Video & Image Intelligence Analyzer

AI-powered multimodal analysis for images and videos. Extract structured tags, scene descriptions, text content, mood analysis, and virality scores from any image or video URL.

	Free plan (preview)	Paid Apify plan (Starter and up)
URLs analyzed per run	1 (the first URL)	every URL you enter
Frame-by-frame rows of a video	1 frame row; the rest are counted (N of M shown)	every frame row
What the rest would give	a free-plan-preview row: URLs not analyzed, frame rows locked, and an estimate (BRONZE prices) of a paid run of the same input	—
Price	same events	same events, with plan discounts: BRONZE 20% off, SILVER 35% off, GOLD and up 48% off

A free run ends as SUCCEEDED with a status message that says how many URLs and frame rows were left out. Run the same input again on a paid plan for everything.

Features

• Image Analysis: Detailed descriptions of any image
• Video Analysis: Frame-by-frame analysis with comprehensive summary
• Smart Tagging: Structured JSON output with category, tags, mood, text detection, and virality score
• 15 Languages: English, Spanish, Portuguese, French, German, Arabic, Hindi, Vietnamese, Thai, Indonesian, Turkish, Russian, Korean, Japanese, Chinese
• Custom Prompts: Override default analysis with your own questions

Pricing

Free plan: 1 URL analyzed and 1 frame row per video a run (see the table above). Paid Apify plans get every URL and every frame row.

Event	Price (FREE tier list price)	When it is charged
analysis-complete	$0.05	once per URL whose analysis row is delivered
frame-detail	$0.005	once per frame row of an analyzed video (only when the vision API returns a frame breakdown)
url-checked	$0.005	once per URL that both our server and the Actor tried and that failed on the URL's own side: the image host answered with an HTTP error, the URL is not an image, the body is empty, the file is over 20 MB, or the address is not http(s). The row has rowType: "url-checked", errorSide: "target", reason and httpStatus. Charged only once this event is on the live price list

Who is behind a failed URL. When the URL's own host answers 401, 403, 404 or 410, the check is done and the answer is the host's: errorSide: "target" with reason (login-required, forbidden, not-found, gone) and httpStatus, charged as url-checked. When it answers 429, 503 or another temporary code, the Actor waits briefly and asks once more; the same kind of answer again is the host's own state: reason: "temporarily-unavailable" with the HTTP code, charged the same way. Not charged: rows with errorSide: "service" — our side: our time limit, a host that never answered, our vision server's errors — and notice rows.

If the platform restarts a run, the new run life reads the run's own dataset and the platform's charge counts: rows already delivered are not delivered or charged again. A URL whose analysis row was already delivered is not analyzed again: if the restart cut it between its analysis row and its frame rows, the missing frame rows are not made again (a second analysis would describe other frames) and not charged, and one free partial-result row names them (partial: true, missingLayers, inputIndex); the status says N of M complete, K partial. Every result row and the partial-result row carry inputIndex: the URL's 0-based place in urls exactly as given — nothing is de-duplicated, so a URL listed twice gets two places and two separate answers. The dataset's Overview view shows inputIndex, rowType, noticeCode, missingLayers and message, so a cut input is visible next to its rows. If the dataset cannot be read back, the run stops without processing or charging anything more. Plan discounts: BRONZE 20%, SILVER 35%, GOLD and up 48%.

The run stops when its maximum charge is reached: no further row is delivered, a charge-limit-reached notice row says how many URLs were not processed, and the run ends as SUCCEEDED.

Input

Field	Type	Default	Description
urls	string[]	required	Image or video URLs to analyze
mode	string	tag	tag = JSON tags, image = description, video = frame-by-frame
prompt	string	—	Custom analysis prompt
language	string	en	Response language (15 supported)
maxFrames	number	20	Max frames for video analysis
maxTokens	number	256	Max response length

Output Example (Tag Mode)

{
    "url": "https://example.com/image.jpg",
    "mode": "tag",
    "source": "direct",
    "analyzedUrl": "https://example.com/image.jpg",
    "delivery": "server-fetch",
    "analysis": {
        "category": "logo",
        "tags": ["google", "search", "technology", "brand", "icon"],
        "mood": "neutral",
        "has_text": true,
        "text_content": "Google",
        "virality_score": 9
    },
    "processingTimeMs": 978,
    "model": "qwen2.5vl:7b"
}

Supported Video Formats

MP4, MOV, AVI, WebM, MKV (direct file URLs).

YouTube links (youtube.com/watch, youtu.be, /shorts/) are analyzed through the video's public thumbnail image, not the full video. Those rows have source: "youtube-thumbnail" and analyzedUrl pointing at the thumbnail.

Hosts that block automated downloads: if the vision server cannot download an image URL, the Actor downloads the image itself and sends the bytes (delivery: "actor-fetch" on the row).

Disclaimer

• This Actor is an independent, unofficial tool and is not affiliated with, endorsed by, or sponsored by any social platform whose content you may submit a URL for.
• Analysis results are generated by AI and provided for reference only. No guarantees of accuracy.
• This tool does not store or redistribute any analyzed content. All temporary files are deleted immediately after processing.
• Users are responsible for ensuring they have the right to analyze the content they submit.
• This tool is not intended for surveillance, facial recognition databases, or any use prohibited by applicable laws.
• The developer is not liable for any decisions made based on the analysis results.
• By using this Actor, you agree that analysis of content containing personal data (faces, identifying information) is your responsibility under applicable privacy laws including GDPR.

---

🔗 Related Actors by ntriqpro

Build your data pipeline with the ntriqpro Actor suite:

• alt-text-batch — Bulk Alt-Text Generator — SEO + WCAG
• content-factory — AI Content Engine — Quiz, Flashcard, Podcast
• image-batch-optimizer — Image Compressor

⭐ Love it? Leave a Review

Your rating helps creators and media teams discover this actor. Rate it here.