Grok Vision Beta API

Access Grok Vision Beta from xAI using Puter.js AI API.

Get Started

Model Card

Grok Vision Beta was the initial vision-enabled API model from xAI, providing image understanding and multimodal capabilities for processing text alongside visual inputs. It was released alongside grok-beta for enterprise API testing with an 8K context window.

Context Window 8K

tokens

Max Output 8K

tokens

Input Cost $5

per million tokens

Output Cost $15

per million tokens

Input text, image

modalities

Tool Use Yes

 

Knowledge Cutoff Aug 2024

 

Release Date Nov 1, 2024

 

API Usage Example

Add Grok Vision Beta to your app with just a few lines of code.
No API keys, no backend, no configuration required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "x-ai/grok-vision-beta"
}).then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "x-ai/grok-vision-beta"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

More Models from xAI

Chat

xAI: Grok 4.1 Fast

Grok 4.1 Fast is xAI's best tool-calling model released November 2025, featuring a 2M context window...

 Chat

xAI: Grok 4.1 Fast Non-Reasoning

Grok 4.1 Fast Non-Reasoning is the low-latency, non-reasoning variant of Grok 4.1 Fast that skips ex...

 Chat

xAI: Grok 4 Fast

Grok 4 Fast is an optimized variant delivering performance similar to Grok 4 but using 40% fewer thi...

View all xAI models →

Frequently Asked Questions

What is this Grok Vision Beta API about?

The Grok Vision Beta API gives you access to xAI's chat model through Puter.js. With just a few lines of JavaScript, you can integrate Grok Vision Beta into any web app or Node.js project — no API keys, no backend, and no configuration required.

Who created Grok Vision Beta?

Grok Vision Beta was created by xAI and released on Nov 1, 2024.

What is the context window of Grok Vision Beta?

Grok Vision Beta supports a context window of 8K tokens. For reference, that is roughly equivalent to 16 pages of text.

What is the max output length of Grok Vision Beta?

Grok Vision Beta can generate up to 8K tokens in a single response.

What is the knowledge cutoff of Grok Vision Beta?

Grok Vision Beta has a knowledge cutoff date of Aug 2024. This means the model was trained on data available up to that date.

What types of input can Grok Vision Beta process?

Grok Vision Beta accepts the following input types: text, image. It produces: text.

Does Grok Vision Beta support tool use (function calling)?

Yes, Grok Vision Beta supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.

How much does it cost?
The Grok Vision Beta API is available through the User-Pays Model. As a developer, you can add the Grok Vision Beta API to your app for free — your users pay for their own AI costs directly.
Price per 1M tokens
Input$5
Output$15
How do I access the Grok Vision Beta API?

You can access the Grok Vision Beta API with just a few lines of JavaScript — no API keys, no backend, and no configuration required. Include the Puter.js library in your project and start making calls right away. For more details, check out our documentation.

Does the Grok Vision Beta API work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Grok Vision Beta API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Grok Vision Beta to your app without worrying about API keys or setup.

Read the Docs View Tutorials