[{"data":1,"prerenderedAt":736},["ShallowReactive",2],{"content:\u002Falternatives\u002Fsightengine":3,"page-dates":699},{"kind":4,"path":5,"locale":6,"title":7,"htmlTitle":8,"description":9,"navTitle":10,"published":11,"updated":11,"alternates":12,"breadcrumbs":13,"indexable":21,"twin":22,"collection":23,"slug":24,"file":25,"hub":19,"data":26},"template","\u002Falternatives\u002Fsightengine","en","A Sightengine alternative with credits for each kind of content.","Sightengine Alternative: Pricing & Limits · Detectivision","Sightengine’s free plan, plans from $29, how it counts operations, its languages and live streams, from its own pages, next to Detectivision’s credits.","Sightengine Alternative: Pricing & Limits","2026-10-17T01:27:51+03:00",[],[14,17,20],{"name":15,"path":16},"Home","\u002F",{"name":18,"path":19},"Solutions","\u002Fsolutions",{"name":10,"path":5},true,"\u002Falternatives\u002Fsightengine.md","alternatives","sightengine","content\u002Fen\u002Falternatives\u002Fsightengine.yml",{"status":27,"published":11,"noindex":28,"author":29,"reviewer":30,"pillar":28,"keywords":31,"competitor":34,"sources":35,"related":227,"relatedExclude":234,"requires":235,"availabilityNotice":28,"reviewAfter":261,"redirectFrom":262,"mergedFrom":263,"featured":28,"aiAssisted":21,"faq":264,"nature":265,"seoTitle":10,"description":9,"hero":266,"sections":276},"published",false,"detectivision","owner",{"primary":32,"intent":33},"sightengine alternative","commercial",[24],[36,42,46,50,54,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158,162,166,171,175,179,183,187,191,195,199,203,207,211,215,219,223],{"id":37,"title":38,"url":39,"publisher":40,"accessed":41},"sightengine-pricing","Sightengine pricing","https:\u002F\u002Fsightengine.com\u002Fpricing","Sightengine","2026-10-17",{"id":43,"title":44,"url":45,"publisher":40,"accessed":41},"sightengine-operation","What is an operation?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fwhat-is-an-operation",{"id":47,"title":48,"url":49,"publisher":40,"accessed":41},"sightengine-free-plan","Can I stay on the free plan forever?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fstay-on-free-plan-forever",{"id":51,"title":52,"url":53,"publisher":40,"accessed":41},"sightengine-free-trial","Do you offer a free trial?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fdo-you-offer-a-free-trial",{"id":55,"title":56,"url":57,"publisher":40,"accessed":41},"sightengine-exceed-plan","What happens if I exceed a plan?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fif-exceed-a-plan",{"id":59,"title":60,"url":61,"publisher":40,"accessed":41},"sightengine-failed-requests","Do failed requests or errors count as an operation?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Ffailed-requests-errors-operation",{"id":63,"title":64,"url":65,"publisher":40,"accessed":41},"sightengine-throttling","Do you throttle requests?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Frequest-throttling",{"id":67,"title":68,"url":69,"publisher":40,"accessed":41},"sightengine-sla","What is your uptime? Do you provide a Service Level Agreement?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fsightengine-uptime-sla",{"id":71,"title":72,"url":73,"publisher":40,"accessed":41},"sightengine-text-languages","What languages does text moderation work with?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Flanguages-for-text-moderation",{"id":75,"title":76,"url":77,"publisher":40,"accessed":41},"sightengine-text-length","What is the maximum text length?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fmaximum-text-length",{"id":79,"title":80,"url":81,"publisher":40,"accessed":41},"sightengine-text-introduction","Text Moderation Introduction","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Ftext-moderation-introduction",{"id":83,"title":84,"url":85,"publisher":40,"accessed":41},"sightengine-text-ml","Text Moderation - ML models","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Ftext-moderation-ml-models",{"id":87,"title":88,"url":89,"publisher":40,"accessed":41},"sightengine-text-rules","Rule-based Text Moderation","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Ftext-moderation-rule-based",{"id":91,"title":92,"url":93,"publisher":40,"accessed":41},"sightengine-models","Visual Moderation models","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Fmodels",{"id":95,"title":96,"url":97,"publisher":40,"accessed":41},"sightengine-nudity","Nudity Detection","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Fadvanced-nudity-detection-model-2.1",{"id":99,"title":100,"url":101,"publisher":40,"accessed":41},"sightengine-violence","Violence Detection","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Fviolence-detection-model",{"id":103,"title":104,"url":105,"publisher":40,"accessed":41},"sightengine-ocr-text","Text Moderation in Images and Videos","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Focr-text-moderation-in-images-2.0",{"id":107,"title":108,"url":109,"publisher":40,"accessed":41},"sightengine-image-types","What image types are supported?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fsupported-image-types",{"id":111,"title":112,"url":113,"publisher":40,"accessed":41},"sightengine-image-dimensions","What are the acceptable \u002F recommended image dimensions?