Grok 2 Vision API

Access Grok 2 Vision from xAI using Puter.js AI API.

Get Started

Model Card

Grok 2 Vision is a multimodal AI model that combines text and visual understanding capabilities, excelling at object recognition, visual math reasoning (MathVista), and document-based question answering (DocVQA). It supports image analysis with a 32K context window.

Context Window 8K

tokens

Max Output 8K

tokens

Input Cost $2

per million tokens

Output Cost $10

per million tokens

Input text, image

modalities

Tool Use Yes

 

Knowledge Cutoff Aug 2024

 

Release Date Aug 20, 2024

 

API Usage Example

Add Grok 2 Vision 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-2-vision"
}).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-2-vision"
        }).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 2 Vision API about?

The Grok 2 Vision API gives you access to xAI's chat model through Puter.js. With just a few lines of JavaScript, you can integrate Grok 2 Vision into any web app or Node.js project — no API keys, no backend, and no configuration required.

Who created Grok 2 Vision?

Grok 2 Vision was created by xAI and released on Aug 20, 2024.

What is the context window of Grok 2 Vision?

Grok 2 Vision 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 2 Vision?

Grok 2 Vision can generate up to 8K tokens in a single response.

What is the knowledge cutoff of Grok 2 Vision?

Grok 2 Vision 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 2 Vision process?

Grok 2 Vision accepts the following input types: text, image. It produces: text.

Does Grok 2 Vision support tool use (function calling)?

Yes, Grok 2 Vision 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 2 Vision API is available through the User-Pays Model. As a developer, you can add the Grok 2 Vision API to your app for free — your users pay for their own AI costs directly.
Price per 1M tokens
Input$2
Output$10
How do I access the Grok 2 Vision API?

You can access the Grok 2 Vision 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 2 Vision API work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Grok 2 Vision 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 2 Vision to your app without worrying about API keys or setup.

Read the Docs View Tutorials