Collins Dictionary API
48
AI ReadinessFoundational (D+)48/100
Agent-ready OpenAPI document · curated by JenticData EnrichmentData TransformationapiKey3 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Search Collins dictionaries, fetch full entries by ID, and walk nearby alphabetical entries across English, thesaurus, and bilingual content through 3 endpoints.
Use for: Look up the definition of an English word, Find synonyms for a word in the Collins thesaurus, Translate a word from English to French using Collins, Retrieve example sentences for a word
Not supported: Does not handle full-sentence translation, grammar checking, or speech recognition - use for dictionary entry lookup, search, and nearby browsing only.
Jentic publishes the only available OpenAPI specification for Collins Dictionary API, keeping it validated and agent-ready. The Collins Dictionary API exposes Collins's English, thesaurus, and bilingual dictionary content covering definitions, translations, examples, and related entries. The API has 3 GET endpoints scoped per dictionary code: search, fetch entry by ID, and nearby alphabetical entries. Authentication is via an accesskey query parameter issued through api.collinsdictionary.com registration.
Install Jentic One Beta
Connect the Collins Dictionary API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Collins 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.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcollinsdictionary.com%2Fcollinsdictionary" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcollinsdictionary.com%2Fcollinsdictionary" | 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.
Capabilities
What an agent can do with Collins Dictionary API.
Search a Collins dictionary for entries matching a headword via GET /dictionaries/{dictionary}/search
Retrieve a complete dictionary entry with definitions, examples, and metadata via GET /dictionaries/{dictionary}/entries/{entryId}
Browse alphabetically adjacent entries via GET /dictionaries/{dictionary}/nearby
Choose between English, thesaurus, and bilingual dictionaries via the {dictionary} path parameter
Filter and paginate search results to power autocomplete or 'did you mean' suggestions
Use Cases
Patterns agents use Collins Dictionary API for, with concrete tasks.
★ Reading Comprehension Tools
Power a reader app's tap-to-define feature by calling GET /dictionaries/english/search with the tapped word and rendering the first matching entry's definitions and examples. Collins's editorial content is well-suited to learners because each entry includes pronunciations, part-of-speech labels, and contextual examples. Pair with the thesaurus dictionary for synonym suggestions.
Call GET /dictionaries/english/search?q=ephemeral and return the first entry's definitions and example sentences
Bilingual Translation Helper
Build a translation helper by selecting a bilingual dictionary code (e.g., english-french) and calling GET /dictionaries/{dictionary}/search with the source word. Collins returns the target-language headwords, sense numbers, and examples - enough context for a learner-grade translation tool without a full neural translation model. This is particularly useful for language-learning apps.
Call GET /dictionaries/english-french/search?q=house and return the French headwords with their example sentences
Crossword and Word Game Hints
Build hint and validation features for word games using GET /dictionaries/{dictionary}/nearby to walk alphabetical neighbours and GET /dictionaries/{dictionary}/search to confirm a word exists. The nearby endpoint suits 'did you mean' UX and partial-match autocomplete because it returns surrounding entries from the live dictionary.
Call GET /dictionaries/english/nearby?word=epheemral to surface near-spellings and GET /search to verify the corrected spelling exists
AI Agent Lexical Lookups via Jentic
Expose Collins lookups to an LLM agent through Jentic by searching for the operation and executing it with the returned schema. The accesskey is held in your Jentic One instance and applied at execution as a query parameter so the agent never sees the key. Useful for writing-assistant copilots and educational chatbots.
Use Jentic to search 'look up an English word definition', load the GET /dictionaries/{dictionary}/search schema, and execute it with dictionary=english and q=alacrity
Key Endpoints
3 endpoints — jentic publishes the only available openapi specification for collins dictionary api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
GET
/dictionaries/{dictionary}/search
Search dictionary entries
GET
/dictionaries/{dictionary}/entries/{entryId}
Get an entry by ID
GET
/dictionaries/{dictionary}/nearby
List alphabetically nearby entries
GET
/dictionaries/{dictionary}/search
Search dictionary entries
GET
/dictionaries/{dictionary}/entries/{entryId}
Get an entry by ID
GET
/dictionaries/{dictionary}/nearby
List alphabetically nearby entries
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
C
Collins Dictionary API
- Foundational (D+)48/100
100
Foundational Compliance61
Developer Experience & Jentic Compatibility51
AI-Readiness & Agent Experience94
Agent Usability15
Security75
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
99%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
61
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
4%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
42%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
51
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: C-Signals: 4
56%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
15
Security
Trust, risk posture, and security compliance.
Grade: FSignals: 1
15%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
75
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
75%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Collins Dictionary API by hand means passing its accesskey in the query against the api.collinsdictionary.com host and handling the search, entry, and nearby endpoints across each dictionary yourself. Through Jentic you install once, import Collins Dictionary from the API Directory, store the key once, and your agent calls it.
Permission scoping
Collins Dictionary is read-only lookup, so you scope by choosing the operations the agent may call: limit it to what it needs, such as searching for a word or fetching an entry, and other calls like nearby browsing are not included unless you add them.
Credential isolation
Your Collins access key is stored once, encrypted, by your own Jentic One instance and injected into the query string at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'look up an English word definition' or 'search the dictionary', and Jentic returns the matching Collins operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Collins Dictionary API through Jentic.
Why is there no official OpenAPI spec for Collins Dictionary API?
Collins does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Collins Dictionary API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Collins Dictionary API use?
Collins requires an accesskey query parameter on every call, obtained by registering at api.collinsdictionary.com. Through Jentic the key lives in the encrypted vault and is appended to the query at execution so the agent never sees it.
Which Collins dictionaries are available through this API?
The {dictionary} path parameter selects the dictionary code: English, English thesaurus, and several bilingual dictionaries (e.g., English-French, English-German, English-Spanish). Consult the Collins developer portal for the current list of supported codes.
Can I get example sentences with the Collins Dictionary API?
Yes. GET /dictionaries/{dictionary}/entries/{entryId} returns the full entry including definitions, part-of-speech labels, pronunciations, and example sentences. Search results from /search include entry IDs you can pass to /entries to fetch the full content.
What are the rate limits for the Collins Dictionary API?
The OpenAPI spec does not enumerate rate limits. Limits are tier-based and tied to your accesskey. HTTP error responses indicate when limits or subscription scope block a request.
How do I look up a word's definition through Jentic?
Search Jentic for 'look up an English word definition', load the GET /dictionaries/{dictionary}/search schema, and execute it with dictionary=english and q={word}. Jentic injects the accesskey from the vault and returns matching entries.
Can I limit what my agent is allowed to do with the Collins Dictionary API?
Yes. Because you run Jentic One yourself, your own rules decide which Collins operations the agent may call and which access key it uses. Since Collins is read-only lookup, you can allow just the operations it needs, such as searching a dictionary or fetching an entry by ID, while leaving nearby alphabetical browsing out until you choose to add it. The agent can only invoke the operations you have scoped for it.
GET STARTED