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Facceptable-recommended-image-dimensions",{"id":115,"title":116,"url":117,"publisher":40,"accessed":41},"sightengine-bulk-images","Is it possible to perform bulk image moderation?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fbulk-image-moderation",{"id":119,"title":120,"url":121,"publisher":40,"accessed":41},"sightengine-quickstart","Get started with Image Moderation","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Fgetstarted",{"id":123,"title":124,"url":125,"publisher":40,"accessed":41},"sightengine-video-length","What are the recommended or acceptable video dimensions, resolution and length?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Frecommended-video-dimensions-and-length",{"id":127,"title":128,"url":129,"publisher":40,"accessed":41},"sightengine-video-formats","What video formats and what protocols do you support?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fvideo-formats-protocols-supported",{"id":131,"title":132,"url":133,"publisher":40,"accessed":41},"sightengine-live-streams","Live Stream and Live Video Analysis","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Flive-stream-video-moderation-guide",{"id":135,"title":136,"url":137,"publisher":40,"accessed":41},"sightengine-callback-signature","Callback verification and signature","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Fcallback-signature",{"id":139,"title":140,"url":141,"publisher":40,"accessed":41},"sightengine-audio","Audio Profanity Detection","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Faudio-profanity-model",{"id":143,"title":144,"url":145,"publisher":40,"accessed":41},"sightengine-workflows","Image Moderation Workflows","https:\u002F\u002Fsightengine.com\u002Fdocs\u002Fimage-moderation-workflows",{"id":147,"title":148,"url":149,"publisher":40,"accessed":41},"sightengine-hybrid","What is the difference between Automated and Hybrid Moderation?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fautomated-vs-hybrid-moderation",{"id":151,"title":152,"url":153,"publisher":40,"accessed":41},"sightengine-data-retention","What happens to our images, videos and audio files after processing?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fdata-retention-after-processing",{"id":155,"title":156,"url":157,"publisher":40,"accessed":41},"sightengine-data-location","Where will the images, videos and texts be processed?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fdata-processing-location",{"id":159,"title":160,"url":161,"publisher":40,"accessed":41},"sightengine-security","Is my data safe and secure?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fdata-safety-security",{"id":163,"title":164,"url":165,"publisher":40,"accessed":41},"sightengine-gdpr","How about the General Data Protection Regulation (GDPR)?","https:\u002F\u002Fsightengine.com\u002Ffaq\u002Fgdpr-content-moderation",{"id":167,"title":168,"url":169,"publisher":170,"accessed":41},"detectivision-pricing","Detectivision pricing","https:\u002F\u002Fdetectivision.ai\u002Fpricing","Detectivision",{"id":172,"title":173,"url":174,"publisher":170,"accessed":41},"detectivision-docs-text","Text moderation (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Ftext",{"id":176,"title":177,"url":178,"publisher":170,"accessed":41},"detectivision-docs-image","Image moderation (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fimage",{"id":180,"title":181,"url":182,"publisher":170,"accessed":41},"detectivision-docs-video","Video moderation (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fvideo",{"id":184,"title":185,"url":186,"publisher":170,"accessed":41},"detectivision-docs-live-streams","Live streams (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Flive-streams",{"id":188,"title":189,"url":190,"publisher":170,"accessed":41},"detectivision-docs-tracking","Tracking (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Ftracking",{"id":192,"title":193,"url":194,"publisher":170,"accessed":41},"detectivision-audio-moderation","Audio moderation","https:\u002F\u002Fdetectivision.ai\u002Faudio-moderation",{"id":196,"title":197,"url":198,"publisher":170,"accessed":41},"detectivision-docs-credits","Credits and billing (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fcredits",{"id":200,"title":201,"url":202,"publisher":170,"accessed":41},"detectivision-docs-async","Async requests (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fasync",{"id":204,"title":205,"url":206,"publisher":170,"accessed":41},"detectivision-docs-webhooks","Webhooks (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fwebhooks",{"id":208,"title":209,"url":210,"publisher":170,"accessed":41},"detectivision-docs-actions","Metadata and actions (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Factions",{"id":212,"title":213,"url":214,"publisher":170,"accessed":41},"detectivision-docs-errors","Errors and rate limits (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Ferrors",{"id":216,"title":217,"url":218,"publisher":170,"accessed":41},"detectivision-docs-flags","Flags (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fflags",{"id":220,"title":221,"url":222,"publisher":170,"accessed":41},"detectivision-docs-responses","Responses (docs)","https:\u002F\u002Fdetectivision.ai\u002Fdocs\u002Fresponses",{"id":224,"title":225,"url":226,"publisher":170,"accessed":41},"detectivision-privacy","Privacy policy","https:\u002F\u002Fdetectivision.ai\u002Fprivacy",[228,229,230,231,232,233],"\u002Fguides\u002Fcontent-moderation-apis","\u002Fguides\u002Ffree-content-moderation-apis","\u002Falternatives\u002Fhive","\u002Falternatives\u002Fopenai-moderation-api","\u002Falternatives\u002Famazon-rekognition","\u002Fpricing",[],[236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260],"text_moderation","image_moderation","video_moderation","audio_moderation","live_stream_moderation","text_moderation:hate","text_moderation:insult","text_moderation:profanity","text_moderation:racism","text_moderation:self_harm","text_moderation:sexism","text_moderation:sexual","image_moderation:hate","image_moderation:scam","image_moderation:sexual","image_moderation:violence","video_moderation:nudity","video_moderation:explicit_nudity","video_moderation:sexual_objects","video_moderation:smoking","video_moderation:alcohol","audio_moderation:hate","audio_moderation:insult","audio_moderation:profanity","audio_moderation:sexual","2027-01-15",[],[],[],"article",{"eyebrow":267,"title":268,"lead":272,"more":273},"Sightengine alternative",{"before":269,"em":270,"after":271},"A Sightengine alternative with ","credits for each kind of content",".","Sightengine has a free plan, then Starter from $29 a month for 10,000 operations and Pro from $99 for 40,000. How many operations a check uses depends on the models you pick. Video moderation starts on Starter and live streams on Pro. Detectivision charges in credits for each kind of content: an image costs 1 credit when the result comes later by webhook and 2 when you wait for the answer, whichever flags it checks. Basic is $49 a month with a free trial. The tables show where each fits.",{"label":274,"to":275},"Read the docs","\u002Fdocs\u002Fquickstart",[277,321,352,406,430,454,510,571,581,589,623,634,654,676],{"kind":278,"eyebrow":279,"title":280,"lead":281,"head":282,"rows":286,"note":320},"table","The facts","What Sightengine says about price and plans","From Sightengine’s pricing page, FAQ and documentation, as read on 17 October 2026. Detectivision is not affiliated with Sightengine.",[283,284,285],"What","What Sightengine says","Sightengine page",[287,291,295,298,301,305,309,313,316],[288,289,290],"Free plan","2,000 operations a month, at most 500 a day, at 1 request a second, with “Basic Content Moderation” and “AI Detection”. Sightengine calls it “Perfect for testing the API and building proof-of-concepts” and says “There is no time limit.” It adds that video moderation and some other features “are only available on paid plans”.","Pricing page; free plan FAQ; free trial FAQ",[292,293,294],"Starter","$29 a month for 10,000 operations, or $99 for 50,000. Extra operations cost $0.002 each at 10,000 and $0.0018 each at 50,000. Visual and text moderation, videos up to 50 MB, and “No live-stream support.” For 200,000 or more operations: Contact us.","Pricing page",[296,297,294],"Pro","$99 a month for 40,000 operations, or $399 for 200,000. Extra operations cost $0.002 each at 40,000 and $0.0015 each at 200,000. Adds “Advanced Video & Live-Stream Moderation” (videos up to 500 MB), audio moderation, custom lists, near-duplicate detection and more. For 500,000 or more operations: Contact us.",[299,300,294],"Enterprise","Custom operations, custom models and classes, geo-fencing, enterprise SLAs and a dedicated support engineer.",[302,303,304],"Over the plan","Paid plans keep working: extra operations are charged at the per-operation rate a few days later. The free plan has hard limits of 500 operations a day and 2,000 a month.","Pricing page; exceed a plan FAQ",[306,307,308],"Errors","Requests that return an error (4xx) are not counted: “You won’t get a higher bill because of errors or invalid photos.” Operations may still be counted if you disconnect before a request finishes.","Pricing page; failed requests FAQ",[310,311,312],"Capacity","1 request a second on Free and Starter, 10 on Pro, custom on Enterprise. When Sightengine throttles a request it answers 429 and asks you to retry with exponential back-off.","Pricing page; throttling FAQ",[314,315,294],"Concurrent video jobs","1 on Starter, 5 on Pro, custom on Enterprise.",[317,318,319],"Support","Online docs on Free, email support on Starter, priority support on Pro, a dedicated engineer on Enterprise. Service level agreements are available for Enterprise customers.","Pricing page; SLA FAQ","The prices above include the tiers of the pricing page’s plan sliders. Sightengine can change them, so check its page before you decide.",{"kind":278,"eyebrow":322,"title":323,"lead":324,"head":325,"rows":327},"Operations","How Sightengine counts operations","From Sightengine’s FAQ, as read on 17 October 2026. Sightengine adds that the counts for visual models “may not apply to accounts on legacy models (from before 2025)”.",[326,322],"What you send",[328,331,334,337,340,343,346,349],[329,330],"Most visual model groups: