Most AI tasks no longer need a frontier model Read launch post

docling

An open model that reads documents and page images into text. docling

  • Accuracy

    31.7%

    olmOCR-Bench, checks passed

  • Time per request

    Not timed one request at a time

  • Serverless price

    $0.398

    per 1,000 pages

Call it

from sie_sdk import SIEClient
​
client = SIEClient(api_key="sk-sie-…")
​
# Parse a document → clean markdown, tables and layout kept.
result = client.extract(
"modeldocling",
{"document": fileHTMLstore-receipt.htmlbrowse},
)
print(result["data"]["markdown"])
document_bytes=$(base64 < 'store-receipt.html' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/docling \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"document\":{\"data\":\"$document_bytes\",\"format\":\"html\"}}]}"
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: docling (SIE primitive: /extract). Keep the model id configurable.

Task
- Input: an uploaded document (PDF / Office / scan).
- Behaviour: return clean markdown for the document, preserving tables and reading order
- Call the selected SIE primitive once per request and map the response into your domain type.

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.

Next to the other document models

Next to the other document models
Model olmOCR-Bench, checks passed Time per request Serverless price Size
LightOnOCR-3 lightonai Not measured Not timed $0.14 in · $1.37 out per 1M tokens 4.5B
GLM-OCR zai-org 73.8% Not timed $0.25 per 1,000 images 1.3B
LightOnOCR 2 1B lightonai 77.7% Not timed $2.00 per 1,000 pages 1.0B
MinerU2.5 Pro 2604 1.2B opendatalab 59.1% Not timed Run in your cloud 1.2B
All 6 document models

Measured on public datasets

Measured on public datasets
Dataset Accuracy
olmOCR-Bench Measured internally 31.7%

Facts

Size
80M parameters
License
other
Reads
Image, document
Endpoint
extract
Evaluation
Accuracy
Run on SIE against the public dataset named in each figure
Prices
Serverless list prices, effective 10 Nov 2026

Run docling on Serverless or in your own cloud

Native Inference

Kubernetes in your own cloud, backed by our engineers.

  • Terraform modules for your cloud
  • Apache-2.0, same engine as Serverless
  • GPU workers scale to zero between jobs
  • Separate worker pools for each tenant
Agent prompt Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment.

SIE Local

The open-source server on your own machine.

  • Runs on your NVIDIA GPU
  • One container, no cluster
  • Process your data fully offline
  • Same SDK and model IDs as Serverless
docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-default

Talk to us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.