This document serves as the official reference for the PixLab Vision Language Models (vLM) API endpoints. It details functionalities such as text analysis, Retrieval Augmented Generation (RAG), document parsing, text & image embedding, chunking, and structured data extraction. Users can integrate vision capabilities, tool calls, and document parsing from various formats, including Word, Office, image, and text embeddings, utilizing the PixLab Vision Platform.
To begin integration, obtain your API Key from the PixLab Console ↗. For detailed implementation guidance, please consult the REST API Reference or the specific vLM API endpoint documentation, which provides instructions for initiating your first API call using your preferred programming language. For a complete list of non-vision LLM API endpoints provided by PixLab, please consult the API Endpoints page →.
Vision Language Models API Endpoints & Tools
vLM API Endpoints Reference Guide
Boost your LLM workflow through the integration of vision capabilities, tool calls, and document parsing from diverse formats, including Word, Office, image, and text embedding, leveraging the PixLab Vision Platform.
Supercharge Your LLM Workflow...
Monthly API requests ↗ served
Uptime reliability guaranteed
API Endpoints and growing
Version 2.197 (Release Notes ↗)
List of Public Vision-Language API Endpoints
API endpoints are categorized for easy navigation and selection based on your integration needs. To start integrating the PixLab API, obtain your API Key ↗.
LLM Feed & Data Parse API
Parse & Extract data from various document formats including PDFs, Word documents, Excel spreadsheets, etc. for ingestion by an LLM.
- llm-parse LLM-friendly data extraction from various document formats
Text & Image Embedding API
Transform textual and image data into numerical vectors that encapsulate semantic meaning and contextual relationships.
ID Scan & Extract API
Scans and extracts data from nearly all official ID documents issued by over 200 countries & territories.
- docscan Scan and extract structured JSON data from over 11,000 ID documents
Health Check & System Status
Provide system and health status, supported file extension, and general details about the PixLab APIs.
Vision Language Models - vLM API
Analyze and extract content from images and other media using advanced Vision Language Models.
- query Receive natural language responses to image-related queries
- describe Generate a natural language description of an image content
- tagimg Retrieve a list of tags describing the image content
- nsfw Detect Adult and Bloody Content
- vOCR Vision Optical Character Recognition
- detect Identify objects in images and determine their locations
OpenAI Compatible LLM API
A set of state-of-the-art LLM models with an OpenAI Compatible API interface integrated within the PixLab API.
- chat OpenAI-compatible LLM interaction API endpoint
- summarize Summarize a given text
- answer Generate short answer using language models
- altext Generate alternative text (altext) for accessibility
- seotag Generate a search engine optimized description of an image or video frame
- coder OpenAI-compatible API endpoint for code generation
Face Recognition & Authentication
FACEIO ↗ is a facial recognition platform that enables secure, Passwordless login across all browsers through facial authentication, allowing you to integrate this feature into your website or web application.
- authenticate ↗ Identify registered users using facial recognition
- enroll ↗ Enroll a new user using facial recognition in your web application.
- face-verify ↗ Verify (Compare) if two faces in different images belong to the same person or not
- age-check ↗ Perform age estimation programmatically on a given face image
- liveness-check ↗ Mitigating Deepfake and Face Spoofing Threats
- facedetect detect faces in images or video frames
- facelandmarks identify facial landmarks and key points
- facemotion analyze facial expressions and emotions
Featured, Non-VLM API Endpoints
Featured non-vision LLM API endpoints. Streamline intelligent application development with easy API integration →, tailored for developers, businesses, and content creators.
ID Scan & Extract API ↓
Automate ID scanning and data extraction with PixLab’s ID Scan Platform →. Verify IDs from passports, driver’s licenses, and more with high accuracy. Supports over 11,000 document types from 197+ countries.
- Global ID Support: Scan passports, national IDs, driver’s licenses, and over 11,000+ document types from 197+ countries.
- Programmatic Data Extraction: Convert ID details into structured JSON with high accuracy.
Face Recognition & Authentication
Enhance authentication and access control with FACEIO ↗, a PixLab solution providing secure, cross-browser, passwordless authentication via facial recognition for websites and web applications.
- Age Verification: Verify user age instantly and with high accuracy.
- Facial Authentication: Enable seamless, password-free logins & attendance monitoring.
- Liveness Detection: Prevent spoofing with real-time security checks.
Background Removal API ↓
Effortlessly remove backgrounds and objects from images using PixLab’s Background Removal API →.
- Blazing-Fast Performance: Process images in seconds with minimal latency and achieve pixel-perfect results without manual adjustments.
- Seamless Integration: Integrate via API → for automated background removal in apps and websites, or use the Bulk Background Removal Online App ↗.
You're one step closer to creating an intelligent user experience...