nudity; violence, gore, weapon and self-harm; hate and offensive; restricted content (drugs, alcohol, tobacco, medical, gambling, money); text, QR codes and OCR; destruction and military scenes","1 for each group. Models of the same group count once per request.",[332,333],"AI-generated media detection, deepfake detection","5 each",[335,336],"Face liveness detection","10",[338,339],"Recapture detection","3",[341,342],"Videos, animated GIFs and batch requests","The count is multiplied by the frames analysed. Video moderation analyses 1 frame every 2 seconds by default; Starter and Pro can set 0.5 to 2 frames a second, Enterprise 0.1 to 10.",[344,345],"Text, rule-based","1 for each 1,000 characters. A text of 1,800 characters counts 2 operations.",[347,348],"Text, classification models","1 for each 1,000 characters, for each model. A text of 1,800 characters with the general and self-harm models counts 4 operations.",[350,351],"Audio moderation of a video","1 for each 2 seconds of audio, added to the operations of the visual models on the same video.",{"kind":278,"eyebrow":353,"title":354,"lead":355,"head":356,"rows":357},"What it checks","What Sightengine checks, and what comes back","From Sightengine’s documentation and FAQ, as read on 17 October 2026.",[283,284,285],[358,362,366,370,374,378,382,386,390,394,398,402],[359,360,361],"Image models","You pick the models for each request: nudity (29 classes), violence, gore, weapons, self-harm, drugs, alcohol, tobacco, gambling, money and banknotes, hate and offensive signs, destruction and fire, military and religious content, among others.","Visual moderation models; nudity docs",[363,364,365],"Images in","JPEG, GIF, PNG, WEBP, AVIF, BMP or TIFF, by URL or upload. Up to 12 MB and 64 megapixels. Up to 6 images in one request, 24 MB in total.","Image type, dimension and bulk FAQs",[367,368,369],"Video","A video under 60 seconds in one request, or longer videos asynchronously with callbacks: 30 minutes by default, up to 60 with max_duration. Raw uploads under 50 MB, and the Upload API takes larger files; the pricing page lists videos up to 50 MB on Starter and 500 MB on Pro. MP4, MPG, MKV, AVI, MOV, OGG, M3U8, FLV, WEBM and more.","Video length and format FAQs",[371,372,373],"Live streams","HLS, RTMP and RTMPS, RTSP and RTP, and MPEG-DASH. Results by callback or by polling. On Pro and Enterprise.","Live stream guide; pricing page",[375,376,377],"Audio","Profanity in audio and video files: “Profanity Detection is done in English by default.” Each match has start_ms and end_ms. On Pro and Enterprise.","Audio profanity docs; pricing page",[379,380,381],"Text classification","Classes sexual, discriminatory, insulting, violent, toxic and self-harm, each with a score from 0 to 1, in English, French, Italian, Portuguese, Spanish, Russian and Turkish. “Other languages are available upon request.”","Text classification docs",[383,384,385],"Text rules","Pattern matching that returns the flagged words, in 18 languages: profanity with an intensity, personal information, links, extremism, weapons, drugs, self-harm, violence, spam, and your own lists.","Rule-based text docs; text languages FAQ",[387,388,389],"Text length","Up to 10,000 characters; usernames up to 128.","Text length FAQ",[391,392,393],"Workflows","Rules built in the dashboard, with accept or reject as the action. In a hybrid workflow some decisions “could be reviewed \u002F confirmed through your human moderation platform”.","Workflows docs; hybrid FAQ",[395,396,397],"Callbacks","Sightengine uses callbacks for videos and live streams. Callbacks to the account-level callback URL can be signed with a Sightengine-Signature header; callbacks to a callback_url sent in the request are not signed.","Callback signature docs",[399,400,401],"Data","“By default, images, videos and audios are deleted after processing.” Sightengine keeps a file when you use a feature that stores it, such as hybrid review, the Feedback API, the Upload API or near-duplicate lists. Processing may happen in the EU, Canada or the US, and Enterprise plans can choose the region. Sightengine says it is in compliance with the GDPR and offers a data processing addendum.","Data retention, location and GDPR FAQs",[403,404,405],"Other products","The pricing page lists AI-generated image and video detection and deepfake detection on Starter, and face liveness, recapture detection, age estimation, AI music detection and near-duplicate detection on Pro. Sightengine also has AI-generated speech detection, which its FAQ says is only on paid plans.","Pricing page; free trial FAQ",{"kind":407,"eyebrow":408,"title":409,"lead":410,"items":411},"list","Stay with Sightengine","When Sightengine fits","Sightengine’s own pages show what it offers. These are the cases where that list decides it.",[412,415,418,421,424,427],{"name":413,"text":414},"You want a free plan with no end date","Free gives 2,000 operations a month, at most 500 a day, at 1 request a second, and Sightengine says there is no time limit. It includes basic content moderation and AI detection.",{"name":416,"text":417},"You pick from a large library of image models","Sightengine lists models for nudity in 29 