ConvertAPI
★ Only Publicly Available OpenAPI DocumentData EnrichmentData TransformationapiKey, bearer4 EndpointsREST
For Agents
Convert a file from one format to another with a single POST call to ConvertAPI. Agents authenticate with an API secret query parameter or bearer token.
Use for: Convert this DOCX to PDF, I want to turn an HTML page into a PNG screenshot, Upload a PowerPoint file and convert it to PDF, List every conversion ConvertAPI supports between PDF and other formats
Not supported: Does not perform OCR, content editing, or asynchronous task queuing - use for direct format-to-format file conversion only.
Jentic publishes the only available OpenAPI specification for ConvertAPI, keeping it validated and agent-ready. ConvertAPI converts files between document, image, and web formats through a single POST /convert/{sourceFormat}/to/{destinationFormat} endpoint that returns the converted output synchronously. The API also supports uploading files for later conversion, listing available converters, and inspecting account usage. Authentication is either an API secret in the query string or a bearer token in the Authorization header.
Install Jentic One Beta
Connect the ConvertAPI to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ConvertAPI, 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%2Fconvertapi.com%2Fconvertapi" | 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%2Fconvertapi.com%2Fconvertapi" | 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 ConvertAPI API.
Convert a file between any supported source and destination format via POST /convert/{sourceFormat}/to/{destinationFormat}
Upload a file with POST /upload to use as input on subsequent conversions
Discover supported source and target formats via GET /info
Inspect account usage and remaining quota via GET /user
Authenticate either with the Secret query parameter or an Authorization Bearer token
Use Cases
Patterns agents use ConvertAPI API for, with concrete tasks.
★ Synchronous Document-to-PDF Conversion
Convert documents - DOCX, XLSX, HTML, Markdown - to PDF on demand by POSTing the source file to /convert/{sourceFormat}/to/pdf. The response carries the converted file directly, so there is no polling step. Suited to applications that need instant export-as-PDF behaviour for user-facing documents.
POST a DOCX file to /convert/docx/to/pdf and stream the resulting PDF back to the user
Format Discovery and Capability Reporting
Build user interfaces that show only the conversions actually supported by ConvertAPI by reading GET /info at startup. The endpoint returns the full source-to-destination matrix, so dropdowns and file pickers stay in sync with the live capability list. Useful for SaaS dashboards exposing conversion options to end users.
Call GET /info and return the full list of formats that can be converted to PDF
Two-Step Upload-Then-Convert Workflow
Upload a large file once via POST /upload, then run multiple conversions against the same uploaded file by referencing its ID on the convert endpoint. This avoids re-transferring large source files when the same input needs PDF, PNG, and TXT outputs. Useful for archival and indexing pipelines that produce several derivative formats from each source.
Upload report.docx via POST /upload, then trigger conversions to PDF, PNG, and TXT against the returned upload ID
Agent-Driven File Conversion via Jentic
An AI agent converts user files end-to-end through Jentic without holding the API secret. The agent searches Jentic for 'convert a file', loads the schema, and executes POST /convert/{sourceFormat}/to/{destinationFormat} with the desired formats. Through Jentic the secret or bearer token is injected from the vault so authoring loops stay safe.
Search Jentic for 'convert a docx to pdf', load the ConvertAPI schema, then convert the user's uploaded DOCX and return the PDF URL
Key Endpoints
4 endpoints — jentic publishes the only available openapi specification for convertapi, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
POST
/convert/{sourceFormat}/to/{destinationFormat}
Convert a file between two formats
POST
/upload
Upload a file to reuse on later conversions
GET
/info
List all available converters
GET
/user
Get the authenticated user's account information
POST
/convert/{sourceFormat}/to/{destinationFormat}
Convert a file between two formats
POST
/upload
Upload a file to reuse on later conversions
GET
/info
List all available converters
GET
/user
Get the authenticated user's account information
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring ConvertAPI by hand means deciding whether to pass the Secret as a query parameter or a bearer token, then handling the format-to-format request and file handoff yourself. Through Jentic you install once, import ConvertAPI from the API Directory, store the credential once, and your agent calls it.
Permission scoping
The source and destination formats travel in the request path as conversion parameters, not as a fixed resource you own, so scope this by operations: allow the agent the calls it needs, such as converting a file and uploading one, and leave read-only lookups like account info in or out as you choose. Each operation you credit the agent with stays inside that allowed set.
Credential isolation
Your ConvertAPI secret is stored once, encrypted, by your own Jentic One instance and injected as the Secret query parameter or 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 'convert a docx to pdf', and Jentic returns the matching ConvertAPI convert operation with its input schema so the agent builds the request without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using ConvertAPI API through Jentic.
Why is there no official OpenAPI spec for ConvertAPI?
ConvertAPI does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call ConvertAPI 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 ConvertAPI use?
Two schemes are supported: the Secret query parameter (apiKey) for the simplest direct use, and HTTP Bearer authentication via the Authorization header. Through Jentic the secret or bearer token is stored in the vault and injected at execution time so it never enters the agent's prompt.
How do I convert a DOCX file to PDF with ConvertAPI?
POST your DOCX file to /convert/docx/to/pdf with multipart form data and the API returns the converted PDF synchronously. There is no separate task or polling step - the response body carries the result.
Which formats can ConvertAPI convert between?
Call GET /info to retrieve the live list of supported source and destination formats - documents, images, web pages, and more. The endpoint returns the matrix so applications can stay in sync as ConvertAPI adds converters.
How do I check my ConvertAPI account quota?
Call GET /user with your bearer token or Secret. The response includes account information and the remaining quota for the authenticated user.
How do I run a conversion through Jentic?
Run jentic search for 'convert a file', load the POST /convert/{sourceFormat}/to/{destinationFormat} operation, then execute it with the source format, destination format, and file. Jentic injects the credential from the vault and returns the converted file as a structured response.
Can I upload a file once and convert it to multiple formats?
Yes. POST /upload returns an ID for the uploaded file, which can be referenced on subsequent /convert calls to produce different output formats without re-uploading the source. This is efficient for derivative-format pipelines.
Can I limit what my agent is allowed to do with the ConvertAPI?
Yes. Because you run Jentic One yourself, your own rules decide which ConvertAPI operations and credentials the agent may use. You can allow just the calls it needs, such as converting a file with POST /convert/{sourceFormat}/to/{destinationFormat} and uploading a file with POST /upload, while choosing to include or exclude the read-only lookups like GET /info and GET /user. Each operation you credit the agent with stays inside that allowed set, and your stored secret is injected at execution time rather than exposed to the agent.
GET STARTED