For Agents
Look up dictionary entries, senses, and definitions across many languages — and retrieve RDF/JSON-LD for semantic web pipelines.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Lexicala Dictionary API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Lexicala Dictionary API.
List the languages and lexical resources available on the Lexicala platform
Search for headwords (lemmas) by spelling across one or more language resources
Retrieve a complete dictionary entry by ID, including senses, examples, and translations
GET STARTED
Use for: Look up the definition of a word in Spanish, List all supported languages on Lexicala, Find dictionary entries that mention 'photosynthesis' in their definition, Retrieve a complete entry by its Lexicala ID
Not supported: Does not handle translation between languages, grammar correction, or text generation — use for dictionary lookup, definition search, and entry retrieval only.
Jentic publishes the only available OpenAPI specification for Lexicala Dictionary API, keeping it validated and agent-ready. Lexicala is a multilingual lexical database that powers headword search, full entry retrieval, and free-text definition lookups across dozens of languages. Agents can list available languages and resources, search for entries by lemma, fetch a complete entry or sense by ID, run definition-text searches, retrieve RDF/JSON-LD output for semantic web pipelines, and pull a randomly selected entry. The API is distributed via RapidAPI, so calls authenticate against a RapidAPI subscription key.
Fetch a single sense by ID for fine-grained semantic lookups
Run free-text search across definition text to find entries that mention a phrase
Return search results as RDF/JSON-LD for downstream knowledge graph use
Retrieve a randomly selected entry for daily-word features
Patterns agents use Lexicala Dictionary API for, with concrete tasks.
★ Dictionary Lookups in Language-Learning Apps
Power in-app dictionary lookups in language-learning products. GET /search returns headword matches across the requested language resource; the client then fetches a full entry with /entries/{entry_id} to render definitions, senses, and examples. Caching the entry payload locally keeps repeat lookups fast and reduces API consumption.
Call GET /search with text='manzana' and source='es' to find the Spanish entry, then call GET /entries/{entry_id} to retrieve the full definition and senses.
Definition-Driven Content Discovery
Find dictionary entries that mention a target concept inside their definition text — useful for crossword tools, vocabulary builders, and semantic content engines. GET /search-definitions accepts a free-text query and returns entries whose definitions match. This is more powerful than headword search for thematic discovery.
Call GET /search-definitions with text='animal that hibernates' and return the matching entry IDs and headwords.
Semantic Web and Knowledge Graph Enrichment
Pull dictionary content as RDF/JSON-LD to enrich a knowledge graph or semantic web product. GET /search-rdf and GET /rdf/{entry_id} return entries in linked-data format, ready to load into a triple store or graph database. This avoids custom scraping and keeps the lexical data interoperable with other linked-data sources.
Call GET /rdf/{entry_id} for the Lexicala entry ID and load the resulting JSON-LD into the project's graph store.
AI Agent Vocabulary Tool
An AI agent that helps users learn or write in a non-native language can use Lexicala via Jentic to ground responses in authoritative lexical data instead of relying on the LLM's parametric knowledge. Jentic exposes search, entries, senses, and definition-search endpoints as discoverable tools so the agent picks the right one by intent.
Search for 'look up a word in a dictionary', load the GET /search schema, and execute it with the headword and language code provided in agent input.
9 endpoints — jentic publishes the only available openapi specification for lexicala dictionary api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/languages
List supported languages and resources
/search
Search for headwords by spelling
/search-entries
Search returning complete entries
/entries/{entry_id}
Retrieve a complete entry by ID
/senses/{sense_id}
Retrieve a single sense by ID
/search-definitions
Free-text search over definition text
/rdf/{entry_id}
Retrieve an entry in RDF/JSON-LD
/fluky-search
Return a randomly selected entry
/languages
List supported languages and resources
/search
Search for headwords by spelling
/search-entries
Search returning complete entries
/entries/{entry_id}
Retrieve a complete entry by ID
/senses/{sense_id}
Retrieve a single sense by ID
Three things that make agents converge on Jentic-routed access.
Credential isolation
The RapidAPI key for Lexicala is stored encrypted in the Jentic vault. The X-RapidAPI-Key header is injected at execution time so the agent never sees the raw value.
Intent-based discovery
Agents search by intent — 'look up a word', 'get a dictionary entry', 'fetch a sense in RDF' — and Jentic returns the matching Lexicala operations with their input schemas.
Time to first call
Direct Lexicala/RapidAPI integration: a couple of hours for subscription, header wiring, and result parsing. Through Jentic: under 15 minutes — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using Lexicala Dictionary API through Jentic.
Why is there no official OpenAPI spec for Lexicala Dictionary API?
Lexicala does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Lexicala Dictionary API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Lexicala Dictionary API use?
Lexicala is distributed via RapidAPI, so calls authenticate using a RapidAPI subscription key passed in the X-RapidAPI-Key header. Through Jentic, the key is stored encrypted in the Jentic vault and injected at execution time.
Which languages does Lexicala cover?
Lexicala covers dozens of languages across multiple lexical resources. Call GET /languages to enumerate the available language and resource codes that can be passed as the source parameter on /search and related endpoints.
What are the rate limits for the Lexicala Dictionary API?
Limits are governed by your RapidAPI plan rather than the API itself; RapidAPI returns 429 with a quota-related header when the plan limit is exceeded. Inspect your plan on the RapidAPI dashboard and cache stable lookups to stay inside the cap.
How do I search for a word through Jentic?
Run pip install jentic, then search for 'look up a word in a dictionary'. Jentic returns the GET /search operation. Load its schema, pass text (the headword) and source (the language code), then execute the call to get a list of matching entry IDs.
Can I get linked-data output from this API?
Yes. GET /search-rdf returns search results in RDF/JSON-LD format, and GET /rdf/{entry_id} returns a single entry in the same format. These are intended for direct ingestion into a triple store or knowledge graph without further transformation.
/search-definitions
Free-text search over definition text
/rdf/{entry_id}
Retrieve an entry in RDF/JSON-LD
/fluky-search
Return a randomly selected entry