OpenGVLab: InternVL3 78B

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

InternVL3 78B is an open-source multimodal large language model developed by OpenGVLab, combining a 6B vision transformer with a 72.7B Qwen2.5 language backbone. It is the flagship of the InternVL3 series and achieves state-of-the-art performance among open-source multimodal models.

The model excels at visual reasoning, document understanding, OCR, chart interpretation, and video comprehension. On the MMMU benchmark it scores 72.2%, surpassing GPT-4o (70.7%), and on MathVista it reaches approximately 79.0 compared to GPT-4o's 63.8. It also achieves an OCRBench score of 906.

A key differentiator is its native multimodal pre-training approach, which trains vision and language capabilities together from the start rather than retrofitting vision onto a text-only model. This actually improves text performance over the base Qwen2.5, making it a strong choice for developers who need both visual and textual reasoning in a single model with a 32,768-token context window.

Context Window N/A

tokens

Max Output 33K

tokens

Input Cost $0.15

per million tokens

Output Cost $0.6

per million tokens

Release Date Apr 10, 2025

Code Example

Add AI to your app with the Puter.js AI API, no API keys or setup required.

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

puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

Frequently Asked Questions

How do I use InternVL3 78B?

InternVL3 78B is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for InternVL3 78B?

InternVL3 78B costs $0.15 per 1M input tokens and $0.6 per 1M output tokens.

	Price per 1M tokens
Input	$0.15
Output	$0.6

Who created InternVL3 78B?

InternVL3 78B was created by OpenGVLab and released on Apr 10, 2025.

What is the max output length of InternVL3 78B?

InternVL3 78B can generate up to 33K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the InternVL3 78B 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 AI to your application without worrying about API keys or setup.

Explore Models View Tutorials