API Reference

VLM-1

Documentation

Contact

Health

Extract JSON from images, videos, and documents with a unified API.

Introduction

Extract JSON from images, videos, and documents with type-safety.

Structured Responses

Extract JSON from images, videos, and documents with custom schemas.

Custom Schemas

Run VLM-1 with the OpenAI Python SDK with just 2 lines of code change.

OpenAI Compatibility

Extract structured data from long documents and reports.

Parsing Documents

Extract structured data from rich visual PDFs and presentations.

Parsing Presentations

Parsing Resumes

Parsing Invoices

Learn how to extract structured data from TV news broadcasts.

Understanding TV News

Learn how to analyze video podcasts using our Video Transcription API.

Understanding Video Podcasts

Learn how to generate captions, tags and descriptions for images.

Image Cataloging

Learn how to extract dense tables with structure from documents.

Dense Table Extraction

Learn how to extract visual groundings / citations from documents.

Visual Grounding

Learn how to visually scrape websites using VLM Run.

Visual Web Scraping

Learn how to fine-tune VLM-1 for your use-case.

Get models

Generate structured prediction for the given image.

Image -> JSON

Generate structured prediction for the given document.

Doc -> JSON

Generate structured prediction for the given audio.

Audio -> JSON

Generate structured prediction for the given url.

Web -> JSON

Generate embeddings for the given image or text.

Image / Text Embeddings

Generate embeddings for a given document.

Doc / Text Embeddings

Get Response by ID

Upload file

Get file

Create chat completion

List all models

MongoDB

ChromaDB

Rate limits to consider when using the API.

Rate Limits

List of error codes that you may encounter when using the API

Models

Generate

Embeddings

Responses

Files

OpenAI Compatibility

Health

Response