ConceptNet Similarity API
Semantic similarity and relatedness using Numberbatch embeddings
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/conceptnet-similarity-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: ConceptNet REST Similarity API
description: ConceptNet is a freely available multilingual knowledge graph providing computers access to common-sense knowledge.
version: '5.7'
license:
name: CC BY-SA 4.0
url: https://creativecommons.org/licenses/by-sa/4.0/
contact:
name: ConceptNet Users Group
url: https://groups.google.com/g/conceptnet-users
x-website: https://conceptnet.io
x-github: https://github.com/commonsense/conceptnet5
servers:
- url: https://api.conceptnet.io
description: ConceptNet public API
tags:
- name: Similarity
description: Semantic similarity and relatedness using Numberbatch embeddings
paths:
/related/{uri}:
get:
operationId: getRelatedConcepts
summary: Find semantically related concepts
description: Returns a ranked list of concepts most semantically related to the given URI, using ConceptNet Numberbatch word vector similarity. Results are sorted by descending relatedness weight. This endpoint and /relatedness each count as 2 requests against the rate limit quota (3,600 req/hour, 120 req/min). The optional filter parameter restricts results to a particular language subtree.
tags:
- Similarity
parameters:
- name: uri
in: path
description: ConceptNet URI path (e.g. c/en/dog — the leading slash is part of the base path, so omit it here)
required: true
schema:
type: string
example: c/en/dog
- name: limit
in: query
description: Maximum number of related concepts to return (0-100)
required: false
schema:
type: integer
minimum: 0
maximum: 100
default: 50
- name: filter
in: query
description: Restrict results to URIs under this prefix (e.g. /c/en to limit to English concepts)
required: false
schema:
type: string
example: /c/en
responses:
'200':
description: Ranked list of related concepts with weights
content:
application/json:
schema:
$ref: '#/components/schemas/RelatedList'
example:
'@id': /related/c/en/dog
related:
- '@id': /c/en/puppy
weight: 0.713
- '@id': /c/en/canine
weight: 0.698
- '@id': /c/en/pet
weight: 0.621
'404':
description: URI not found in embedding space
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
/relatedness:
get:
operationId: getRelatedness
summary: Compute pairwise relatedness score
description: Returns a single floating-point relatedness score between 0 and 1 for any two ConceptNet concept URIs, computed from Numberbatch word vector cosine similarity. A score of 1.0 indicates maximum similarity and 0.0 indicates no detectable relationship. This endpoint and /related each count as 2 requests against the rate limit quota.
tags:
- Similarity
parameters:
- name: node1
in: query
description: First ConceptNet concept URI
required: true
schema:
type: string
example: /c/en/dog
- name: node2
in: query
description: Second ConceptNet concept URI
required: true
schema:
type: string
example: /c/en/cat
responses:
'200':
description: Relatedness result
content:
application/json:
schema:
$ref: '#/components/schemas/RelatednessResult'
example:
'@id': /relatedness?node1=/c/en/dog&node2=/c/en/cat
value: 0.849
node1:
'@id': /c/en/dog
node2:
'@id': /c/en/cat
'400':
description: Missing or invalid node parameters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
components:
schemas:
RelatedList:
type: object
description: Ranked list of semantically related concepts
properties:
'@id':
type: string
description: URI of this related-terms result
example: /related/c/en/dog
related:
type: array
items:
$ref: '#/components/schemas/WeightedConcept'
RelatednessResult:
type: object
description: Pairwise semantic relatedness result
properties:
'@id':
type: string
description: URI of this relatedness result
value:
type: number
format: float
description: Relatedness score between 0.0 and 1.0
example: 0.849
node1:
$ref: '#/components/schemas/ConceptRef'
node2:
$ref: '#/components/schemas/ConceptRef'
WeightedConcept:
type: object
description: A concept with a numeric relatedness weight
properties:
'@id':
type: string
description: ConceptNet URI of the related concept
example: /c/en/puppy
weight:
type: number
format: float
description: Relatedness score (0.0-1.0)
example: 0.713
ConceptRef:
type: object
description: Reference to a ConceptNet concept node
properties:
'@id':
type: string
description: ConceptNet URI
example: /c/en/dog
label:
type: string
description: Human-readable label
example: dog
language:
type: string
description: BCP-47 language code
example: en
term:
type: string
description: Concept URI (same as @id)
example: /c/en/dog
sense_label:
type: string
description: Part-of-speech or sense label if applicable
example: n
Error:
type: object
description: API error response
properties:
error:
type: string
description: Error type identifier
details:
type: string
description: Human-readable error description