Creatomate Render API
Agent-ready OpenAPI document · curated by JenticMediaVideo Processingbearer4 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Generate videos and images programmatically from Creatomate templates by submitting a render job and waiting for the finished file URL. Use it for automated social posts, ad variants, or templated media at scale.
Use for: Generate a 30-second product video from a Creatomate template with custom text and image, Render an Instagram story from a template and get the MP4 URL, List all video templates in my Creatomate workspace, Check the status of a render job I started two minutes ago
Not supported: Does not handle template authoring, asset hosting beyond the rendered output, or live video streaming - use for template-driven video and image rendering only.
Jentic publishes the only available OpenAPI specification for Creatomate Render API, keeping it validated and agent-ready. Creatomate is a render service that turns templates and parameter sets into produced videos and images, returning rendered assets that an application can ship to social channels, ad platforms, or storage. The API exposes operations to list and inspect templates, kick off a render with template substitutions or raw RenderScript, and poll a render's status to retrieve the final output URL.
Install Jentic One Beta
Connect the Creatomate Render API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Creatomate Render 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%2Fcreatomate.com%2Fcreatomate" | 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%2Fcreatomate.com%2Fcreatomate" | 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 Creatomate Render API.
List the templates available in a Creatomate workspace with their IDs and names
Fetch the full definition of a single template, including its named modifiable elements
Start a render by passing a template ID with modifications, or by supplying a full RenderScript scene
Poll a render by ID to read its status, progress, and the URL of the finished video or image
Receive completion callbacks at a webhook URL passed when a render is created
Use Cases
Patterns agents use Creatomate Render API for, with concrete tasks.
★ Templated social-media video generation
Produce one video per data row, such as a product feed or daily news headline, by calling POST /renders with a template ID and a modifications object that overrides text and image elements. Creatomate handles encoding and returns a hosted URL for the finished MP4, removing the need for an in-house ffmpeg pipeline.
Call POST /renders with template_id of the Instagram template, modifications setting Headline.text and Product.source, then poll GET /renders/{id} until status is 'succeeded' and return the url field.
Ad creative variants at scale
Generate dozens of ad variants from a single base template by submitting a render request per variant with different copy, imagery, or call-to-action elements in modifications. Creatomate runs the renders server-side so the agent only manages the variant matrix and the resulting URLs.
For 12 headline-image pairs, call POST /renders with the same template_id and a modifications object per pair, collect the returned render IDs, and poll each until completion.
On-demand image card generation
Render branded share cards or social images on demand by posting to /renders with an image template and per-request modifications. Useful for blog open-graph cards, certificate generation, or quote-of-the-day images where the rendered file is fetched and served by the calling application.
Call POST /renders with the share-card template_id and modifications setting Title.text and Author.text, then return the url field once the render reports succeeded.
Agent-driven content rendering through Jentic
Let an agent fulfil a 'render me a 15-second teaser with this script' request without code by routing through Jentic. The agent searches for a render operation, loads the Creatomate /renders schema, and submits the template ID with modifications; Jentic injects the bearer key from the vault and returns the polling endpoint to use.
Through Jentic, run search('render a video from a template'), load Creatomate POST /renders, submit template_id and modifications, then poll GET /renders/{id} via Jentic until succeeded.
Key Endpoints
4 endpoints — jentic publishes the only available openapi specification for creatomate render api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
GET
/templates
List all templates in the workspace
GET
/templates/{id}
Fetch a single template definition
POST
/renders
Start a render from a template or RenderScript
GET
/renders/{id}
Get the status and output URL of a render
GET
/templates
List all templates in the workspace
GET
/templates/{id}
Fetch a single template definition
POST
/renders
Start a render from a template or RenderScript
GET
/renders/{id}
Get the status and output URL of a render
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Creatomate by hand means managing its bearer header and polling /renders/{id} to know when a template-driven render has finished. Through Jentic you install once, import Creatomate from the API Directory, store the token once, and your agent calls it.
Permission scoping
Creatomate takes the template and modifications in the request body when starting a render, so scope the agent to the operations it needs, such as listing templates and submitting a render. Reading a render's status stays out unless you include that operation.
Credential isolation
Your Creatomate bearer key is stored once, encrypted, by your own Jentic One instance and applied as the Authorization header at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'render a video from a template', and Jentic returns the matching Creatomate 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 Creatomate Render API through Jentic.
Why is there no official OpenAPI spec for Creatomate Render API?
Creatomate does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Creatomate Render API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Creatomate Render API use?
The API uses HTTP bearer authentication. Pass your Creatomate API key in the Authorization header as 'Bearer <key>' on every request. Through Jentic, the key is stored encrypted in the vault and applied at execution so it never enters the agent's prompt.
Can I render a video from a template with the Creatomate Render API?
Yes. Call POST /renders with a template_id and a modifications object that overrides the named elements in that template. The response contains a render id; call GET /renders/{id} to poll until status is 'succeeded' and read the output URL.
How do I get notified when a Creatomate render finishes?
Pass a webhook_url field in the POST /renders body and Creatomate will POST the completion event to that URL when the render reaches a terminal state, instead of requiring continuous polling of GET /renders/{id}.
What are the rate limits for the Creatomate Render API?
Creatomate enforces concurrency and monthly render quotas tied to the workspace plan rather than fixed per-second limits in the spec. Build retries around 429 responses on POST /renders and use webhooks instead of tight polling on GET /renders/{id} to stay within plan limits.
How do I render a video through Jentic?
Install Jentic with pip install jentic, then async-search for 'render a video from a template'. Load the Creatomate POST /renders operation, execute with template_id and modifications, and poll GET /renders/{id}. Jentic attaches the bearer key automatically.
Can I limit what my agent is allowed to do with the Creatomate Render API?
Yes. Because Jentic One is self-hosted, you decide which Creatomate operations your agent may call, so you can allow it to list templates with GET /templates and start a render with POST /renders while keeping the rest out of reach. If polling is not needed, you can leave GET /renders/{id} unimported so the agent cannot inspect render status, and template reads stay off unless you add GET /templates/{id}. The bearer key is applied by your own instance at execution, so the agent only ever calls the operations your rules permit.
GET STARTED