)
size	string	Image dimensions
user	string	End-user identifier

---

Add Provider in Model Catalog

Before making requests, add ZhipuAI to your Model Catalog:

1. Go to Model Catalog → Add Provider
2. Select ZhipuAI
3. Enter your ZhipuAI API key
4. Name your provider (e.g., zhipu)

Complete Setup Guide

See all setup options and detailed configuration instructions

---

Next Steps

Gateway Configs

Add fallbacks, load balancing, and more

Observability

Monitor and trace your ZhipuAI requests

Prompt Library

Manage and version your prompts

Metadata

Add custom metadata to requests

For complete SDK documentation:

SDK Reference

Complete Portkey SDK documentation