Ebay Recommendation API
Browse all Ebay APIs0
AI ReadinessNon-Ready (F)0/100
Official vendor OpenAPI document · agent-readyE CommerceStorefrontoauth21 EndpointsREST
For Agents
Get eBay seller recommendations for which listings to promote and the suggested ad-rate strategy via a single find endpoint.
Use for: Get Promoted Listings recommendations for my top 100 active listings, Find which of my listings eBay recommends I promote with paid ads, Retrieve the suggested ad-rate strategy for a specific listingId, Check whether eBay recommends a listing for Promoted Listings
Not supported: Does not handle campaign creation, bidding execution, or analytics reporting - use for eBay Promoted Listings recommendations and suggested ad-rate strategies only.
The eBay Recommendation API gives sellers programmatic recommendations to improve their listings, starting with Promoted Listings ad recommendations. Its single endpoint, POST /find, returns recommended actions for one or more listingIds, telling the seller which listings would benefit from being promoted and the suggested ad-rate strategies. Sellers integrate it with Promoted Listings flows so they only spend ad budget on listings eBay's models predict will respond.
Install Jentic One Beta
Connect the Recommendation API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Recommendation 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%2Febay.com%2Fsell-recommendation" | 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%2Febay.com%2Fsell-recommendation" | 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 Recommendation API.
Retrieve eBay's Promoted Listings recommendations for a batch of listingIds
Identify listings predicted to benefit most from being promoted with paid ads
Get suggested ad-rate strategies for each recommended listing
Filter recommendations by listing characteristics passed in the request body
Pre-qualify Promoted Listings campaigns before bidding by surfacing eBay's data-driven picks
Use Cases
Patterns agents use Recommendation API for, with concrete tasks.
★ Smart Promoted Listings Campaign Building
Rather than promoting every active listing, sellers can call POST /find with their listingIds and receive eBay's recommendation on which would benefit from being promoted. The response includes suggested ad-rate strategies so the seller can start a campaign with eBay-informed bids. This typically improves ROAS because budget concentrates on listings with predicted lift.
POST /find with the seller's top 100 active listingIds and read the recommendation response to choose which to promote.
Periodic Ad-Rate Strategy Refresh
Marketplace dynamics shift, so the recommended ad-rate for a listing changes over time. Sellers schedule a recurring job that calls POST /find on their full active inventory to refresh the suggested ad-rates and update the corresponding Promoted Listings ads via the Marketing API. The combined flow keeps bids aligned with eBay's current recommendations.
Run POST /find weekly across active listings, compare the recommended ad-rates with current bids, and update bids via the Marketing API where the recommendation has changed.
Decision Support for Manual Sellers
Smaller sellers who manage campaigns by hand can use a one-shot recommendation pull to decide where to put their first ad budget. The Recommendation API exposes which listings eBay's models predict will respond to paid promotion and the recommended starting bid, so a seller without paid-search experience has a sensible baseline.
Call POST /find with all of the seller's active listingIds and present the top 10 recommendations to the seller as a starting Promoted Listings shortlist.
AI Agent Promoted Listings Curator
An AI agent integrated with a seller's commerce platform can use Jentic to discover the Recommendation API, pull recommendations, and orchestrate Promoted Listings creation through the Marketing API in a single workflow. The agent uses recommendations as the input to a campaign-launch step and can re-evaluate weekly without seller intervention.
Through Jentic, search 'get ebay promoted listings recommendations', load the POST /find schema, and execute it to build a Promoted Listings campaign from the recommended listings.
Key Endpoints
1 endpoints — the ebay recommendation api gives sellers programmatic recommendations to improve their listings, starting with promoted listings ad recommendations.
METHOD
PATH
DESCRIPTION
POST
/find
Get Promoted Listings recommendations for a batch of listingIds
POST
/find
Get Promoted Listings recommendations for a batch of listingIds
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.
R
Recommendation API
- Non-Ready (F)0/100
74
Foundational Compliance69
Developer Experience & Jentic Compatibility45
AI-Readiness & Agent Experience94
Agent Usability90
Security0
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
74
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A-Signals: 4
96%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
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.
69
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B+Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
75%
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.
45
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
80%
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.
0%
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.
90
Security
Trust, risk posture, and security compliance.
Grade: A+Signals: 1
90%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
0
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: FSignals: 1
0%
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 eBay Recommendation API by hand means implementing eBay's OAuth 2.0 authorization-code flow for a seller user token, refreshing it, and pointing requests at the api.ebay.com sell/recommendation host. Through Jentic you install once, import the Recommendation API from the API Directory, store the eBay OAuth credentials once, and your agent calls it.
Permission scoping
This API exposes a single endpoint, POST /find, with no resource id in the URL path, so scope it by operation: you limit the agent to requesting Promoted Listings recommendations for the listing ids and filters you pass. It returns suggested ad-rate strategies and does not create or run campaigns.
Credential isolation
Your eBay OAuth seller credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get eBay Promoted Listings recommendations', and Jentic returns the POST /find operation with its input schema for listing ids and filters 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 Recommendation API through Jentic.
What authentication does the eBay Recommendation API use?
The eBay Recommendation API uses OAuth 2.0 (the api_auth scheme) with seller-scoped tokens. Through Jentic, the OAuth client credentials are stored encrypted in your Jentic One instance and the agent receives only short-lived scoped access tokens at call time.
Can I get Promoted Listings recommendations for my eBay inventory?
Yes. POST /find accepts an array of listingIds and returns eBay's recommendation on which to promote, along with the suggested ad-rate strategy for each recommended listing.
What are the rate limits for the eBay Recommendation API?
The Recommendation API shares the eBay Sell API call quota tied to the seller's Application Growth Check tier rather than per-endpoint limits in the spec. Batching listingIds in a single POST /find keeps call volume low at scale.
How do I get Promoted Listings recommendations through Jentic?
Search 'get ebay promoted listings recommendations' in Jentic, load the POST /find schema, pass an array of listingIds, and Jentic executes the call. The response identifies which listings to promote and at what ad-rate.
Does the eBay Recommendation API give recommendations for non-Promoted-Listings actions?
No. Today the spec exposes only Promoted Listings recommendations through the find endpoint. Other recommendation types are not part of this API surface.
Can I limit what my agent is allowed to do with the eBay Recommendation API?
Yes. Because you run Jentic One self-hosted, your own rules decide which operations and credentials the agent may use. This API exposes a single endpoint, POST /find, so you scope the agent to requesting Promoted Listings recommendations for only the listing ids and filters you allow it to pass. That operation returns suggested ad-rate strategies and cannot create or run campaigns, so the agent stays read-only against your eBay seller account.
GET STARTED