Interfaze 1.1 Lite

copy markdown

Open weights

Smaller open weight model. Available for self-hosting.

interfaze-1.1-lite is a smaller any-to-text open-weight model. It takes text, images, audio and files, runs on a single 80 GB GPU, and is available for self-hosting.

Specs and pricing

Model ID

interfaze-1.1-lite

Input tokens

$0.85 / MTok

Output tokens

$1.50 / MTok

Context window

128k tokens

Max output tokens

32k tokens

Input modalities

Text, Images, Audio, File

Output

Text

Reasoning

Available

Caching

Included

Compare models | View pricing | View limits

Quickstart

Interfaze SDK

Vercel AI SDK

OpenAI SDK

import { Interfaze } from "interfaze";

const interfaze = new Interfaze();

const response = await interfaze.chat.completions.create({
	model: "interfaze-1.1-lite",
	messages: [
		{
			role: "user",
			content: [
				{ type: "text", text: "Extract the details from this ID" },
				{ type: "image_url", image_url: { url: "https://r2public.jigsawstack.com/interfaze/examples/id.jpg" } },
			],
		},
	],
});

console.log(response.choices[0]?.message.content);

See the getting started guide for setup and authentication.

The weights are on Hugging Face. They combine several models, each under its own license; see the license file for the terms. You need one 80 GB GPU with compute capability 8.9 or newer, like an H100, and ffmpeg for audio.

hf download interfaze-ai/interfaze-1-lite requirements.txt --local-dir .
pip install -r requirements.txt

from transformers import AutoModel

model = AutoModel.from_pretrained("interfaze-ai/interfaze-1-lite", trust_remote_code=True)

answer = model.chat(
    [{"role": "user", "content": "What is the total, and which item is highlighted?"}],
    files=["receipt.jpg"],
)
print(answer["content"])

The Hugging Face model card covers every method and its limitations.

interfaze-1

OCR (Image & Document)

Interfaze 1.1 Lite

Quickstart

Self-host