Interfaze: Interfaze Beta

interfaze/interfaze-beta

Access Interfaze Beta from Interfaze using the Puter.js AI API.

Get Started

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

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

Model Card

Interfaze Beta is a hybrid model from Interfaze, a Y Combinator-backed company, built around specialized DNN/CNN encoders paired with a transformer decoder rather than a single general-purpose language model.

The design targets deterministic developer tasks such as OCR, document and ID processing, web scraping, speech-to-text, and structured, validated JSON extraction, and it returns confidence scores and bounding boxes alongside its output.

Interfaze reports 85.7% on olmOCR (versus 75.3% for Gemini-3-Flash and 73.9% for Claude-Sonnet-4.6), 79.5% exact-match accuracy on its own structured-output benchmark (versus 77.3% for Gemini-3-Flash), and a 2.4% word-error rate on VoxPopuli speech transcription, ahead of Deepgram Nova-3 (2.9%) and Whisper Large v3 (3.5%).

The API is OpenAI-compatible, supports a 1M-token context window, and is aimed at pipelines that need consistent, schema-validated output rather than open-ended conversation or general reasoning.

Context Window 1M

tokens

Max Output 32K

tokens

Input Cost $1.5

per million tokens

Output Cost $3.5

per million tokens

Release Date N/A

Model Playground

Try Interfaze Beta instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat interfaze/interfaze-beta

Chat with Interfaze Beta

Frequently Asked Questions

How do I use Interfaze Beta?

You can access Interfaze Beta by Interfaze through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Interfaze Beta free?

Interfaze Beta is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.

What is the pricing for Interfaze Beta?

Interfaze Beta costs $1.5 per 1M input tokens and $3.5 per 1M output tokens.

	Price per 1M tokens
Input	$1.5
Output	$3.5

What is the context window of Interfaze Beta?

Interfaze Beta supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.

What is the max output length of Interfaze Beta?

Interfaze Beta can generate up to 32K tokens in a single response.

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

Yes — the Interfaze 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.

Add Interfaze Beta to your app for free

Developers can integrate Interfaze Beta for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.

Get started How pricing works