classes, violence, gore, weapons, drugs, alcohol, tobacco, gambling, money, hate signs, destruction, military and religious content, and you choose the ones you need for each request.",{"name":419,"text":420},"You need AI-generated media or identity checks","Sightengine lists AI-generated image and video detection and deepfake detection on Starter, and face liveness, age estimation and AI music detection on Pro.",{"name":422,"text":423},"You write text rules in many languages","Its rule-based text moderation covers 18 languages, returns the flagged words with an intensity for profanity, and takes lists of your own.",{"name":425,"text":426},"You keep lists of images and videos","Pro allows 10 custom lists. A list for image search or near-duplicate detection holds up to 1,000,000 images or 1,000 videos.",{"name":428,"text":429},"You need enterprise terms","Enterprise plans can choose where data is processed, and come with SAML single sign-on, service level agreements and a dedicated support engineer.",{"kind":407,"eyebrow":170,"title":431,"lead":432,"items":433},"When Detectivision fits","What Detectivision documents, point by point. The tables show Sightengine’s side of each.",[434,438,442,446,450],{"name":435,"text":436,"to":437},"Text checks in ten languages","Detectivision documents its text checks for English, Spanish, Portuguese, French, German, Italian, Turkish, Arabic, Russian and Hindi, with no language to set in the request.","\u002Fdocs\u002Ftext",{"name":439,"text":440,"to":441},"An image costs the same, whichever flags","An image costs 1 credit when the result comes later by webhook and 2 when you wait for the answer, whether it is checked for one flag or for all of them.","\u002Fdocs\u002Fcredits",{"name":443,"text":444,"to":445},"Speech checks in ten languages","Detectivision’s audio moderation understands the same ten languages as its text moderation. In capture mode, the default, each finding comes with its start and end in seconds.","\u002Faudio-moderation",{"name":447,"text":448,"to":449},"Video, audio and live streams in one credit system","Every plan has video credits, 300 on Basic. Pro adds 2,000 audio and 1,000 live stream credits. A live session can be set up to 30 frames a second and keeps flagged moments with their picture.","\u002Flive-stream-moderation",{"name":451,"text":452,"to":453},"A review screen with your own actions","A moderator opens a request in the dashboard’s Logs and takes one of your actions, such as Approve or Ban. Your system gets each one as a moderation.action webhook and carries it out.","\u002Fdocs\u002Factions",{"kind":278,"eyebrow":455,"title":456,"lead":457,"head":458,"rows":459,"note":509},"Side by side","Sightengine and Detectivision, row by row","Sightengine from its pricing page, FAQ and docs, as read on 17 October 2026. Detectivision from its docs and pricing page.",[283,40,170],[460,464,468,472,476,480,484,487,490,493,497,501,505],[461,462,463],"Free start","A free plan with no time limit: 2,000 operations a month, at most 500 a day.","A free trial of the Basic plan.",[465,466,467],"Paid plans","Starter $29 for 10,000 operations or $99 for 50,000; Pro $99 for 40,000 or $399 for 200,000; Enterprise custom.","Basic $49, Pro $199 and Enterprise $999 a month. Each kind of content has its own credits: Basic has 10,000 text, 10,000 image and 300 video credits, and audio and live stream credits start on Pro.",[469,470,471],"Unit","Operations, counted by model group; video multiplied by the frames analysed; text per 1,000 characters.","Credits for each kind: a text per started 2,500 characters, an image 1, a video per started 60 frames checked. An answer given at once costs twice the webhook price.",[473,474,475],"An image checked for nudity only","1 operation, so Starter’s 10,000 operations cover 10,000 images.","1 credit by webhook and 2 at once, so Basic’s 10,000 image credits cover 10,000 images by webhook, or half that when answered at once.",[477,478,479],"An image checked for nudity, violence and offensive signs","3 operations, one for each model group, so Starter’s 10,000 operations cover 3,333 images.","1 credit by webhook and 2 at once, whichever flags it checks, so Basic’s 10,000 image credits cover 10,000 images by webhook, or half that when answered at once.",[481,482,483],"A text of 1,800 characters","Rule-based: 2 operations. Classification with the general and self-harm models: 4 operations.","1 credit by webhook and 2 at once, for every text flag.",[367,485,486],"Starter and above. Starter takes videos up to 50 MB, one job at a time; Pro up to 500 MB, five at a time. One frame every 2 seconds by default.","Every plan has video credits. A video URL (MP4, MOV, WebM, MKV or AVI, up to 100 MB), 0.5 to 10 frames a second, up to 300 frames in one check.",[371,488,489],"Pro and Enterprise. HLS, RTMP and RTMPS, RTSP and RTP, MPEG-DASH; results by callback or polling.","Live stream credits come with Pro and Enterprise. Stream links over RTSP, RTMP, HLS, HTTP or SRT, or frames from your camera.",[375,491,492],"Pro and Enterprise. Profanity in English by default; Sightengine says to reach out about other languages.","Audio credits come with Pro and Enterprise. Ten languages.",[494,495,496],"Text