Better Markdown than Mistral OCR 4.1, for 35% less

Turn PDFs and scanned pages into clean Markdown that keeps tables and reading order intact, ready for search and LLMs. SIE runs LightOnOCR-3, an open model built for documents, so you pay less per page.

Get started Run in your cloud

LightOnOCR-3 on SIE

Table rows kept together

Page image

Crop of the Inti Everspring, Methomyl 90 SP technical data sheet: a borderless specification table with characteristic, specification and method columns. — Inti Everspring, Methomyl 90 SP technical data sheet

Markdown

Characteristic	Specification	Method of analysis
Al, as Methomyl	87.5 - 92.5 %	High Performance Liquid Chromatography
pH (1 % in water)	4.0 - 8.0	pH-meter
Appearance	White to cream powder	Visual

Mistral OCR 4.1 split this specification table into loose lists

Mistral OCR 4.1

Table rows flattened

Same page image

Returned Markdown

CHARACTERISTIC

Al, as Methomyl pH (1 % in water) Appearance

SPECIFICATION

87.5 - 92.5 % 4.0 - 8.0 White to cream powder

METHOD OF ANALYSIS

High Performance Liquid Chromatography pH-meter Visual

Chunks split at these headings lose the table’s row associations.

arXiv:2604.08538 Study of 14 document parsers on 2,000 business pages: none is consistently strong across all five areas it tests
ParseBench: A Document Parsing Benchmark for AI Agents

Boyang Zhang, Sebastián G. Acosta, Preston Carlson and others

“no method is consistently strong across all five dimensions”
9 April 2026
Microsoft Foundry Blog Microsoft: when a model loses table structure, teams bolt on a layout parser
“When the model does not preserve table structure, you add a layout parser.”
29 September 2026

Claude Sonnet 5.5 accuracy, 9x cheaper

Run this eval

Quality

benchmark checks passed ↑

SIE LightOnOCR-3

SIE LightOnOCR-3 85.1%

Claude Sonnet 5.5

Claude Sonnet 5.5 84.1%

Mistral OCR 4.1

Mistral OCR 4.1 83.3%

GPT-6 Luna

GPT-6 Luna 80.6%

Claude Haiku 5.5

Claude Haiku 5.5 80.0%

Cost

USD / 1k pages ↓

GPT-6 Luna

$1.02 GPT-6 Luna

Claude Haiku 5.5

$1.24 Claude Haiku 5.5

SIE LightOnOCR-3

$2.60 SIE LightOnOCR-3

Mistral OCR 4.1

$4.00 Mistral OCR 4.1

Claude Sonnet 5.5

Claude Sonnet 5.5 $25.42

olmOCR-Bench

1,366 page images from the public benchmark

Checks: 8,234 text, reading-order, table and math checks
Prices: Real-time list prices: SIE effective 2026-10-13, Mistral read 2026-10-10

Send a page image, get Markdown back

from urllib.request import urlopen
from sie_sdk import SIEClient
client = SIEClient(api_key="API keysk-sie-…")
image_bytes = urlopen(imagemethomyl-page.pngbrowse).read()
image = {"data": image_bytes, "format": "png"}
result = client.extract(
    "modellightonai/LightOnOCR-3-4B",
    {"id": "methomyl-page", "images": [image]},
    instruction="instructiongrounding",
    options={"max_new_tokens": 12288, "temperature": 0.1, "top_p": 1},
)
print(result["entities"][0]["text"])

import { unpackMessage } from '@superlinked/sie-sdk';

