HrFlow background
The industry-leading Parser for Profiles & Jobs

Parsing API

The Parsing API converts the most complex resumes, CVs, and job descriptions into structured Talent & Workforce Data. Extract 60+ data points from PDF, DOCX, PNG, JPEG, and more, across 43+ languages with deterministic accuracy and blazing speed.

Read the Docs
+96% accuracy
43+ Languages
60+ Data points
GDPR-ready & EU AI Act
99.99% uptime
output.json
{
  "parsing": {
    "model": "hrflow-file-v2.1",
    "confidence": 0.92,
  },
  "profile": {
    "name": "John Smith",
    "title": "Data Scientist",
    "skills": ["ML", "Python"]
  }
}

Trusted by Customers, Partners & the AI Ecosystem

ManpowerLogo
CritLogo
EuropeanUnionLogo
SanofiLogo
EnhanceCVLogo
TeamtailorLogo
API RESPONSE

Build Your Single Source of Truth

Get clean, structured, normalized JSON you can store, search, score, and route anywhere.
No JSON drift. No hallucinations. Only deterministic output values.

Select Parsing Type

Upload a resume or CV → returns Parsing + Profile JSON.

Explore

View full schemaTry Live DemoAPI Docs

Top Extracted Fields

Personal Info

name, email, phone, picture, etc.

Experience

companies, jobs, dates, tasks, etc.

Education

schools, degrees, dates, tasks, etc.

Skills

hard-skills, soft-skills, certifications, etc.

Location

geopoints, addresses, cities, countries

response.json
 1{
 2  "parsing": {
 3    "model": "hrflow-resume-v2.1",
 4    "confidence": 0.95
 5  },
 6  "profile": {
 7    "info": {
 8      "first_name": "Sarah",
 9      "last_name": "Chen",
10      "email": "sarah@example.com"
11    },
12    "education": [{
13      "school": "MIT",
14      "degree": "M.S. Computer Science"
15    }],
16    "experiences": [{
17      "company": "Google",
18      "title": "Senior Engineer"
19    }],
20    "skills": ["Python", "ML", "React"]
21  }
22}
🎯 MODEL SELECTOR

Parsing Algorithms' Versions by Use Case

Pick the right HR-native model version for your needs—balancing use case, speed, precision, and cost.

Precision

Relative accuracy grade (A highest) based on internal evaluation.

Speed

Typical p95 latency per request (varies by document size).

ModuleAlgorithmDataUse CaseSpeedPrecision
ParsingQuickSilver
CVResumeJobText
Blazing-fast parsing for immediate user experiences. Best for: clean resumes and well-structured job descriptions.500msC-
ParsingHawk
CVResume
Balances speed with precision. Best for: parsing scanned resumes and complex layout design.1.5sC
ParsingAtlas
CVResumeJob Text
Precision-focused, prioritizing accuracy over speed. Best for: scans, images, complex layouts and multipage documents.3sB
ParsingChronos
CVResume
Most capable parsing model. Best for: complex multi-page resumes, nested work experiences, scans, and images.5sA
INTERACTIVE SANDBOX

Try & Install the Parsing API

Test the API in real-time with your own documents. Get production-ready code in seconds.

API Playground

Interactive testing environment

PostmanCollection
1

Parsing Type

2

API Token

3

Run

Input

Upload a resume to parse

PDF, Word, or Image - Maximum size: 10 MB.

Enter your API token or sign in to try the parsing demo.

Response
JSON
{
  "profile": {
    "info": {
      "first_name": "John",
      "last_name": "Smith",
      "email": "john@example.com"
    },
    "experiences": [{
      "company": "TechCorp",
      "title": "Senior Engineer",
      "location": "San Francisco"
    }],
    "skills": ["Python", "ML", "NLP"]
  }
}
CUSTOMER STORIES

Don't take our word for it!

Trusted by fast-growing HR Tech and Global Enterprise

“

Deterministic parsing, no hallucinations

vs. OpenAI
Before HrFlow.ai

+30s response time per resume, costs exploded, JSON drift broke our pipelines, and we had to deal with hallucinations.

After HrFlow.ai

HrFlow.ai gave us deterministic parsing, a stable schema, and hands-on support to meet our GDPR and EU AI Act goals.

“

Finally: zero-config parsing

vs. Textkernel
Before HrFlow.ai

Textkernel felt like a 'configure forever' parser: mapping rules, edge cases, and still inconsistent outputs.

After HrFlow.ai

HrFlow.ai just worked: unified profile object, better work experience parsing, and no weeks lost tuning ontologies.

“

Accuracy + the HR stack we needed

vs. Affinda
Before HrFlow.ai

Affinda's accuracy wasn't strong enough for our matching engine—especially experience, location, and education.

After HrFlow.ai

HrFlow.ai improved parsing results and saved us months by providing HR-native connectors and a recommendation system we planned to build in-house.

“

Deterministic parsing, no hallucinations

vs. OpenAI
Before HrFlow.ai

+30s response time per resume, costs exploded, JSON drift broke our pipelines, and we had to deal with hallucinations.

After HrFlow.ai

HrFlow.ai gave us deterministic parsing, a stable schema, and hands-on support to meet our GDPR and EU AI Act goals.

“

Finally: zero-config parsing

vs. Textkernel
Before HrFlow.ai

Textkernel felt like a 'configure forever' parser: mapping rules, edge cases, and still inconsistent outputs.

After HrFlow.ai

HrFlow.ai just worked: unified profile object, better work experience parsing, and no weeks lost tuning ontologies.

“

Accuracy + the HR stack we needed

vs. Affinda
Before HrFlow.ai

Affinda's accuracy wasn't strong enough for our matching engine—especially experience, location, and education.

After HrFlow.ai

HrFlow.ai improved parsing results and saved us months by providing HR-native connectors and a recommendation system we planned to build in-house.

“

Deterministic parsing, no hallucinations

vs. OpenAI
Before HrFlow.ai

+30s response time per resume, costs exploded, JSON drift broke our pipelines, and we had to deal with hallucinations.

After HrFlow.ai

HrFlow.ai gave us deterministic parsing, a stable schema, and hands-on support to meet our GDPR and EU AI Act goals.

“

Finally: zero-config parsing

vs. Textkernel
Before HrFlow.ai

Textkernel felt like a 'configure forever' parser: mapping rules, edge cases, and still inconsistent outputs.

After HrFlow.ai

HrFlow.ai just worked: unified profile object, better work experience parsing, and no weeks lost tuning ontologies.

“

Accuracy + the HR stack we needed

vs. Affinda
Before HrFlow.ai

Affinda's accuracy wasn't strong enough for our matching engine—especially experience, location, and education.

After HrFlow.ai

HrFlow.ai improved parsing results and saved us months by providing HR-native connectors and a recommendation system we planned to build in-house.

“

Deterministic parsing, no hallucinations

vs. OpenAI
Before HrFlow.ai

+30s response time per resume, costs exploded, JSON drift broke our pipelines, and we had to deal with hallucinations.

After HrFlow.ai

HrFlow.ai gave us deterministic parsing, a stable schema, and hands-on support to meet our GDPR and EU AI Act goals.

“

Finally: zero-config parsing

vs. Textkernel
Before HrFlow.ai

Textkernel felt like a 'configure forever' parser: mapping rules, edge cases, and still inconsistent outputs.

After HrFlow.ai

HrFlow.ai just worked: unified profile object, better work experience parsing, and no weeks lost tuning ontologies.

“

Accuracy + the HR stack we needed

vs. Affinda
Before HrFlow.ai

Affinda's accuracy wasn't strong enough for our matching engine—especially experience, location, and education.

After HrFlow.ai

HrFlow.ai improved parsing results and saved us months by providing HR-native connectors and a recommendation system we planned to build in-house.

“

Matching-ready parsing at scale

vs. Rchilli
Before HrFlow.ai

RChilli's location and education extraction was too noisy for our ranking workflows.

After HrFlow.ai

HrFlow.ai improved those core fields and delivered a unified, deterministic Profile object at scale.

“

Parsing that survives real data

vs. DaXtra
Before HrFlow.ai

DaXtra couldn't handle real-world inputs—scans, weird layouts, mixed attachments.

After HrFlow.ai

HrFlow.ai's vision preprocessing + layout parsing raised accuracy and cut latency without manual cleanup.

“

No more ontology limits

vs. Sovren
Before HrFlow.ai

Sovren was stuck in rules and ontologies—modern resumes kept breaking it.

After HrFlow.ai

HrFlow.ai's semantic + layout parsing stabilized results and halved our manual review.

“

Matching-ready parsing at scale

vs. Rchilli
Before HrFlow.ai

RChilli's location and education extraction was too noisy for our ranking workflows.

After HrFlow.ai

HrFlow.ai improved those core fields and delivered a unified, deterministic Profile object at scale.

“

Parsing that survives real data

vs. DaXtra
Before HrFlow.ai

DaXtra couldn't handle real-world inputs—scans, weird layouts, mixed attachments.

After HrFlow.ai

HrFlow.ai's vision preprocessing + layout parsing raised accuracy and cut latency without manual cleanup.

“

No more ontology limits

vs. Sovren
Before HrFlow.ai

Sovren was stuck in rules and ontologies—modern resumes kept breaking it.

After HrFlow.ai

HrFlow.ai's semantic + layout parsing stabilized results and halved our manual review.

“

Matching-ready parsing at scale

vs. Rchilli
Before HrFlow.ai

RChilli's location and education extraction was too noisy for our ranking workflows.