languages","Classification: English, French, Italian, Portuguese, Spanish, Russian and Turkish. Rule-based: 18 languages.","English, Spanish, Portuguese, French, German, Italian, Turkish, Arabic, Russian and Hindi.",[498,499,500],"Review screen","Workflows with accept or reject; a hybrid workflow passes some decisions to your human moderation platform.","The dashboard’s Logs, your own actions and a moderation.action webhook.",[502,503,504],"Rate limit","1 request a second on Free and Starter, 10 on Pro; 429 when throttled.","1,200 calls a minute per API key; 429 with Retry-After; up to 50 async checks waiting per account.",[506,507,508],"Data kept","Images, videos and audio are deleted after processing by default, unless you use a feature that stores them, such as hybrid review or the Upload API.","An image itself is downloaded, checked and not stored. Requests, results and censored copies stay in your account’s history while the account is open, unless you delete them sooner.","Units differ: Sightengine counts operations, Detectivision credits. The examples count images and texts, not dollars: Starter is $29 a month and Basic $49. Work out a busy month on both price pages before you choose.",{"kind":278,"eyebrow":511,"title":512,"lead":513,"head":514,"rows":518,"note":570},"Model by model","Where Sightengine’s models go","Sightengine’s models and classes as its docs list them on 17 October 2026, next to the Detectivision flags that cover the same ground. GET \u002Fapi\u002Fv1\u002Fflags lists the flags of your account. A flag keeps its key.",[515,516,517],"Sightengine model or class","Detectivision flag","Note",[519,523,527,530,534,538,542,546,550,554,558,562,566],[520,521,522],"nudity-2.1: sexual_activity, sexual_display, erotica and the suggestive classes","sexual (images); nudity, explicit_nudity, sexual_objects (video and live streams)","Sightengine returns 29 classes, among them bikini, lingerie and male_underwear. Detectivision’s sexual flag covers nudity and sexual content in the whole image.",[524,525,526],"violence","violence (images)","Sightengine separates physical violence, firearm threats and combat sports into classes. Detectivision’s violence flag covers violence shown in the picture, such as fights, blood or injuries.",[528,525,529],"gore-2.0","Blood, wounds and injuries.",[531,532,533],"offensive-2.0: hate and offensive signs","hate (images)","Detectivision’s hate flag covers hate symbols, and hateful text or drawings aimed at a group of people.",[535,536,537],"tobacco, alcohol","smoking, alcohol (video); smoking (live streams)","In capture mode, the default, each finding comes with its second and its box.",[539,540,541],"text-content-2.0: personal information such as phone numbers and e-mail addresses in images","scam (images)","Contact details written on a picture raise scam, as do fake giveaways and fake payment screens.",[543,544,545],"Text classification: sexual","sexual (text)","Sexual language and sexual harassment.",[547,548,549],"Text classification: discriminatory","hate, racism, sexism (text)","Three flags, so your rules can treat them apart.",[551,552,553],"Text classification: insulting","insult (text)","The insult flag covers attacks on one person: name-calling, belittling, cursing at someone.",[555,556,557],"Text classification: toxic","flagged","flagged is true when any flag you asked for was raised, and each flag has its own confidence.",[559,560,561],"Text classification: self-harm","self_harm (text)","One flag for talk of suicide or self-harm.",[563,564,565],"Rule-based profanity, with an intensity","profanity (text; the Basic plan has this flag)","Swear words, aimed at someone or not. An attack on a person has its own flag, insult.",[567,568,569],"audio-profanity: sexual, inappropriate, discriminatory, insult","profanity, hate, insult, sexual (audio)","In capture mode, the default, each finding comes with its start and end in seconds.","The table lists the models and classes that have a matching flag. Sightengine’s model pages list more; compare them with the list your account gets from GET \u002Fapi\u002Fv1\u002Fflags before you move.",{"kind":572,"eyebrow":573,"title":574,"blocks":575,"note":580},"code","Before and after","An image check, both ways",[576,578],{"label":40,"code":577},"curl -X GET -G 'https:\u002F\u002Fapi.sightengine.com\u002F1.0\u002Fcheck.json' \\\n  -d 'models=nudity-2.1,violence,offensive-2.0' \\\n  -d 'api_user={api_user}&api_secret={api_secret}' \\\n  --data-urlencode 'url=https:\u002F\u002Fexample.com\u002Fphoto.jpg'",{"label":170,"code":579},"curl https:\u002F\u002Fapi.detectivision.ai\u002Fapi\u002Fv1\u002Fmoderation \\\n  -H \"Api-Key: $DETECTIVISION_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"type\": \"image_moderation\",\n    \"input\": \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\",\n    \"mode\": \"detect\",\n    \"flags\": [\"sexual\", \"violence\", \"hate\"]\n  }'","Sightengine takes the models in models and an API user and secret pair in the request. Detectivision takes the flags in flags and its key in the Api-Key header. The three Sightengine models are three operations. The Detectivision check as written is answered at once and costs 2 credits; with \"async\": true it costs 1.",{"kind":572,"eyebrow":573,"title":582,"blocks":583,"note":588},"A text check, both ways",[584,586],{"label":40,"code":585},"curl -X POST 'https:\u002F\u002Fapi.sightengine.com\u002F1.0\u002Ftext\u002Fcheck.json' \\\n  -F 'text=You are such an idiot, just shut up.' \\\n  -F 'lang=en' \\\n  -F 'models=general,self-harm' \\\n  -F 'mode=ml' \\\n  -F 'api_user={api_user}' \\\n  -F 'api_secret={api_secret}'",{"label":170,"code":587},"curl https:\u002F\u002Fapi.detectivision.ai\u002Fapi\u002Fv1\u002Fmoderation \\\n  -H \"Api-Key: $DETECTIVISION_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"type\": \"text_moderation\",\n    \"input\": \"You are such an idiot, just shut up.