skip to content
gigarouter gigarouter
models / image-to-text · coming soon

LightOnOCR 1B 1025

lightonai/LightOnOCR-1B-1025

published Oct 2025 · updated Jun 2026

LightOnOCR 1B 1025 is a compact end-to-end vision-language model for OCR and document understanding that extracts text from document images.

est. price
~$0.235
/ 1k images · estimated, set at launch
API providers
0
downloads / mo
199.9K
license
apache-2.0

specs

TaskOptical Character Recognition (OCR) and Document Understanding
ArchitectureVision Transformer (Pixtral-based) encoder + Qwen3-based text decoder
Parameters1B
LicenseApache 2.0

about this model

LightOnOCR-1B-1025 is an end-to-end vision-language model for Optical Character Recognition (OCR) and document understanding that converts high-resolution document images into layout-aware, naturally ordered text. It combines a Pixtral-based Vision Transformer encoder with a Qwen3-based lightweight text decoder, distilled from high-quality open VLMs, making it fully differentiable with no external OCR pipeline.

The model is optimized for speed and efficiency: it is 5× faster than dots.ocr, 2× faster than PaddleOCR-VL-0.9B, and 1.73× faster than DeepSeekOCR. On a single H100, it processes 5.71 pages per second (approximately 493,000 pages per day) at a cost below $0.01 per 1,000 pages. It handles tables, receipts, forms, multi-column layouts, and mathematical notation. All benchmarks are evaluated using vLLM on Olmo-Bench.

best for

FAQ

What input formats does LightOnOCR 1B 1025 support?

PNG and JPEG images, typically rendered from PDF at 1540px longest dimension.

What is the output format?

Plain text extracted from the document image.

How does it compare to larger models?

It is 9x smaller and several times faster than prior best-performing models on OlmOCR-Bench, while achieving state-of-the-art accuracy in its weight class.

Is it open-source?

Yes, under Apache 2.0 license, model weights are available on Hugging Face.

How can I use it via the gigarouter API?

Use the OpenAI-compatible endpoint with your API key to send image URLs or base64-encoded images.

not yet live

We're benchmarking and onboarding LightOnOCR 1B 1025 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related image-to-text models

compare all →