Datamuse Suggestions API

Autocomplete suggestions with spelling correction and semantic fallback.

Operations 1

GET /sug Get Autocomplete Suggestions #

Documentation

Specifications

Schemas & Data

Other Resources

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.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/datamuse-suggestions-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

datamuse-suggestions-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Datamuse Suggestions API
  description: 'The Datamuse API is a word-finding query engine for developers. It returns lists of

    words (and optional metadata) matching a combination of semantic, phonetic, orthographic,

    and vocabulary constraints, plus context ranking hints. The API powers OneLook,

    OneLook Thesaurus, RhymeZone, Rimar.io, and CivicSearch.


    Two operations are exposed:


    * `GET /words` — find words matching a rich set of constraint and ranking parameters.

    * `GET /sug` — return autocomplete suggestions for a partially-entered string.


    The service is free for non-commercial use up to 100,000 requests per day with no

    API key required. Commercial use, higher rate limits, and custom vocabularies are

    available via a paid commercial agreement.

    '
  version: 1.1.0
  termsOfService: https://www.datamuse.com/api/
  contact:
    name: Datamuse API Support
    url: https://www.datamuse.com/api/
  license:
    name: Datamuse Free Non-Commercial Use
    url: https://www.datamuse.com/api/
servers:
- url: https://api.datamuse.com
  description: Datamuse production API
tags:
- name: Suggestions
  description: Autocomplete suggestions with spelling correction and semantic fallback.
paths:
  /sug:
    get:
      summary: Get Autocomplete Suggestions
      description: 'Return intelligent autocomplete suggestions for a partially-entered search string.

        Sorted by popularity; the response may include spelling corrections or semantically

        similar terms when an exact prefix match is unavailable.

        '
      operationId: getSuggestions
      tags:
      - Suggestions
      parameters:
      - $ref: '#/components/parameters/SuggestionPrefix'
      - $ref: '#/components/parameters/SuggestionMax'
      - $ref: '#/components/parameters/Vocabulary'
      responses:
        '200':
          description: A ranked list of suggested words.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Suggestion'
        '400':
          description: Malformed request.
        '429':
          description: Too many requests — exceeded the 100,000 requests/day free tier limit.
components:
  parameters:
    SuggestionMax:
      name: max
      in: query
      description: Maximum number of suggestions to return.
      schema:
        type: integer
        minimum: 1
        maximum: 1000
        default: 10
    SuggestionPrefix:
      name: s
      in: query
      description: Partially-entered search string for which to return suggestions.
      required: true
      schema:
        type: string
      example: rawn
    Vocabulary:
      name: v
      in: query
      description: Vocabulary identifier. Default English (`en`, 550k terms) or `es` for Spanish (500k terms). Custom vocabularies available on request.
      schema:
        type: string
        enum:
        - en
        - es
        default: en
  schemas:
    Suggestion:
      type: object
      description: A suggestion returned from the /sug endpoint.
      required:
      - word
      properties:
        word:
          type: string
          description: The suggested completion (may include a spelling correction or semantic fallback).
          example: prawn
        score:
          type: integer
          description: Popularity score; higher means more likely.
          example: 1500