\",\n    \"mode\": \"detect\",\n    \"flags\": [\"insult\", \"hate\", \"sexual\", \"self_harm\"]\n  }'","Sightengine asks for the language in lang and the models in models. Detectivision reads the text in input with no language to set, and checks the flags you name; without flags, every text flag of your account.",{"kind":278,"eyebrow":590,"title":591,"lead":592,"head":593,"rows":594},"Reading the answer","What comes back","The fields Sightengine’s docs describe, next to the fields of a Detectivision answer (docs: Responses).",[283,40,170],[595,599,603,607,611,615,619],[596,597,598],"Verdict","Scores for each model you ask for. A workflow adds a decision: accept or reject.","flagged, true when any flag you asked for was raised.",[600,601,602],"Scores","A score from 0 to 1 for each class of each model; the nudity model has 29 classes.","flags: only the flags raised, each with a confidence from 0 to 1, from 0.5 up by default.",[604,605,606],"Cost in the answer","request.operations: the operations the request used.","usage.charged and usage.remaining, in credits.",[608,609,610],"Where","Video: per frame. Audio: start_ms and end_ms for each match. Rule-based text: the flagged words.","In capture and censor mode: for video and live streams the second, the frame and the box of each finding, for audio the start and end in seconds. Text and images get one result for the whole input.",[612,613,614],"Coverage","A text classification answer lists the classes available for the models you asked for.","checked and unchecked: what was looked for and what could not be; a partial result is free.",[616,617,618],"Request id","request.id, such as req_…, and media.id, such as med_….","id, an integer.",[620,621,622],"Results later","A callback to the account-level URL set in the dashboard (signed) or to a callback_url sent in the request (not signed), or polling with the media id.","Webhooks, signed, with your metadata, or reading the request back by its id.",{"kind":572,"eyebrow":624,"title":625,"blocks":626,"note":633},"Detectivision’s answer","At once, or later by webhook",[627,630],{"label":628,"code":629},"Example response (format from the API reference; values illustrative)","{\n  \"id\": 4120,\n  \"type\": \"image_moderation\",\n  \"mode\": \"detect\",\n  \"status\": \"completed\",\n  \"flagged\": true,\n  \"flags\": [{ \"flag\": \"violence\", \"confidence\": 0.87 }],\n  \"checked\": [\"hate\", \"scam\", \"sexual\", \"violence\"],\n  \"unchecked\": [],\n  \"tookMs\": 1240,\n  \"usage\": { \"charged\": 2, \"remaining\": 5126 }\n}",{"label":631,"code":632},"The same check, async","curl https:\u002F\u002Fapi.detectivision.ai\u002Fapi\u002Fv1\u002Fmoderation \\\n  -H \"Api-Key: $DETECTIVISION_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"type\": \"image_moderation\",\n    \"input\": \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\",\n    \"mode\": \"detect\",\n    \"async\": true,\n    \"metadata\": { \"listingId\": \"l_7731\" }\n  }'","Sent async, the same check costs half: the API answers 202 with the request’s id, and the result comes by webhook with your metadata.",{"kind":407,"eyebrow":635,"title":636,"items":637,"numbered":21},"Moving over","Moving from Sightengine in five steps",[638,641,645,648,651],{"name":639,"text":640},"List the models and rules you use","Write down the models in your requests, the classes you act on, and the rules of any workflow.",{"name":642,"text":643,"to":644},"Map them to flags","Use the table above, then ask GET \u002Fapi\u002Fv1\u002Fflags for the flags your account has. A flag keeps its key.","\u002Fdocs\u002Fflags",{"name":646,"text":647,"to":441},"Recount your volume in credits","A text costs 1 credit per started 2,500 characters and an image 1 credit by webhook, whichever flags it checks. An answer given at once costs twice that. Count your busiest month, not an average one.",{"name":649,"text":650,"to":453},"Set up your own actions","Act on flagged and the flags raised. Define actions such as Approve or Ban in the dashboard’s Logs, and your system gets each one as a moderation.action webhook.",{"name":652,"text":653},"Send the same content to both","Run a sample of your own messages and images through Sightengine and Detectivision, as separate calls, and compare the answers before you switch.",{"kind":407,"eyebrow":655,"items":656},"Related",[657,660,663,666,669,672],{"name":658,"text":659,"to":228},"Content moderation APIs compared","What each API checks, its languages and its published