Interfaze: Interfaze Beta
interfaze/interfaze-beta
Access Interfaze Beta from Interfaze using 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>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="interfaze/interfaze-beta",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "interfaze/interfaze-beta",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
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.
Frequently Asked Questions
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.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Interfaze Beta to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $1.5 |
| Output | $3.5 |
Interfaze Beta supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.
Interfaze Beta can generate up to 32K tokens in a single response.
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.
Get started with Puter.js
Add Interfaze Beta to your app without worrying about API keys or setup.
Read the Docs View Tutorials