Pechincha.ai Partner API
59
AI ReadinessFoundational (C+)59/100
Official vendor OpenAPI document · agent-readyE CommerceStorefrontapiKey6 EndpointsREST
For Agents
Search active Brazilian e-commerce promotions by text, store, category, or price range, compare a product's offers across stores, and read its BRL price history before recommending a deal.
Use for: Find current deals on air fryers under R$400, I want to know if this phone's price is actually lower than usual, Compare the offers for this product across Amazon and Mercado Livre, List all active promotions from one store sorted by price
Not supported: Does not place orders, process payments, or manage seller listings on the stores it tracks. Use for reading Brazilian promotions, product details, and price history only.
The Pechincha.ai Partner API returns active promotions and price-tracked products from Brazilian stores such as Amazon, Mercado Livre, AliExpress, and Shopee, with prices in BRL and content in Brazilian Portuguese. You can page through live promotions filtered by text, store, category, tag, or price range and sorted by price, recency, or engagement, then open a product to see its specifications, pros and cons, FAQs, and lowest current price. Per product it also lists the same item's offers across stores for price comparison, its price history over periods from a week to all time, and related products.
Install Jentic One Beta
Connect the Pechincha.ai Partner API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pechincha.ai Partner 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%2Fpechincha.ai%2Fpechincha" | 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%2Fpechincha.ai%2Fpechincha" | 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 Pechincha.ai Partner API.
Search active promotions by title text, store_id, category_ids, tag_id, or a price_min and price_max range in BRL
Sort promotions by price, created_at, views, or engagement counts such as total_clicks, and hide expired offers
Read a product's technical_specs, pros, cons, FAQ, and lowest_price with the store offering it
Compare the same product's offers across Brazilian stores, including coupon_code and is_expired on each offer
Pull a product's price history over 7d, 30d, 90d, 1y, or all to judge whether a deal is real
Look up a product by its slug instead of its UUID and list related products
Use Cases
Patterns agents use Pechincha.ai Partner API for, with concrete tasks.
★ Shopping assistant agent through Jentic
A shopping agent for Brazilian users finds the Pechincha.ai promotions operation through Jentic, searches by product text and a price ceiling in BRL, and then checks the top result's price history before recommending it. Jentic injects the x-api-key header at call time, so the partner key never appears in the agent's context.
Call GET /promotions with search 'air fryer', price_max 400, and sort 'price', then call GET /product/{productId}/price-history with period '90d' for the cheapest result
Cross-store price comparison
For a given product, GET /product/{productId}/promotions returns its offers across stores with price, old_price, coupon_code, store, and is_expired, while GET /product/{productId} reports lowest_price and lowest_price_store. Together they answer where an item is cheapest today among Amazon, Mercado Livre, AliExpress, Shopee, and other Brazilian stores.
Call GET /product/{productId} to read lowest_price and lowest_price_store, then GET /product/{productId}/promotions and list non-expired offers with their coupon_code
Deal validation with price history
Discounts are only meaningful against past prices. GET /product/{productId}/price-history accepts a period of 7d, 30d, 90d, 1y, or all, so an agent or deal site can show whether today's price is a real low or a marked-up discount.
Call GET /product/{productId}/price-history with period '1y' and compare the current promotion price against the lowest recorded price
Deal feeds for content and newsletters
Publishers building deal roundups page through GET /promotions with filters such as category_id or tag_id, sorted by total_clicks or created_at, at 25 promotions per page. Each promotion carries title, price, old_price, discount, url, images, and store, enough to render a deal card without further calls.
Call GET /promotions with category_id for electronics, sort 'total_clicks', and hide_expired true, then format the first page as a deal roundup
Key Endpoints
6 endpoints — the pechincha.
METHOD
PATH
DESCRIPTION
GET
/promotions
List active promotions
GET
/product/{productId}
Product details
GET
/product/{productId}/promotions
Offers for the same product across stores
GET
/product/{productId}/price-history
Product price history
GET
/product/slug/{productSlug}
Product details by slug
GET
/product/{productId}/related
Related products
GET
/promotions
List active promotions
GET
/product/{productId}
Product details
GET
/product/{productId}/promotions
Offers for the same product across stores
GET
/product/{productId}/price-history
Product price history
GET
/product/slug/{productSlug}
Product details by slug
GET
/product/{productId}/related
Related products
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.
P
Pechincha.ai Partner API
- Foundational (C+)59/100
100
Foundational Compliance63
Developer Experience & Jentic Compatibility40
AI-Readiness & Agent Experience94
Agent Usability50
Security50
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
98%
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.
63
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.
50%
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.
40
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D-Signals: 4
16%
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.
46%
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.
50
Security
Trust, risk posture, and security compliance.
Grade: C-Signals: 1
50%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
50
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: C-Signals: 1
50%
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 Pechincha.ai Partner API by hand means adding the x-api-key partner header, paging through promotions, and pacing calls to stay under its rate limit yourself. Through Jentic you install once, import Pechincha.ai from the API Directory, store the partner key once, and your agent calls it.
Permission scoping
Pechincha.ai puts the product id in the URL path (/product/{productId}/...), so a rule can pin your agent to one product's details, offers, and price history. You choose the operations it may call, so an agent meant to watch one item does not get the open promotions search unless you add it.
Credential isolation
Your Pechincha.ai partner key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find deals in Brazilian stores' or 'get a product price history', and Jentic returns the matching Pechincha.ai 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 Pechincha.ai Partner API through Jentic.
What authentication does the Pechincha.ai Partner API use?
Per its OpenAPI spec, the Pechincha.ai Partner API takes a partner key in the `x-api-key` header. Keys are requested from the Pechincha.ai commercial team. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context.
Which stores does the Pechincha.ai API cover?
The spec describes promotions and price-tracked products from Brazilian stores including Amazon, Mercado Livre, AliExpress, and Shopee, among others. Prices are in BRL and content is in Brazilian Portuguese. Filter by a specific store with the store_id parameter on GET /promotions.
How do I find a deal and check its price history through Jentic?
Search Jentic for 'find deals in Brazilian stores', call GET /promotions with your search text and optional price_max, take the product id from a result, and call GET /product/{productId}/price-history with a period such as 90d. To run it on your own infrastructure, install Jentic One from its GitHub repo.
What are the rate limits for the Pechincha.ai Partner API?
The OpenAPI spec states a limit of 60 requests per minute, with a 429 response above that. See https://pechincha.ai/desenvolvedores for current details.
Is there a Pechincha.ai MCP server?
You don't need an MCP server to give your agent the Pechincha.ai Partner API. Jentic connects it directly from the API Directory: import it, store your partner key once, and your agent calls it. Operations are discovered on demand, so no extra tool definitions sit in the agent's context.
Can I limit what my agent is allowed to do with the Pechincha.ai Partner API?
Yes. Every operation is a read, so the question is which data the agent may pull. For example, allow only GET /promotions and GET /product/{productId}/price-history, so a deal-checking agent can search offers and validate prices but not browse product detail or related items. Every call it makes is logged by your Jentic One instance.
GET STARTED