2 APIs across 1 product group. All share one credential.
| I want to... | Use | Why |
|---|---|---|
| Add new media, apply transformations, or tag and rename assets | Cloudinary Upload API | The Upload API creates and mutates assets: it uploads images, videos, and raw files, applies eager transformations, and handles tagging, renaming, and deletion. |
| List existing resources, organize folders, or monitor account usage | Cloudinary Admin API | The Admin API handles account-level administration: listing and inspecting resources by type, managing folder hierarchies, and reading storage, bandwidth, and transformation-credit usage. |
| Delete a media asset | Cloudinary Upload API | Both APIs can remove assets, but the Upload API destroy operation permanently deletes an asset and its CDN derivatives, while the Admin API delete works on listed resources by type and public ID. |
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cloudinary APIs, 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://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcloudinary.com" | shStep 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%2Fcloudinary.com" | 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.
Once connected, ask your agent something like: .
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Cloudinary by hand means configuring Basic auth with your API key and secret, computing upload signatures, and resolving the per-account api.cloudinary.com host for both the Upload and Admin APIs. Through Jentic you install once, add the Cloudinary APIs from the Jentic directory, store the key and secret once, and your agent calls either API.
Permission scoping
Both APIs work within one cloud fixed by the cloud name and address assets by parameters rather than one id pinned in the path, so you scope the agent to the operations it needs, such as uploading, tagging, listing resources, or reading usage. Destructive operations like destroy or resource delete are only in reach if your rules include them.
Credential isolation
Specific to using Cloudinary APIs through Jentic.
What is the difference between the Cloudinary Upload API and Admin API?
The Upload API creates and mutates assets: it uploads images, videos, and raw files, applies transformations, and handles tagging, renaming, and deletion. The Admin API handles account-level administration: listing and inspecting resources, managing folder hierarchies, and monitoring usage. Use the Upload API to add and change content, and the Admin API to organize and audit what already exists.
Do the two Cloudinary APIs share one set of credentials?
Yes. Both APIs use HTTP Basic authentication with the same Cloudinary API Key and API Secret, scoped to a single cloud name. One credential pair covers uploading, transformation, resource administration, folder management, and usage monitoring, so an agent set up for one API can call the other without a separate login.
Can an agent both upload media and organize it into folders?
Yes. An agent can create and search folders with the Admin API and upload assets that target those folders through the Upload API. A typical flow creates a folder structure first, uploads and tags the media into it, then lists the folder to confirm placement, keeping ingest and organization aligned in one workflow.
Why does Jentic maintain these Cloudinary specs?
BOOK A DEMO
Browse thousands of APIs and connect them all to your agent with Jentic One. One layer, one credential — every API your agent needs.
For Agents
Across Cloudinary's APIs an agent can upload images, videos, and raw files, apply transformations and tags, rename or delete assets, organize them into folders, and inspect resource metadata and account usage. It covers the full media lifecycle from ingest and transformation through library administration and quota monitoring.
Cloudinary pairs media ingest and transformation with library administration under one account and one cloud name, so upload, organization, and usage monitoring share the same asset namespace. Assets uploaded and transformed through the Upload API are the same resources the Admin API lists, organizes, and tracks against quota.
Use for: Uploading, transforming, tagging, and organizing images, videos, and raw files in Cloudinary, and administering the resulting resources, folders, and account usage quotas.
Not supported: image content analysis, facial recognition, video transcoding pipelines, raw object storage, real-time streaming
Credentials: Both APIs use HTTP Basic authentication with the same Cloudinary API Key and API Secret scoped to one cloud name, so a single credential pair covers the entire portfolio.
All 2 Cloudinary OpenAPI specs are Jentic-generated and indexed by Jentic, kept validated and agent-ready.
Cloudinary is a cloud media platform for storing, transforming, and delivering images, videos, and raw files. Its APIs cover two halves of media management: uploading and transforming assets on ingest, and administering the resulting library of resources, folders, and account usage. Jentic publishes and maintains the OpenAPI specifications for both Cloudinary APIs, keeping them validated and callable by AI agents. Together they let an agent add new media, tag and rename it, apply transformations without re-uploading, organize assets into folder hierarchies, and monitor storage and bandwidth against plan quotas.
Each workflow spans multiple Cloudinary APIs. Jentic routes each operation to the right API automatically.
Upload, tag, then verify against quota
An agent uploads a batch of product images with tags applied on ingest through the Upload API, then uses the Admin API to confirm the resources are listed and to check that storage and bandwidth remain below plan limits before continuing.
Upload product images with tags via the Upload API, then list the new image resources and read current usage with the Admin API to confirm storage is below the quota
Cloudinary Upload API + Cloudinary Admin API
Organize a library and place new assets in it
An agent creates a folder hierarchy for a campaign using the Admin API, then uploads the campaign's media into those folders and tags it through the Upload API, keeping ingest and organization aligned in a single flow.
Create a campaign folder with the Admin API, upload assets into it and apply tags with the Upload API, then list the folder contents to confirm placement
Cloudinary Admin API + Cloudinary Upload API
Audit and clean up a media library
An agent inspects resource metadata and usage through the Admin API to find oversized or untagged assets, then applies corrective transformations, retags, or removes them through the Upload API to reclaim storage.
List resources and read usage with the Admin API to flag oversized assets, then apply transformations or delete them with the Upload API and re-check usage
Cloudinary Admin API + Cloudinary Upload API
Your single Cloudinary API key and secret are stored once, encrypted, by your own Jentic One instance and injected as the Basic auth header at execution time, with upload signatures computed there. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'upload an image to cloud storage' or 'check Cloudinary usage', and Jentic returns the matching Upload or Admin API operation with its input schema, resolving the cloud name parameter so the agent calls the right endpoint without browsing the reference docs.
Cloudinary does not publish an official OpenAPI specification for these APIs. Jentic generates and maintains both specs, validates them against the live API, and keeps them current so AI agents and developers can call Cloudinary through structured tooling instead of hand-reading the reference docs.
How does an agent monitor storage and bandwidth while uploading?
The Admin API usage operation returns current-period metrics for storage, bandwidth, transformation credits, and API calls against your plan limits. An agent can upload media through the Upload API and then read usage through the Admin API to confirm it stays below quota before overages trigger extra charges.
Can an agent apply transformations without re-uploading an asset?
Yes. The Upload API explicit operation applies eager transformations such as resizing, cropping, format conversion, and quality adjustment to an asset that is already stored, using its public ID. Cloudinary generates the derivatives and caches them on its CDN, so no new upload is required.
All 4 are in the Jentic catalogue with the same one-credential, intent-search pattern.