Vision API

The Reka Vision API provides powerful video processing and analysis capabilities, enabling you to upload, manage, and interact with videos using AI-powered question answering.

Key Features

• Video Management: Upload, retrieve, list, and delete videos
• Video Search: Find videos using semantic search
• Video Q&A: Ask questions about video content and get AI-powered answers with streaming support
• Metadata Tagging: Generate tags for videos
• Highlight Reel Generation: Generate shorter highlight reels from your longer videos

Getting Started

1. Upload a video using the /videos/upload endpoint
2. Search your videos using the /videos/search endpoint
3. Ask questions about your videos using the /qa/chat endpoint
4. Generate tags for your videos using the /qa/indexedtag endpoint
5. Generate highlight reels from your videos using the /generations endpoint

Authentication

All Vision API requests require authentication using an API key in the X-Api-Key header:

$
X-Api-Key: YOUR_API_KEY

Rate limits

The vision API allows up to 2-hours of indexed video content per API key for free. For additional usage, please contact us.

Base URL

https://vision-agent.api.reka.ai

Healthcheck

Quickly verify service availability by pinging /health.

$
curl -s https://vision-agent.api.reka.ai/health | jq .

1
import requests
2
3
def health_check():
4
    url = "https://vision-agent.api.reka.ai/health"
5
    resp = requests.get(url, timeout=5)
6
    resp.raise_for_status()
7
    print("[HEALTH ✓]", resp.status_code)
8
9
health_check()

Finetuning

We offer finetuning services with our engineering team.

Pricing starts from $0.5 per input video minute (including output text), with discounts for larger scale training.