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/fastcrw-com:fastcrw-com-crawl-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
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: CRW REST Crawl API
version: 0.39.1
description: Firecrawl-compatible web scraping, crawling, mapping, search, and extraction API. Hosted at https://api.fastcrw.com; self-host with `docker run -p 3000:3000 ghcr.io/fastcrw/crw:latest`.
license:
name: AGPL-3.0
url: https://opensource.org/licenses/AGPL-3.0
contact:
url: https://github.com/fastcrw/crw
servers:
- url: https://api.fastcrw.com
description: Hosted (requires Bearer token)
- url: http://localhost:3000
description: Self-hosted (no auth by default)
security:
- bearerAuth: []
- {}
tags:
- name: crawl
description: Async multi-page crawl jobs
paths:
/v1/crawl:
post:
tags:
- crawl
summary: Start an async crawl job
operationId: crawlStart
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CrawlRequest'
responses:
'200':
description: Crawl job accepted; poll with /v1/crawl/{id}
content:
application/json:
schema:
$ref: '#/components/schemas/CrawlAccepted'
/v1/crawl/{id}:
get:
tags:
- crawl
summary: Get crawl job status and results
operationId: crawlStatus
parameters:
- name: id
in: path
required: true
schema:
type: string
description: Crawl job id returned by POST /v1/crawl
responses:
'200':
description: Job status + collected pages
content:
application/json:
schema:
$ref: '#/components/schemas/CrawlStatus'
'404':
$ref: '#/components/responses/NotFound'
components:
schemas:
Basis:
type: object
required:
- basisVersion
- field
- value
- status
- citations
description: Per-field extraction evidence. Emitted only for top-level scalar schema properties, and only when the request set basis:true. citations is empty exactly when status is 'unsupported' or 'notFound'; value is null exactly when status is 'notFound'.
properties:
basisVersion:
type: integer
field:
type: string
value:
description: The schema-validated value; null when status is 'notFound'. Never rewritten to the model's claim.
status:
$ref: '#/components/schemas/FieldStatus'
confidence:
type: string
enum:
- low
- medium
- high
citations:
type: array
items:
$ref: '#/components/schemas/EvidenceCitation'
CrawlStatus:
type: object
required:
- success
- status
- total
- completed
- data
properties:
success:
type: boolean
status:
type: string
enum:
- scraping
- completed
- failed
- cancelled
completed:
type: integer
total:
type: integer
data:
type: array
items:
$ref: '#/components/schemas/ScrapeResponse'
error:
type: string
Error:
type: object
required:
- success
- error
properties:
success:
type: boolean
const: false
error:
type: string
description: Human-readable error message
errorCode:
type: string
description: Machine-readable error code (see docs/error-codes.md)
ScrapeResponse:
type: object
required:
- success
- data
properties:
success:
type: boolean
warning:
type: string
description: Top-level advisory (e.g. fallback render notice)
data:
type: object
properties:
markdown:
type: string
html:
type: string
rawHtml:
type: string
links:
type: array
items:
type: string
format: uri
json:
type: object
additionalProperties: true
metadata:
$ref: '#/components/schemas/PageMetadata'
warning:
type: string
warnings:
type: array
items:
type: string
renderDecision:
type: object
description: 'How the renderer was chosen. A tagged object: `kind` is one of `userPinned`, `autoDefault`, `autoPromoted`, `breakerSkipped`, `failover`, and the remaining fields depend on it.'
properties:
kind:
type: string
creditCost:
type: number
basis:
type: array
items:
$ref: '#/components/schemas/Basis'
description: Per-field evidence for the 'json' format; present only when the request set basis:true.
basisWarnings:
type: array
items:
$ref: '#/components/schemas/BasisWarning'
llmInputHash:
type: string
description: '''sha256:''-prefixed hash of the canonical text sent to the extraction LLM. The independent record a consumer checks a citation''s sourceHash against, so the check is not circular.'
sourceHash:
type: string
description: Fingerprint of the canonical markdown, for dedup and caching.
plainText:
type: string
description: Plain-text view; present when `formats` includes `plainText`.
images:
$ref: '#/components/schemas/ScrapedImages'
summary:
type: string
description: LLM summary; present when `formats` includes `summary`.
llmUsage:
type: object
description: Token usage for the LLM call, when one ran.
chunks:
type: array
items:
type: object
description: Chunked content, when a `chunkStrategy` was requested.
contentType:
type: string
description: MIME type of the fetched resource.
changeTracking:
type: object
description: Diff result; present when `formats` includes `changeTracking`.
screenshot:
type: string
description: PNG capture as a `data:image/png;base64,...` URL; present when `formats` includes `screenshot`.
block:
type: object
description: Anti-bot verdict. Present only when the page was a block or challenge shell, in which case `success` is false.
debugExtraction:
type: object
description: 'Extraction trace; present only when `debug: true`.'
