x-ai/grok-3-mini
Model Card
Grok 3 Mini is a lightweight, cost-efficient reasoning model that thinks before responding, ideal for logic-based tasks that don't require deep domain knowledge. It features configurable reasoning effort and exposes accessible thinking traces for transparency.
Context Window
131K
tokens
Max Output
131,072
tokens
Input Cost
$0.3
per million tokens
Output Cost
$0.5
per million tokens
API Usage Example
Add Grok 3 Mini 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: "x-ai/grok-3-mini"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Get started with Puter.js
Add Grok 3 Mini to your app without worrying about API keys or setup.
Read the Docs View Tutorials