Tools
Image to Markdown API
Submit any image. Get back a readable Markdown document with OCR text, dimensions, and metadata.
Try it below:
Turn images into Markdown
Upload an image or submit a URL, get Markdown back.
What is Exabase's image to Markdown API?
Submit an image to the Exabase Extract API and get a Markdown document back instead of JSON. The same extraction pipeline runs: OCR, metadata extraction, and thumbnail generation. Pass ?format=markdown when retrieving the result and you get a human-readable Markdown document with the extracted text instead of a JSON object.
The Markdown output includes image dimensions, MIME type, file size, and the full OCR text. JPEG, PNG, WebP, TIFF, BMP, and other major formats are supported. No Tesseract, no OpenCV, no preprocessing pipeline.
What you get back
The Markdown response is a single text document. Image dimensions and file metadata appear at the top. The OCR text follows under a ## Media section. The result is ready to feed into an LLM context window, store as a searchable note, or use as a reference.
You can also configure webhooks with webhookFormat: "markdown" so completed jobs POST the Markdown document directly to your server.
One multi-modal API
The same POST /v2/extract endpoint handles every content type Exabase supports, and the ?format=markdown parameter works across all of them. For images, you get dimensions and OCR text. For PDFs, you get document metadata and text. For audio and video, you get duration and the transcript. For web pages, you get the title, site name, and content.
The submission flow is identical across all types. The Extract docs cover each content type in detail.
What you can build with it
Feed OCR results directly into your agent's context window as readable text. Build a document digitisation pipeline where photos of paper documents become readable Markdown. Power a searchable archive where every image's text content is stored as a readable, indexed document.
Store extracted images as Resources in a Base and the OCR text becomes searchable through Deep Search. Workers can process new images as they arrive.
Beyond Markdown
The Extract API also returns JSON (the default) with structured chunks. Use Markdown for LLM context and human review, JSON for structured processing and search indexing. The Image to JSON tool page covers the JSON output.
How do I use it?
Get your API key
Free, no credit card:
Sign up at exabase.io and copy your API key from the dashboard.
Submit an image file
Using the SDK (Node.js):
Get Markdown back
Poll the job until state reaches completed, or skip polling entirely with webhooks.
One API call. No Tesseract, no OpenCV, no Markdown conversion.
Why Exabase
Works with other Exabase features
FAQs
What is Exabase?
Exabase is infrastructure for AI agents. It gives your agents memory, versioned file storage, AI deep search, and context automation through a set of APIs. Store what your agent learns, search inside any content type, and keep knowledge bases current automatically. Built for production use. Give your agent precise context and cut your token spend by up to 81%.
Who uses Exabase?
Developers and teams building AI agents, copilots, and RAG applications. If your agent needs to remember things between sessions, store and retrieve files, search across documents and media, or stay up to date without manual maintenance, Exabase handles that infrastructure so you can focus on your product.
How fast is processing?
Most images complete in a few seconds. Processing is asynchronous, so your application is not blocked while extraction runs.
How do I get Markdown instead of JSON?
Add ?format=markdown to the GET /v2/extract/{jobId} request. For webhooks, set webhookFormat: "markdown".
Does it handle rotated or skewed text?
The OCR engine handles common orientations and skew. For best results, images with text that's roughly upright will produce the most accurate output.
Can I still get JSON?
Yes. JSON is the default. Both formats are available from the same extraction job.
How is this different from Image to JSON?
Same pipeline, different output. Image to JSON returns structured JSON. Image to Markdown returns a readable document.
What image formats are supported?
JPEG, PNG, WebP, TIFF, BMP, and other major formats.
What if the image has no text?
The Markdown document still includes image metadata (dimensions, MIME type, size). The OCR field will be empty.
Does it handle handwriting?
Yes, with caveats. Printed and typed text is extracted reliably. Handwriting accuracy depends on legibility.
Do I have to poll for results?
No. Configure a webhook with webhookFormat: "markdown" to receive the document on completion.
How long are files retained?
Stored files are retained for 1 day from job creation, then permanently deleted.
Is there an SDK?
Yes. The @exabase/sdk package for Node.js/TypeScript handles file streaming, job polling, and chunk retrieval. Install with npm install @exabase/sdk. Or call the REST API directly from any language.
What other content types support Markdown output?
All of them. See the PDF to Markdown, Audio to Markdown, Video to Markdown, and Website to Markdown tool pages.
Other tools
Deciding?
Ask your favourite AI about Exabase:
