For Agents
Search the Getty creative and editorial libraries, generate AI images, and run refinements such as background removal or extension across 71 endpoints with API-key plus OAuth authentication.
Use for: I need to search Getty Images for editorial photos of a specific event, Generate an AI image of 'a cyclist on a mountain road at dawn', Find a creative image suitable for a banner ad, Remove the background from an AI image I generated earlier
Not supported: Does not handle audio licensing, font libraries, or non-Getty third-party media - use for Getty Images and Getty-licensed AI image generation only.
The Getty Images API exposes 71 endpoints across the Getty creative and editorial library, including image and video search, AI image generation, refinement, extension, background removal, and affiliate flows. Authentication uses an API-Key header alongside OAuth 2.0 client credentials, supporting both server-to-server licensing workflows and end-user delegated access. The API also includes beta endpoints for AI file registration so customers can train and license generated content under the Getty rights framework.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Getty Images 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%2Fgettyimages.com%2Fgettyimages" | 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%2Fgettyimages.com%2Fgettyimages" | 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.
What an agent can do with Getty Images API.
Search creative and editorial photography by keyword, contributor, and date
Generate new AI images from text prompts under Getty's rights-cleared model
Refine, extend, or remove backgrounds on previously generated AI images
Register external files as AI training assets through the beta file-registration flow
Search videos and license video assets through affiliate workflows
GET STARTED
Retrieve specific image variations for layout testing without re-generating from scratch
Patterns agents use Getty Images API for, with concrete tasks.
★ Editorial Newsroom Image Search
News and media teams use Getty's editorial endpoints to find rights-cleared photographs of breaking events, sports, and entertainment within minutes of capture. The search endpoints accept keywords, date ranges, and contributor filters and return licensable assets with the metadata needed for caption and credit lines, removing the manual download workflow from the editor's path.
Search editorial images for 'olympics 2026 opening ceremony' filtered to the last 24 hours and return the top 5 by relevance.
AI Image Generation with Rights Clearance
Marketing and design teams use POST /v3/ai/image-generations to create custom imagery under the Getty NoFly rights model - content trained on licensed sources with indemnification. Generated images can be refined, extended, or have their backgrounds removed through dedicated endpoints, so the agent flows from prompt to print-ready asset without leaving Getty.
Generate an image with prompt 'minimalist office workspace, soft daylight', then call the background-removal endpoint on the chosen output.
E-Commerce Creative Asset Sourcing
E-commerce teams source product-adjacent lifestyle imagery from Getty's creative library and pair it with their own product shots. The video search endpoints support comparable workflows for landing pages and ad creative. Affiliate endpoints allow cross-sell partners to share licensed media without re-licensing the asset.
Search creative images matching 'autumn sweater lifestyle' and return the 10 highest-resolution results.
AI Agent Visual Content Workflows
An AI agent generating a marketing brief can call Getty to search for hero imagery, generate AI alternatives if no match exists, and refine the chosen output - all from a single integration. Through Jentic the agent uses natural-language search to find each operation and the Getty API key plus OAuth tokens stay in the encrypted vault.
Generate an AI image for prompt 'team celebrating product launch', then create one variation and remove the background from the variation.
71 endpoints — the getty images api exposes 71 endpoints across the getty creative and editorial library, including image and video search, ai image generation, refinement, extension, background removal, and affiliate flows.
METHOD
PATH
DESCRIPTION
/v3/affiliates/search/images
Search images via affiliate flow
/v3/affiliates/search/videos
Search videos via affiliate flow
/v3/ai/image-generations
Generate a new AI image from a prompt
/v3/ai/image-generations/{generationRequestId}
Retrieve the status and outputs of a generation request
/v3/ai/image-generations/{generationRequestId}/images/{index}/variations
Create variations from a generated image
/v3/ai/image-generations/refine
Refine a generated image
/v3/ai/image-generations/extend
Extend the canvas of a generated image
/v3/ai/image-generations/background-removal
Remove background from a generated image
/v3/affiliates/search/images
Search images via affiliate flow
/v3/affiliates/search/videos
Search videos via affiliate flow
/v3/ai/image-generations
Generate a new AI image from a prompt
/v3/ai/image-generations/{generationRequestId}
Retrieve the status and outputs of a generation request
/v3/ai/image-generations/{generationRequestId}/images/{index}/variations
Create variations from a generated image
/v3/ai/image-generations/refine
Refine a generated image
/v3/ai/image-generations/extend
Extend the canvas of a generated image
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Getty Images API by hand means sending an API-key header alongside an OAuth 2.0 token you exchange at authentication.gettyimages.com, and refreshing that token yourself. Through Jentic you install once, import the Getty Images API from the API Directory, store the API key and OAuth client credentials once, and your agent calls it.
Permission scoping
Getty puts the generation request id in the URL path (/v3/ai/image-generations/{generationRequestId}/...), so a rule can pin your agent to one generation for variations, refine, and extend. You choose the operations it may call, so starting new generations or background removal is not included unless you add them.
Credential isolation
Your Getty API key and OAuth client credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time, with the short-lived access token minted for the call. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search for an editorial image' or 'generate a licensed AI image', and Jentic returns the matching Getty operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Getty Images API through Jentic.
What authentication does the Getty Images API use?
Getty supports two schemes: an API-Key header for server-side identification and OAuth 2.0 for delegated user access. Through Jentic both the API key and OAuth client credentials are stored encrypted; the agent receives a scoped access token at execution time and the raw secrets never enter its context.
Can I generate AI images with the Getty Images API?
Yes. POST /v3/ai/image-generations creates a generation request from a text prompt and returns a generationRequestId that GET /v3/ai/image-generations/{generationRequestId} polls until the outputs are ready. Refinement, extension, and background-removal operate on the same request id.
What are the rate limits for the Getty Images API?
Limits depend on the licensing tier - affiliate and enterprise contracts get higher quotas than developer accounts. The API returns 429 with retry-after headers when limits are hit; production integrations should implement exponential backoff.
How do I run an editorial image search through Jentic?
Search Jentic for 'getty editorial image search'. Jentic returns the matching search operation with its parameter schema; load it with your keyword and date filters and execute. The response includes asset urls and licensing metadata.
Can I remove the background from a generated AI image?
Yes. POST /v3/ai/image-generations/background-removal accepts the generation request id and image index and returns a new asset with the background removed under the same Getty rights model.
Is the Getty Images API free?
No. Getty operates a licensing model - usage is metered and billed per asset or under a contract. Affiliate, developer, and enterprise tiers exist; pricing is negotiated with Getty's commercial team.
Can I limit what my agent is allowed to do with the Getty Images API?
Yes. Because you run Jentic One yourself, your own rules decide which Getty operations and credentials the agent may use, so you can grant only search or variation calls while withholding others. Getty puts the generation request id in the URL path (/v3/ai/image-generations/{generationRequestId}/...), so a rule can pin the agent to a single generation for variations, refine, and extend. Starting a new generation with POST /v3/ai/image-generations or calling background-removal stays off limits unless you explicitly add those operations.
/v3/ai/image-generations/background-removal
Remove background from a generated image