const imageResponse = await fetch("https://superlinked.com/reference/doc-to-markdown/methomyl-page.png");
if (!imageResponse.ok) throw new Error(`Image returned ${imageResponse.status}`);
const image = new Uint8Array(await imageResponse.arrayBuffer());
const response = await fetch("https://api.superlinked.com/v1/extract/lightonai%2FLightOnOCR-3-4B", {
  method: 'POST',
  headers: {
    Authorization: "Bearer sk-sie-…",
    'Content-Type': 'application/json',
    Accept: 'application/msgpack',
  },
  body: JSON.stringify({
    items: [{ id: "methomyl-page", images: [{ data: Buffer.from(image).toString('base64'), format: "png" }] }],
    params: {"instruction":"grounding","options":{"max_new_tokens":12288,"temperature":0.1,"top_p":1}},
  }),
});
if (!response.ok) throw new Error(`SIE returned ${response.status}`);
const result = unpackMessage<{ items: { id: string; entities: { text: string }[] }[] }>(
  new Uint8Array(await response.arrayBuffer()),
);
const item = result.items[0];
if (result.items.length !== 1 || item?.id !== "methomyl-page" || !item.entities[0]?.text) {
  throw new Error('Invalid OCR response');
}
console.log(item.entities[0].text);

curl --fail --silent --show-error 'https://superlinked.com/reference/doc-to-markdown/methomyl-page.png' -o 'methomyl-page.png'
image_bytes=$(base64 < 'methomyl-page.png' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/lightonai%2FLightOnOCR-3-4B \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"id\":\"methomyl-page\",\"images\":[{\"data\":\"$image_bytes\",\"format\":\"png\"}]}],\"params\":{\"instruction\":\"grounding\",\"options\":{\"max_new_tokens\":12288,\"temperature\":0.1,\"top_p\":1}}}"

Build the "Doc to Markdown" capability into my app using the Superlinked Inference Engine (SIE).

Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: lightonai/LightOnOCR-3-4B (SIE primitive: /extract). Keep the model id configurable.

Task
- Input: an uploaded image containing text.
- Behaviour: return the text visible in the image
- Fetch the unmodified PNG from https://superlinked.com/reference/doc-to-markdown/methomyl-page.png. Send one POST https://api.superlinked.com/v1/extract/lightonai%2FLightOnOCR-3-4B with item id "methomyl-page" and images [{data: original PNG bytes, format: "png"}]. Preserve params {"instruction":"grounding","options":{"max_new_tokens":12288,"temperature":0.1,"top_p":1}}; keep this model and profile selected and fail when unavailable instead of substituting another model. In Python use SIEClient.extract; TypeScript uses the native REST body and public unpackMessage decoder shown in Copy. Read the transcription from items[0].entities[0].text (Python single-item result["entities"][0]["text"]), without repairing or calculating source values.

Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

Run

Markdown

METHOMYL 90 SP

Characteristic	Specification	Method of analysis
Al, as Methomyl	87.5 - 92.5 %	High Performance Liquid Chromatography
pH (1 % in water)	4.0 - 8.0	pH-meter
Appearance	White to cream powder	Visual

Convert a million pages for $2,599

Serverless API

We host the models; you call one API.

No idle GPUs, pay for what you use
SOC 2 Type 2, US or EU data residency
$50 of credit to start, no card required

Get started

Self-hosted (Kubernetes)

SIE in your clusters, backed by our engineers.

Data stays in your own cloud account
Same models and API as Serverless
Terraform to your cloud in minutes

Talk to us Deploy guide

Run locally

The open-source server on your own machine.

docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-sglang-vision-extract

Quickstart

Switch to SIE in 5 minutes

from mistralai.client import Mistral

page_url = "https://example.com/scanned-page.png"
client = Mistral(api_key="…")
result = client.ocr.process(
    model="mistral-ocr-4-1",
    document={"type": "image_url", "image_url": page_url},
)
print(result.pages[0].markdown)

SIE

from sie_sdk import SIEClient

page_url = "https://example.com/scanned-page.png"
client = SIEClient(api_key="sk-sie-…")
result = client.extract(
    "lightonai/LightOnOCR-3-4B",
    {"images": [page_url]},
    output="markdown",
)
print(result["markdown"])