SchemaExtract Extract API
The Extract API from SchemaExtract — 1 operation(s) for extract.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
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.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/schemaextract-extract-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
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 Specification
openapi: 3.2.0
info:
title: SchemaExtract Extract API
version: 0.2.0
description: Schema-driven document to JSON extraction. Upload a PDF or image plus a JSON schema (or preset) and receive structured data. Files are processed in memory and discarded after the response.
servers:
- url: /
description: This deployment
security:
- bearerAuth: []
- {}
tags:
- name: Extract
paths:
/v1/extract:
post:
operationId: extractDocument
summary: Extract structured JSON from a document
description: 'Accepts multipart form-data (`file` + `schema`) or a JSON body (`file_base64` + `schema`). Optionally pass `preset` as invoice | packing_list | bank_statement | bol. When AUTH_SECRET is set and DEMO_MODE is not true, send Authorization: Bearer sk_live_…'
parameters:
- name: preset
in: query
required: false
schema:
type: string
enum:
- invoice
- packing_list
- bank_statement
- bol
description: Use a built-in schema when `schema` is omitted.
- name: include_raw_text
in: query
required: false
schema:
type: boolean
description: Include extracted PDF text in meta.raw_text.
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
properties:
file:
type: string
format: binary
schema:
type: string
description: JSON schema or example object, as a string.
preset:
type: string
enum:
- invoice
- packing_list
- bank_statement
- bol
include_raw_text:
type: boolean
required:
- file
application/json:
schema:
type: object
properties:
schema:
type: object
file_base64:
type: string
filename:
type: string
mime:
type: string
preset:
type: string
enum:
- invoice
- packing_list
- bank_statement
- bol
include_raw_text:
type: boolean
required:
- file_base64
responses:
'200':
description: Extraction succeeded
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractSuccess'
'400':
description: Invalid schema, preset, or request
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
'401':
description: Missing or invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
'402':
description: Monthly quota exceeded (upgrade)
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
'413':
description: File too large
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
'415':
description: Unsupported file type
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
'429':
description: Burst rate limited
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
'502':
description: Upstream model failure
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractError'
tags:
- Extract
components:
schemas:
ExtractError:
type: object
required:
- ok
- error
properties:
ok:
type: boolean
enum:
- false
error:
type: object
required:
- code
- message
properties:
code:
type: string
enum:
- BAD_REQUEST
- INVALID_JSON
- INVALID_SCHEMA
- SCHEMA_TOO_LARGE
- INVALID_PRESET
- MISSING_FILE
- UNSUPPORTED_FILE
- FILE_TOO_LARGE
- MODEL_FAILURE
- RATE_LIMITED
- UNAUTHORIZED
- PAYMENT_REQUIRED
- QUOTA_EXCEEDED
message:
type: string
ExtractSuccess:
type: object
required:
- ok
- data
- meta
properties:
ok:
type: boolean
enum:
- true
data:
type: object
additionalProperties: true
meta:
type: object
properties:
model:
type: string
pages:
type: integer
preset:
type: string
nullable: true
filename:
type: string
mode:
type: string
enum:
- mock
- openai
- anthropic
- ollama
warnings:
type: array
items:
type: string
vision_pages:
type: integer
raw_text:
type: string
plan:
type: string
quota_remaining:
type: integer
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: sk_live_