Install Jentic One Beta

Connect the Pixly API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pixly 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://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpixly.app%2Fpixly" | sh

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%2Fpixly.app%2Fpixly" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 Pixly API.

Virtually stage an empty or badly furnished room photo in a chosen interior style such as scandinavian, japandi, or mid-century-modern

Clean up listing photos by decluttering, removing furniture, straightening, enhancing, or upscaling them to HD

Change a property's look with sky replacement, lawn replacement, day-to-night conversion, seasonal reset, or an exterior makeover

Generate property videos from photos, including photo-to-video camera moves such as orbitLeft or pushIn, flythroughs, and before-and-after reels

GET STARTED

Start building with Pixly API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Pixly API for, with concrete tasks.

★ Agent-Driven Listing Photo Staging via Jentic

A real estate assistant agent receives empty-room photos from an agent or photographer and needs staged versions for the listing. Through Jentic it calls the virtual_staging tool with the imageUrl and a style such as scandinavian, polls get_job until the status is completed, and returns the staged image URLs, checking the credit balance first so a run does not stop halfway with a 402.

Read the account's creditsRemaining, then stage three empty bedroom photos in the japandi style with virtual_staging, poll each job until completed, and return the resultUrls

Listing Photo Clean-Up Before Publishing

Photographers and listing coordinators prepare a shoot for publication by running the clean-up tools: declutter_photo and remove_furniture for interiors, straighten_photo for crooked verticals, replace_sky and replace_lawn for exteriors, and blur_faces_plates for privacy. Each result's resultPaths entry can be passed as the r2Path of the next tool, so several edits chain without re-uploading.

Run replace_sky on an exterior photo, then pass the job's first resultPaths entry as r2Path to blur_faces_plates and return the final result URL

Property Videos from Still Photos

Agents who want short listing videos without a video shoot generate them from photos. The photo_to_video tool moves the camera from a start photo, optionally landing on an end photo of the same space, with ready-made moves such as smooth, walk, or riseUp, while flythrough_video and before_after_reel produce tour and comparison clips for social posts.

Create a photo_to_video job from two kitchen photos using endImageUrl and the orbitRight cameraMove, then poll get_job and return the video URL

Renovation and Restyle Previews

Buyers and sellers want to see what a room or facade could look like. The restyle_room, makeover_exterior, and touch_up_exterior tools produce previews of a new interior style or refreshed exterior, and before_after_image composes the original and result side by side for a listing or a client message.

Restyle a dated living room photo with restyle_room, then build a before_after_image from the original and the result and return the comparison URL

Key Endpoints

31 endpoints — the pixly api turns real estate listing photos into virtually staged rooms, edited images, and short property videos.

METHOD

PATH

DESCRIPTION

POST

/api/v1/tools/virtual_staging

Stage a room photo in an interior style

POST

/api/v1/tools/photo_to_video

Turn one or two photos into a video

POST

/api/v1/tools/replace_sky

Replace the sky in an exterior photo

POST

/api/v1/tools/declutter_photo

Declutter a room photo

GET

/api/v1/jobs/{id}

Poll a job for status and result URLs

POST

/api/v1/uploads

Import a photo or get an upload ticket

GET

/api/v1/tools

List tools with input schemas

GET

/api/v1/account

Read credit balance and plan

POST

/api/v1/tools/virtual_staging

Stage a room photo in an interior style

POST

/api/v1/tools/photo_to_video

Turn one or two photos into a video

POST

/api/v1/tools/replace_sky

Replace the sky in an exterior photo

POST

/api/v1/tools/declutter_photo

Declutter a room photo

GET

/api/v1/jobs/{id}

Poll a job for status and result URLs

POST

/api/v1/uploads

Import a photo or get an upload ticket

GET

/api/v1/tools

List tools with input schemas

GET

/api/v1/account

Read credit balance and plan

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Pixly by hand means choosing between a pixly_sk_ bearer key and OAuth 2.1 with PKCE, uploading photos or presigned tickets, and writing the 202-then-poll loop for every generation. Through Jentic you install once, import Pixly from the API Directory, store the credential once, and your agent runs the tools.