After HrFlow.ai

HrFlow.ai improved those core fields and delivered a unified, deterministic Profile object at scale.

“

Parsing that survives real data

vs. DaXtra
Before HrFlow.ai

DaXtra couldn't handle real-world inputs—scans, weird layouts, mixed attachments.

After HrFlow.ai

HrFlow.ai's vision preprocessing + layout parsing raised accuracy and cut latency without manual cleanup.

“

No more ontology limits

vs. Sovren
Before HrFlow.ai

Sovren was stuck in rules and ontologies—modern resumes kept breaking it.

After HrFlow.ai

HrFlow.ai's semantic + layout parsing stabilized results and halved our manual review.

“

Matching-ready parsing at scale

vs. Rchilli
Before HrFlow.ai

RChilli's location and education extraction was too noisy for our ranking workflows.

After HrFlow.ai

HrFlow.ai improved those core fields and delivered a unified, deterministic Profile object at scale.

“

Parsing that survives real data

vs. DaXtra
Before HrFlow.ai

DaXtra couldn't handle real-world inputs—scans, weird layouts, mixed attachments.

After HrFlow.ai

HrFlow.ai's vision preprocessing + layout parsing raised accuracy and cut latency without manual cleanup.

“

No more ontology limits

vs. Sovren
Before HrFlow.ai

Sovren was stuck in rules and ontologies—modern resumes kept breaking it.

After HrFlow.ai

HrFlow.ai's semantic + layout parsing stabilized results and halved our manual review.

đź”— INTEGRATIONS

Works with the tools you use

Integrate 200+ tools with the flip of a switch.

Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
HrFlow.ai Data Studio

HrFlow.ai Data Studio

HR-native ETL with 200+ connectors plus Webhooks to ingest, normalise, and sync jobs & profiles across your stack—reliable pipelines with unified schemas.

Zapier ETL

Zapier ETL

No-code automation platform with 8,000+ app integrations to move data between tools using triggers + actions.

Make.com ETL

Make.com ETL

Visual automation platform to extract/transform/route data across 3,000+ apps (plus HTTP modules for any API).

Microsoft Flow ETL

Microsoft Flow ETL

Microsoft Power Automate—workflow automation with 1,000+ API connectors (and support for custom connectors).

Workato ETL

Workato ETL

Enterprise iPaaS/automation platform with 1,200+ pre-built connectors for orchestrating integrations and data workflows at scale.

Salesforce Flow Automation

Salesforce Flow Automation

Salesforce's low-code workflow automation tool; extended via AppExchange with 7,000+ apps to add integrations and capabilities.

🚀 KEY FEATURES

State-of-the-art Parsing Accuracy

HrFlow.ai Parsing combines cutting-edge Deep Computer Vision and Deep Natural Language Processing to turn the most complex, noisy documents (resumes, CVs, jobs, interview notes, HR files) into clean, structured data with high accuracy, low latency, and production-grade scalability.

Parse resumes, CVs, and job descriptions in 43+ languages, including Arabic, Chinese, Dutch, English, French, German, Italian, Japanese, Portuguese, Romanian, Spanish, and more.

43+ Languages
đź”’ ENTERPRISE-READY

Trust & Security

Built for sensitive HR data—secure by default, enterprise-ready.

01

Encryption

TLS in transit + encryption at rest to protect documents and extracted data.

02

Retention control

Minimal storage by default, with configurable retention policies to match your compliance needs.

03

AI-Act / GDPR / DPA ready

Built for sensitive HR data—secure by default, enterprise-ready. AI Act– and GDPR-ready processing, with documented controls for data handling and compliance.

04

Location / Region

Data processing and storage can be aligned with your required region (e.g., EU or US) depending on your deployment.