CrawlOutputFormat:
type: string
enum:
- markdown
- html
- rawHtml
- plainText
- links
- images
- json
description: The crawl path runs extraction and the optional LLM `json` pass. It does not produce `summary`, `screenshot` or inline `changeTracking`; use `/v1/scrape` for those.
CrawlAccepted:
type: object
required:
- success
- id
properties:
success:
type: boolean
id:
type: string
url:
type: string
format: uri
description: URL to poll with GET /v1/crawl/{id}
CrawlScrapeOptions:
type: object
description: Per-page scrape settings. Every key here may also be sent at the top level; an explicit top-level value wins.
properties:
formats:
type: array
items:
$ref: '#/components/schemas/CrawlOutputFormat'
default:
- markdown
onlyMainContent:
type: boolean
default: true
jsonSchema:
type: object
description: 'JSON Schema for structured extraction, with `formats: ["json"]`.'
renderJs:
type:
- boolean
- 'null'
description: null = auto-detect, true = force JS, false = never use a browser tier.
waitFor:
type: integer
minimum: 0
description: Milliseconds to wait after JS rendering on each page.
headers:
type: object
additionalProperties:
type: string
description: Custom HTTP request headers applied to every page the crawl fetches. On a browser render they apply to every request the page makes, subresources included, so avoid cross-origin-sensitive credentials here.
ScrapedImages:
type: array
description: Present when `formats` includes `images`.
items:
type: object
properties:
url:
type: string
format: uri
alt:
type: string
required:
- url
FieldStatus:
type: string
enum:
- supported
- unverified
- unsupported
- notFound
description: 'How well an extracted field is attributed to its source. Honest: a field whose attribution could not be verified is ''unverified''/''unsupported'' rather than given a fabricated citation.'
EvidenceCitation:
type: object
required:
- url
- sourceHash
- sourceTextKind
description: A citation backing an extracted value. Every field is server-produced; never a model-supplied url, hash or excerpt.
properties:
url:
type: string
description: The document the engine fetched.
title:
type: string
excerpt:
type: string
description: Verbatim span from the canonical source text. Absent when the span could not be established (status 'unverified').
sourceHash:
type: string
description: '''sha256:<hex>'' of the exact text sent to the model.'
sourceTextKind:
type: string
description: Which text sourceHash covers. 'llmInput' for extraction basis (the truncated markdown sent to the model).
PageMetadata:
type: object
additionalProperties: true
properties:
title:
type: string
description:
type: string
sourceURL:
type: string
format: uri
statusCode:
type: integer
CrawlRequest:
type: object
required:
- url
properties:
url:
type: string
format: uri
maxPages:
type: integer
minimum: 1
default: 100
maxDepth:
type: integer
minimum: 0
default: 2
headers:
type: object
additionalProperties:
type: string
description: Custom HTTP request headers applied to every page the crawl fetches. On a browser render they apply to every request the page makes, subresources included, so avoid cross-origin-sensitive credentials here.
scrapeOptions:
$ref: '#/components/schemas/CrawlScrapeOptions'
formats:
type: array
items:
$ref: '#/components/schemas/CrawlOutputFormat'
default:
- markdown
onlyMainContent:
type: boolean
default: true
jsonSchema:
type: object
renderJs:
type:
- boolean
- 'null'
waitFor:
type: integer
minimum: 0
renderer:
type: string
enum:
- auto
- lightpanda
- chrome
- chrome_proxy
- playwright
- camoufox
- impersonated-http
country:
type: string
description: 2-letter ISO 3166-1 alpha-2 proxy egress country.
proxyList:
type: array
items:
type: string
proxyRotation:
type: string
enum:
- round_robin
- random
- sticky_per_host
BasisWarning:
type: object
required:
- field
- code
description: A coded reason a field's attribution was downgraded. Closed, crw-owned code set; never upstream text.
properties:
field:
type: string
code:
type: string
responses:
NotFound:
description: Resource not found
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: API key
description: Hosted only. Get a key at https://fastcrw.com/register.