Hyperbrowser Extract API
Structured data extraction jobs that pull typed records from one or more pages using prompts and JSON schemas.
Structured data extraction jobs that pull typed records from one or more pages using prompts and JSON schemas.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/extract-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Hyperbrowser Extract API
version: 1.0.0
servers:
- url: https://api.hyperbrowser.ai
description: Production server
tags:
- name: Extract
paths:
/api/extract:
post:
summary: Start an extract job
security:
- ApiKeyAuth: []
x-codeSamples:
- lang: javascript
label: Start extract job
source: "import { Hyperbrowser } from '@hyperbrowser/sdk';\n\nconst client = new Hyperbrowser({ apiKey: 'your-api-key' });\n\nawait client.extract.start({\n urls: ['https://example.com'],\n prompt: 'Extract the main headline and author'\n});"
- lang: python
label: Start extract job
source: "from hyperbrowser import Hyperbrowser\nfrom hyperbrowser.models import StartExtractJobParams\n\nclient = Hyperbrowser(api_key='your-api-key')\n\nclient.extract.start(StartExtractJobParams(\n urls=['https://example.com'],\n prompt='Extract the main headline and author'\n))"
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/StartExtractJobParams'
responses:
'200':
description: Extract job started successfully
content:
application/json:
schema:
$ref: '#/components/schemas/StartExtractJobResponse'
'400':
description: Invalid request parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'500':
description: Server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
tags:
- Extract
operationId: postApiExtract
x-operation-id-source: derived
/api/extract/{id}:
get:
summary: Get extract job status and results
security:
- ApiKeyAuth: []
x-codeSamples:
- lang: javascript
label: Get extract job
source: 'import { Hyperbrowser } from ''@hyperbrowser/sdk'';
const client = new Hyperbrowser({ apiKey: ''your-api-key'' });
await client.extract.get(''job-id'');'
- lang: python
label: Get extract job
source: 'from hyperbrowser import Hyperbrowser
client = Hyperbrowser(api_key=''your-api-key'')
client.extract.get(''job-id'')'
parameters:
- name: id
in: path
required: true
schema:
type: string
responses:
'200':
description: Extract job details
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractJobResponse'
'404':
description: Extract job not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'500':
description: Server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
tags:
- Extract
operationId: getApiExtractById
x-operation-id-source: derived
/api/extract/{id}/status:
get:
summary: Get extract job status
security:
- ApiKeyAuth: []
x-codeSamples:
- lang: javascript
label: Get extract job status
source: 'import { Hyperbrowser } from ''@hyperbrowser/sdk'';
const client = new Hyperbrowser({ apiKey: ''your-api-key'' });
await client.extract.getStatus(''job-id'');'
- lang: python
label: Get extract job status
source: 'from hyperbrowser import Hyperbrowser
client = Hyperbrowser(api_key=''your-api-key'')
client.extract.get_status(''job-id'')'
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
'200':
description: Extract job status
content:
application/json:
schema:
$ref: '#/components/schemas/JobStatusResponse'
'404':
description: Extract job not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'500':
description: Server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
tags:
- Extract
operationId: getApiExtractByIdStatus
x-operation-id-source: derived
components:
schemas:
ProxyCountry:
type: string
enum:
- AD
- AE
- AF
- AL
- AM
- AO
- AR
- AT
- AU
- AW
- AZ
- BA
- BD
- BE
- BG
- BH
- BJ
- BO
- BR
- BS
- BT
- BY
- BZ
- CA
- CF
- CH
- CI
- CL
- CM
- CN
- CO
- CR
- CU
- CY
- CZ