Visit Trust Center→
đź“Š FEATURE COMPARISON

HrFlow.ai Parsing is the most advanced and complete Parsing API for HR Data

Feature
HrFlow.ai Parsing
HrFlow.ai Parsing
OpenAI/Gemini
OpenAI/Gemini
OpenAI/Gemini
Affinda
Affinda
Textkernel
Textkernel
Rchilli
Rchilli
Daxtra
Daxtra
Hireablity
Hireablity
Sovren
Sovren
Deployment & Trust
Foundation
2016
2015
2012
2001
2010
2002
1999
1996
Headquarters
🇫🇷 France
🇺🇸 USA
🇦🇺 Australia
🇳🇱 Netherlands
🇮🇳 India
🇬🇧 UK
🇺🇸 USA
🇺🇸 USA
🇺🇸 USA & 🇪🇺 EU Servers
Built-in
config
config
Built-in
Built-in
GDPR / AI-Act
By design
By design
By design
HR Compliance (Safety & Guardrails)
Built-in
Built-in
Built-in
Built-in
Built-in
Built-in
Built-in
Pretraining Data
HQ HR Data
Noisy & Biased Web Data
HR Data
HQ HR Data
HQ HR Data
HQ HR Data
HR Data
HR Data
HR-Focused
Input Security (Prompt injection)
Unified output object (JSON drift)
Deterministic output values (hallucination)
Pricing model
per CV
per input+output tokens (expensive)
per page (unpredictable)
per cv
per cv
per cv
per cv
per cv
Speed (avg response / 1 page resume)
500ms (QuickSilver)
25s to 45s
6.6s
11.25s
8.66s
5.33s
4.8s
4.2s
Speed (avg response / avg job)
100ms (QuickSilver)
>8s
~3s
~3s
~3s
~2s
~2s
~2s
Core Technology
Technology
Deep Computer Vision / Deep NLP / LLM / VLM
LLM / VLM
Deep Computer Vision / Deep NLP
Deep NLP / Heuristics / Static Ontologies
Deep NLP / Heuristics / Static Ontologies
Rules / Heuristics / Static Ontologies
Rules / Heuristics / Static Ontologies
Rules / Heuristics / Static Ontologies
Multilingual
43 lang
40 lang
56 lang
29 lang
31 lang
23 lang
30 lang
12 lang
webhooks + async batch
Semantic Parsing
Picture Parsing
Contact Info accuracy (Name, Email, Location, Phone)
94.26%
~96% (hallucination risk)
90.95%
86.02%
90.55%
84.87%
80.30%
78.68%
Location Accuracy (Info, Work, Edu)
67.36%
~70% (hallucination risk)
60.18%
31.16%
54.22%
44.69%
40.12%
40.12%
Dates Accuracy (Birth, Work, Edu)
90.92%
~93% (hallucination risk)
68.31%
69.10%
71.01%
76.40%
69.14%
64.57%
Work Experience Accuracy
93.30%
~92% (hallucination risk)
82.67%
83.37%
80.83%
76.26%
71.69%
Education Accuracy
88.59%
~90% (hallucination risk)
71.13%
63.23%
62.88%
59.88%
55.31%
50.74%
Titles, Skills, Certifications, Languages Normalization
Built-in (Tagging API)
Tasks Parsing
Built-in
Config (prompt)
Geocoding (lat, lon, etc.)
Built-in (Geocoding API)
Document Layout Analysis
Text OCR
Built-in (HR tuned)
Built-in
Built-in
add-on
add-on
add-on
Formats supported
Word, PDF, Image, 200+ formats
Word, PDF, Image
Word, PDF, Image
Mostly Docs
Mostly Docs
Mostly Docs
Only Docs
Only Docs
Document Vision preprocessing (crop/deskew/denoise/boost)
Text OCR auto-routing
Page Orientation auto-rotate
Distortion / perspective correction
Document classification (resume vs cover letter vs other)
Document splitting (multi-page → multiple profiles)
Config (prompt)
HR Stack integrations (add-ons)
HR data enrichment & taxonomies
Built-in (Linking/Tagging/Asking APIs)
Config (Mapping)
Dropzone UI
Connector (Data Studio)
Browser Extension
Connector (Data Studio)
Search Engine Add-on
Built-in (Searching API)
Recommender System Add-on
Built-in (Scoring API)
Jobboards / ATS / HCM / HRIS connectors
200+ connectors (Data Studio)
Candidate & Recruiter UI
Widgets (App Studio)
âť“ COMMON QUESTIONS

Frequently Asked Questions

Everything you need to know about the Parsing API

🧩 COMPLETE API SUITE

Go beyond the Parsing API

Our APIs are designed to complement each other and unlock your data's full potential

Full Extraction API Suite

Transform HR documents into structured, enriched Talent & Workforce Data — powering every layer of Hiring Intelligence.

API Overview
94%82%71%58%

Ranking API Suite

Unlock Hiring Superintelligence at scale — with transparent, fair, and explainable ranking across every Talent signal.

API Overview

GET STARTED

Ready to transform your HR data?

Start parsing resumes and job postings in minutes with our powerful API.

Start for free→Talk to sales

HrFlow.ai is an API-first company and the leading AI-powered HR data automation platform.

The company helps +1000 customers (HR software vendors, Staffing agencies, large employers, and headhunting firms) to thrive in a high-volume and high-frequency labor market.

The platform provides a complete and fully integrated suite of HR data processing products based on the analysis of hundreds of millions of career paths worldwide -- such as Parsing API, Tagging API, Embedding API, Searching API, Scoring API, and Upskilling API. It also offers a catalog of +200 connectors to build custom scenarios that can automate any business logic.

GDPR Compliant badgeCapterra 4.8 rating badge

SOLUTIONS

PRODUCT

RESOURCES

COMPANY