z-ai/glm-4-32b
Model Card
GLM-4-32B is a 32-billion parameter bilingual (Chinese-English) foundation model by Zhipu AI, pre-trained on 15TB of reasoning-focused data. It delivers performance comparable to GPT-4o on code generation, function calling, and Q&A tasks while remaining deployable on accessible hardware.
Context Window
N/A
tokens
Max Output
N/A
tokens
Input Cost
$0.1
per million tokens
Output Cost
$0.1
per million tokens
API Usage Example
Add Z.AI: GLM 4 32B to your app with just a few lines of code.
No API keys, no backend, no configuration required.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "z-ai/glm-4-32b"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Get started with Puter.js
Add Z.AI: GLM 4 32B to your app without worrying about API keys or setup.
Read the Docs View Tutorials