- DE
- DJ
- DK
- DM
- EC
- EE
- EG
- ES
- ET
- EU
- FI
- FJ
- FR
- GB
- GE
- GH
- GM
- GR
- HK
- HN
- HR
- HT
- HU
- ID
- IE
- IL
- IN
- IQ
- IR
- IS
- IT
- JM
- JO
- JP
- KE
- KH
- KR
- KW
- KZ
- LB
- LI
- LR
- LT
- LU
- LV
- MA
- MC
- MD
- ME
- MG
- MK
- ML
- MM
- MN
- MR
- MT
- MU
- MV
- MX
- MY
- MZ
- NG
- NL
- 'NO'
- NZ
- OM
- PA
- PE
- PH
- PK
- PL
- PR
- PT
- PY
- QA
- RANDOM_COUNTRY
- RO
- RS
- RU
- SA
- SC
- SD
- SE
- SG
- SI
- SK
- SN
- SS
- TD
- TG
- TH
- TM
- TN
- TR
- TT
- TW
- UA
- UG
- US
- UY
- UZ
- VE
- VG
- VN
- YE
- ZA
- ZM
- ZW
- ad
- ae
- af
- al
- am
- ao
- ar
- at
- au
- aw
- az
- ba
- bd
- be
- bg
- bh
- bj
- bo
- br
- bs
- bt
- by
- bz
- ca
- cf
- ch
- ci
- cl
- cm
- cn
- co
- cr
- cu
- cy
- cz
- de
- dj
- dk
- dm
- ec
- ee
- eg
- es
- et
- eu
- fi
- fj
- fr
- gb
- ge
- gh
- gm
- gr
- hk
- hn
- hr
- ht
- hu
- id
- ie
- il
- in
- iq
- ir
- is
- it
- jm
- jo
- jp
- ke
- kh
- kr
- kw
- kz
- lb
- li
- lr
- lt
- lu
- lv
- ma
- mc
- md
- me
- mg
- mk
- ml
- mm
- mn
- mr
- mt
- mu
- mv
- mx
- my
- mz
- ng
- nl
- 'no'
- nz
- om
- pa
- pe
- ph
- pk
- pl
- pr
- pt
- py
- qa
- ro
- rs
- ru
- sa
- sc
- sd
- se
- sg
- si
- sk
- sn
- ss
- td
- tg
- th
- tm
- tn
- tr
- tt
- tw
- ua
- ug
- us
- uy
- uz
- ve
- vg
- vn
- ye
- za
- zm
- zw
ProxyState:
type:
- string
- 'null'
enum:
- AL
- AK
- AZ
- AR
- CA
- CO
- CT
- DE
- FL
- GA
- HI
- ID
- IL
- IN
- IA
- KS
- KY
- LA
- ME
- MD
- MA
- MI
- MN
- MS
- MO
- MT
- NE
- NV
- NH
- NJ
- NM
- NY
- NC
- ND
- OH
- OK
- OR
- PA
- RI
- SC
- SD
- TN
- TX
- UT
- VT
- VA
- WA
- WV
- WI
- WY
- al
- ak
- az
- ar
- ca
- co
- ct
- de
- fl
- ga
- hi
- id
- il
- in
- ia
- ks
- ky
- la
- me
- md
- ma
- mi
- mn
- ms
- mo
- mt
- ne
- nv
- nh
- nj
- nm
- ny
- nc
- nd
- oh
- ok
- or
- pa
- ri
- sc
- sd
- tn
- tx
- ut
- vt
- va
- wa
- wv
- wi
- wy
description: Optional state code for proxies to US states. Is mutually exclusive with proxyCity. Takes in two letter state code.
StartExtractJobParams:
type: object
properties:
urls:
type: array
items:
type: string
systemPrompt:
type: string
maxLinks:
type: number
prompt:
type: string
schema:
type: object
sessionOptions:
$ref: '#/components/schemas/CreateSessionParams'
waitFor:
default: 0
type: number
additionalProperties: false
required:
- urls
Platform:
type: string
enum:
- chrome
- firefox
- safari
- edge
ISO639_1:
type: string
enum:
- aa
- ab
- ae
- af
- ak
- am
- an
- ar
- as
- av
- ay
- az
- ba
- be
- bg
- bh
- bi
- bm
- bn
- bo
- br
- bs
- ca
- ce
- ch
- co
- cr
- cs
- cu
- cv
- cy
- da
- de
- dv
- dz
- ee
- el
- en
- eo
- es
- et
- eu
- fa
- ff
- fi
- fj
- fo
- fr
- fy
- ga
- gd
- gl
- gn
- gu
- gv
- ha
- he
- hi
- ho
- hr
- ht
- hu
- hy
- hz
- ia
- id
- ie
- ig
- ii
- ik
- io
- is
- it
- iu
- ja
- jv
- ka
- kg
- ki
- kj
- kk
- kl
- km
- kn
- ko
- kr
- ks
- ku
- kv
- kw
- ky
- la
- lb
- lg
- li
- ln
- lo
- lt
- lu
- lv
- mg
- mh
- mi
- mk
- ml
- mn
- mo
- mr
- ms
- mt
- my
- na
- nb
- nd
- ne
- ng
- nl
- nn
- 'no'
- nr
- nv
- ny
- oc
- oj
- om
- or
- os
- pa
- pi
- pl
- ps
- pt
- qu
- rm
- rn
- ro
- ru
- rw
- sa
- sc
- sd
- se
- sg
- si
- sk
- sl
- sm
- sn
- so
- sq
- sr
- ss
- st
- su
- sv
- sw
- ta
- te
- tg
- th
- ti
- tk
- tl
- tn
- to
- tr
- ts
- tt
- tw
- ty
- ug
- uk
- ur
- uz
- ve
- vi
- vo
- wa
- wo
- xh
- yi
- yo
- za
- zh
- zu
OperatingSystem:
type: string
enum:
- windows
- android
- macos
- linux
- ios
ErrorResponse:
type: object
properties:
message:
type: string
ScreenConfig:
type: object
properties:
width:
type: number
default: 1280
height:
type: number
default: 720
CreateSessionProfile:
type: object
properties:
id:
type: string
persistChanges:
type: boolean
persistNetworkCache:
type: boolean
description: When persisting profile changes, also persist the browser's network cache (HTTP cache).
