LightOn

LightOnOCR

About

LightOnOCR is a 1B open-weight model from LightOn. Compact document VLM. It accepts text and images. Context window is 8K. Released October 20, 2025.

Parameters
1B
Published parameter count.
Context window
8K
Tokens of context on a request.
License
Apache-2.0
License on the weights.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	—
Output / 1M	—

Benchmarks

Published scores for LightOnOCR, from the LightOnOCR post.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	olmOCR-Bench overall: 76.1.
Cost and performance	Lower listed rate, mid-pack latency

Methods

Methods this model serves. Payload shapes are in the docs.

Method	Returns
markdown	The page as Markdown

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="lightonai/lightonocr-1b-1025",
    messages=[{"role": "user", "content": "What is in this image?"}],
)

print(response.choices[0].message.content)