prices.",{"name":661,"text":662,"to":229},"Free content moderation APIs","What each vendor gives for free, and its limits.",{"name":664,"text":665,"to":230},"Hive alternative","Its prices, its self-serve limit and its contracts, set against credits.",{"name":667,"text":668,"to":231},"OpenAI Moderation API","Its limits, and when a paid API is worth it.",{"name":670,"text":671,"to":232},"Amazon Rekognition alternative","Rekognition’s moderation labels, mapped one by one.",{"name":673,"text":674,"to":675},"Video moderation","Each finding with its second and its box, a censored copy and tracking.","\u002Fvideo-moderation",{"kind":677,"eyebrow":678,"title":679,"items":680},"faq","Questions","Frequently asked",[681,684,687,690,693,696],{"q":682,"a":683},"Does Sightengine have a free plan?","Yes. Sightengine’s pricing page lists 2,000 operations a month, at most 500 a day, at 1 request a second, and its FAQ says there is no time limit. Its free trial FAQ says video moderation and some other features are only available on paid plans. Detectivision has a free trial on its Basic plan, with 10,000 text, 10,000 image and 300 video credits.",{"q":685,"a":686},"What is a Sightengine operation?","The unit its plans are measured in. Models of the same group count once per request: the nudity models are 1 operation, the violence, gore, weapon and self-harm models together 1, hate and offensive 1, AI-generated media detection 5. Video multiplies the count by the frames analysed, one every 2 seconds by default. Text counts 1 operation per 1,000 characters, for each classification model.",{"q":688,"a":689},"Does Sightengine moderate live streams?","Yes, on its Pro and Enterprise plans; Starter is listed with “No live-stream support.” Sightengine takes HLS, RTMP and RTMPS, RTSP and RTP, and MPEG-DASH streams, and reports by callback or polling. Detectivision runs live sessions on a stream link (RTSP, RTMP, HLS, HTTP or SRT) or on frames you send from a camera, with live stream credits on the Pro and Enterprise plans.",{"q":691,"a":692},"Which languages does Sightengine text moderation support?","Its text classification models list English, French, Italian, Portuguese, Spanish, Russian and Turkish. Its rule-based moderation lists 18 languages, among them Chinese, Danish, Dutch, Korean and Polish. Sightengine says other languages are available upon request. Detectivision documents its text checks for English, Spanish, Portuguese, French, German, Italian, Turkish, Arabic, Russian and Hindi, though a flag may cover only some of them.",{"q":694,"a":695},"What happens if I go over my Sightengine plan?","On a paid plan, Sightengine keeps serving requests and charges the extra operations at the per-operation rate a few days later: $0.002 each on Starter at 10,000 and on Pro at 40,000, less on the larger tiers. The free plan has hard limits of 500 operations a day and 2,000 a month. On Detectivision, a check of a kind with no credits left answers insufficient_quota and costs nothing; add credits to continue.",{"q":697,"a":698},"Can I use Sightengine and Detectivision together?","Yes. They are separate HTTP calls, so you can send the same content to both, for example to compare results on your own messages and images before you choose. Each Detectivision check uses credits, and Sightengine counts operations.",{"\u002F":700,"\u002Ftr":703,"\u002Ftext-moderation":704,"\u002Fimage-moderation":706,"\u002Fvideo-moderation":707,"\u002Faudio-moderation":708,"\u002Flive-stream-moderation":710,"\u002Fnsfw-detection-api":711,"\u002Fhate-speech-detection-api":713,"\u002Ftoxicity-detection-api":714,"\u002Fviolence-detection-api":715,"\u002Fself-harm-detection-api":717,"\u002Fturkish-offensive-language-detection-api":718,"\u002Fuse-cases\u002Fdating-apps":719,"\u002Fuse-cases\u002Fmarketplaces":720,"\u002Fuse-cases\u002Fonline-communities":722,"\u002Fuse-cases\u002Fgaming":723,"\u002Falternatives\u002Fperspective-api":724,"\u002Falternatives\u002Fazure-content-moderator":725,"\u002Fpricing":726,"\u002Fmanifesto":727,"\u002Fprivacy":730,"\u002Fterms":733,"\u002Fcookies":734},{"published":701,"modified":702},"2026-10-14T12:53:52+03:00","2026-10-17T02:29:05+03:00",{"published":701,"modified":702},{"published":705,"modified":702},"2026-10-08T17:33:40+03:00",{"published":705,"modified":702},{"published":705,"modified":702},{"published":705,"modified":709},"2026-10-16T18:51:05+03:00",{"published":705,"modified":705},{"published":712,"modified":709},"2026-10-09T01:21:35+03:00",{"published":712,"modified":709},{"published":712,"modified":709},{"published":712,"modified":716},"2026-10-16T10:03:00+03:00",{"published":712,"modified":709},{"published":712,"modified":702},{"published":712,"modified":709},{"published":712,"modified":721},"2026-10-16T18:26:12+03:00",{"published":712,"modified":709},{"published":712,"modified":709},{"published":712,"modified":709},{"published":712,"modified":709},{"published":705,"modified":702},{"published":728,"modified":729},"2026-09-28T16:37:00+03:00","2026-10-16T10:06:42+03:00",{"published":731,"modified":732},"2026-10-04T16:45:35+03:00","2026-10-16T17:37:06+03:00",{"published":731,"modified":731},{"published":731,"modified":735},"2026-10-15T23:48:27+03:00",1792193478127]