SessionRegion:
type: string
enum:
- us-central
- us-west
- us-east
- asia-south
- europe-west
ExtractJobResponse:
type: object
properties:
jobId:
type: string
status:
$ref: '#/components/schemas/JobStatus'
data:
type: object
error:
type: string
additionalProperties: false
required:
- jobId
- status
JobStatus:
type: string
enum:
- pending
- running
- completed
- failed
- stopped
CreateSessionParams:
type: object
properties:
useUltraStealth:
type: boolean
default: false
useStealth:
type: boolean
default: false
useProxy:
type: boolean
default: false
proxyServer:
type: string
proxyServerPassword:
type: string
proxyServerUsername:
type: string
proxyCountry:
$ref: '#/components/schemas/ProxyCountry'
proxyState:
$ref: '#/components/schemas/ProxyState'
proxyCity:
type:
- string
- 'null'
example: new york
description: Desired Country. Is mutually exclusive with proxyState. Some cities might not be supported, so before using a new city, we recommend trying it out
region:
$ref: '#/components/schemas/SessionRegion'
operatingSystems:
type: array
items:
$ref: '#/components/schemas/OperatingSystem'
device:
type: array
items:
$ref: '#/components/schemas/Device'
platform:
type: array
items:
$ref: '#/components/schemas/Platform'
locales:
type: array
items:
$ref: '#/components/schemas/ISO639_1'
default:
- en
screen:
$ref: '#/components/schemas/ScreenConfig'
solveCaptchas:
type: boolean
default: false
solverType:
type: string
enum:
- visual
description: Optional CAPTCHA solver mode. Set to visual to use the visual reCAPTCHA solver.
adblock:
type: boolean
default: false
trackers:
type: boolean
default: false
annoyances:
type: boolean
default: false
enableWebRecording:
type: boolean
enableVideoWebRecording:
type: boolean
default: false
description: enableWebRecording must also be true for this to work
profile:
$ref: '#/components/schemas/CreateSessionProfile'
acceptCookies:
type: boolean
staticIpId:
type: string
format: uuid
saveDownloads:
type: boolean
default: false
extensionIds:
type: array
items:
type: string
format: uuid
default: []
urlBlocklist:
type: array
items:
type: string
default: []
browserArgs:
type: array
items:
type: string
default: []
imageCaptchaParams:
type:
- array
- 'null'
items:
type: object
properties:
imageSelector:
type: string
inputSelector:
type: string
timeoutMinutes:
type: number
minimum: 1
maximum: 720
enableWindowManager:
type: boolean
default: false
enableWindowManagerTaskbar:
type: boolean
default: false
viewOnlyLiveView:
type: boolean
default: false
disablePasswordManager:
type: boolean
default: false
enableAlwaysOpenPdfExternally:
type: boolean
default: false
disablePostQuantumKeyAgreement:
type: boolean
default: false
default:
useStealth: false
useProxy: false
acceptCookies: false
Device:
type: string
enum:
- desktop
- mobile
StartExtractJobResponse:
type: object
properties:
jobId:
type: string
required:
- jobId
JobStatusResponse:
type: object
properties:
status:
$ref: '#/components/schemas/JobStatus'
required:
- status
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: x-api-key