Skip to main content

Marketplace · 45+ models

Automation & RPA Software that does the work

Process automation, workflow AI, document processing, intelligent OCR, and RPA agents — for finance ops, contract review, KYC, and back-office automation.

Editor's pick

The automation & rpa model most teams reach for first.

All categories
Editor's pick

LayoutLMv3

Microsoft·133M / 368M params·CC-BY-NC-SA 4.0

Multimodal layout-aware document understanding (text + image + position).

Deploy on YobibyteCompare on InferenceBench

Spec sheet

Family
Microsoft
Parameters
133M / 368M
License
CC-BY-NC-SA 4.0
Status
Live
Best for
Software that does the work
Sits in
Automation & RPA

Pricing and routing rank visible on InferenceBench. Variants and quantisations appear in the Yobibyte deploy console.

The rest of the lineup

5 more in Automation & RPA. All deployable in one click.

#
Model
Family
Params
License
Deploy
02
Donut

OCR-free document parser; end-to-end image-to-structured-JSON.

NAVER Clova
200M
MIT
Deploy
03
TrOCR Large

Transformer-based OCR for printed and handwritten text recognition.

Microsoft
558M
MIT
Deploy
04
Pix2Struct

Pretrained on web screenshots — strong on charts, UIs, and infographics.

Google
282M / 1.3B
Apache 2.0
Deploy
05
PaddleOCR

Production-grade multilingual OCR pipeline with table recognition.

Baidu
varies
Apache 2.0
Deploy
06
ScreenAI

Vision-language model specialized for UI and infographic understanding.

Google
5B
Research
Deploy

Showing 6 of 45+. The full catalog (with quantisations, hardware variants, and per-region pricing) lives in the Yobibyte console.

Quick start

Five lines to your first automation & rpa call.

Every model in this category is reachable from the same Yobitel SDK. Swap the model name; the rest of the call shape stays identical. Authenticated via your workspace key.

Get an API keySDK on GitHub
automation-rpa-quickstart.py
PythonTypeScriptcURL
from yobitel import Inference

# LayoutLMv3 — document understanding
client = Inference(model="microsoft/layoutlmv3")

invoice = client.extract(
    pdf="invoice_2025_q1.pdf",
    schema={
        "invoice_number":  "string",
        "total_amount":    "decimal",
        "line_items":      "array",
        "payment_terms":   "string",
    },
)

print(invoice.invoice_number, invoice.total_amount)

Where teams ship this

Real automation & rpa. In production.

Four use cases that customers run today. Pick a model from the lineup above, deploy on Yobibyte, plug it into the surrounding stack. Done.

  1. 01

    Invoice and receipt processing

  2. 02

    Contract analysis and clause extraction

  3. 03

    Form and ID document understanding

  4. 04

    Email triage and ticket routing

Frameworks

Bring what your team already knows

TransformersPaddleOCRLangChainDSPy

Yobitel handles the serving layer (GPU scheduling, KV cache, autoscaling, request batching) so your team focuses on the model and the product.

Learn about Yobibyte

Explore the rest

Other categories in the marketplace

85+

Computer Vision

Object detection, image classification, segmentation

120+

NLP & Language

Text generation, translation, sentiment, summarization

95+

Generative AI

Image gen, text gen, code gen, multimodal

60+

Data Analytics

Predictive analytics, forecasting, anomaly detection

50+

Industry-Specific

Vertical-specific models by industry

30+

Speech & Audio

ASR, TTS, speaker diarization, audio classification

25+

Recommendation

Recommender systems, personalization, content matching

Don't see what you need?

Bring your own model or fine-tune one of ours. Yobitel engineers can sit with your team and ship the right stack.

Start BuildingContact Sales