Permission scoping

Every Pixly tool has its own path under /api/v1/tools/, so rules bound which tools your agent may call: virtual staging can be allowed while video generation and checkout stay off the list. You choose the operations it may call, so credit-spending tools are not included unless you add them.

Credential isolation

Your Pixly API key or OAuth token 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 'virtually stage a room' or 'turn a photo into a video', and Jentic returns the matching Pixly tool operation with its input schema so the agent picks the right tool without browsing the reference docs.

FAQs

Specific to using Pixly API through Jentic.

What authentication does the Pixly API use?

Per its OpenAPI spec, the Pixly API accepts two schemes: a bearer API key of the form pixly_sk_... created in your Pixly account settings, or OAuth 2.1 with PKCE through the authorization code flow with the tools scope, which covers running tools with the account's credits and reading its jobs and balance. Through Jentic the key or token is stored encrypted on your own instance and injected at call time.

Is there a Pixly MCP server?

You don't need an MCP server to give your agent Pixly. Jentic connects it directly from the API Directory: import Pixly, store your credential once, and your agent can stage photos and generate videos straight away. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.

Can I limit what my agent is allowed to do with the Pixly API?

Yes. Write a rule that allows only the virtual_staging, replace_sky, and get_job operations, so the agent can stage rooms, swap skies, and poll for results but cannot start credit-heavy video tools or open a checkout link, and every call it makes is logged.

How do I get the result of a Pixly tool call?

If a tool answers 202, the work runs as a job: poll get_job at /api/v1/jobs/{id} until the status is completed or failed. A completed job carries presigned resultUrls valid for 7 days, plus resultPaths you can pass as r2Path to run another tool on the result without uploading it again.

What are the rate limits for the Pixly API?

The Pixly OpenAPI spec states 120 requests per minute, with generations limited to 30 per minute. A rate-limited call returns 429 with a Retry-After header saying when to try again.

How do I stage a room photo with the Pixly API through Jentic?

Search Jentic for an intent like 'virtually stage a room photo', import Pixly, and store your API key once. Your agent then calls the virtual_staging operation at /api/v1/tools/virtual_staging with an imageUrl and a style, and polls get_job for the staged image. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Does the Pixly API charge credits for every call?

No. Generation tools spend credits from the account's Pixly balance, and each job reports creditsCharged. Reading the account, jobs, library, and tool list does not run a generation. When the balance is empty or there is no active plan, tools answer 402 and the checkout operation returns a payment link for the account holder.

Pixly App Pixly API

AI ReadinessAI-Aware (B+)68/100

See full scorecard

Official vendor OpenAPI document · agent-readyMediaImage Processingbearer, oauth231 EndpointsREST

For Agents

Stage empty rooms, declutter or restyle listing photos, replace skies and lawns, and generate property videos from photos, then poll each job for its result URLs. Covers uploads, the tool list, job history, the library, and the credit balance.

Use for: I need to virtually stage an empty living room photo, Remove the furniture from this listing photo, Replace the grey sky in this exterior shot with a blue one, Turn two photos of the kitchen into a short orbit video

Not supported: Does not handle property listing data, MLS publishing, or general video editing timelines. Use for staging, editing, and animating real estate photos only.

The Pixly API turns real estate listing photos into virtually staged rooms, edited images, and short property videos. Each tool has its own operation, from virtual staging in a chosen interior style and furniture removal to sky replacement, day-to-night conversion, floor plan rendering, and photo-to-video camera moves. A tool call takes an imageUrl or an r2Path from your Pixly library; when it answers 202 you poll the job until its status is completed, then download the resultUrls. Generation tools spend credits from the account's Pixly balance, which you can read alongside the active plan.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: ASignals: 4

97%

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).

60%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

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.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C-Signals: 4

51%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

51%

Summary Coverage

Coverage of summaries across operations/tags/info.

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.

Security

Trust, risk posture, and security compliance.

Grade: A-Signals: 1

75%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: BSignals: 1

66%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Pixly API to your agent

Capabilities

Start building with Pixly API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Pixly App Pixly API

Jentic AI Readiness Score

Pixly API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness