[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],[],[],[],null,["# Pricing\n\nVertex AI Vision pricing\n========================\n\nThis document explains Vertex AI Vision pricing details.\n\n\nIf you pay in a currency other than USD, the prices listed in your currency on\n[Cloud Platform SKUs](https://cloud.google.com/skus/)\napply.\n\nBilling framework and discounting schedule\n------------------------------------------\n\n^1^ Each image can contain either one product or one tag \n\n^2^ Visual Inspection AI is currently in GA (restricted) - Contact [Google sales](/contact?direct=true) for more info. \n\n### Billing examples\n\n#### Example 1 (with Model)\n\nUnder a PAYG model, customers will only pay for components they use. Let's use\na simple vehicle counting app for illustrating the pricing.\n\nThe components used to build this Car counting app are Streams (Ingress) and\nModel (Vehicle Counting). User will connect one stream to the vehicle counting\nprocessor. At this point no charges will be incurred. Once a user starts\nstreaming video to the app, charges will be incurred.\n\n***App Cost = Streaming costs + Analytic costs***\n\n1. ***Streaming costs*** = **Stream ingressed (GB)** \\* Stream price / GB ($0.0085/GB)\n\n - Total Stream ingressed (GB): Clip size per minute \\* minutes streamed / 1024\n - Clip size: 60 MB / minutes, Minutes of video streamed for processing: 100\n - Total Stream ingressed (GB) = 60 MB / Minute \\* 100 minutes / 1024 MB= 58.6 GB (rounded)\n\n Streaming costs = Stream ingressed (GB) \\* Stream price / GB\n\n Streaming Costs = 5.86 GB \\* $0.0085 / GB = **$0.049**\n2. ***Analytic Costs*** = Minutes of Video processed for streaming \\* Vehicle Counting Processor price / min\n\n Analytic Costs = 100 minutes \\* $0.10 / min = **$10**\n\n***App Cost = Streaming costs + Analytic costs***\n\nTherefore, App Cost = $0.049 + $10 = **$10.049**\n\n#### Example 2 (with Warehouse)\n\nUnder a PAYG model, customers will only pay for components they use. Let's use\na simple warehouse app for illustrating the pricing.\n\nUsers will connect one stream to the warehouse and at some point will also\ndownload clips that they have searched for in the warehouse. Once a user\nstarts streaming video to the warehouse, charges will be incurred as follows\nassuming the video is stored for two months.\n\n**Total Cost** = Month 1 + Month 2\n\n**Month1 Cost** = Streaming costs (Ingress) + Warehouse costs + Streaming costs (Egress)\n\n1. Streaming costs (Ingress) = **Stream ingressed (GB)** \\* Stream price / GB ($0.0085/GB)\n\n Video stream ingressed (GB) : 10 GB\n\n Streaming costs = Stream ingressed (GB) \\* Stream price / GB\n\n Streaming Costs = 10 GB \\* $0.0085 / GB = **$0.085**\n2. Warehouse Costs = Stored Video (GB) \\* Storage costs (per month)\n\n Warehouse Costs = 10 GB \\* $0.020 / GB-mo = \\**$0.2 / month*\n3. Streaming costs (Egress) = **Video Clips egressed (GB)** \\* Stream price / GB ($0.0085/GB)\n\n Video clip egressed: 10 MB or equivalently 0.01 GB\n\n Streaming costs (Egress) = Video Clips egressed (GB) \\* Stream price / GB\n\n Streaming Costs = 0.01 GB \\* $0.0085 / GB = **$0.000085**\n\nMonth 1 Cost = Streaming costs (Ingress) + Warehouse costs + Streaming costs (Egress)\n\n**Month 1 Cost** = $0.085 + $0.2 + $0.000085 = **$0.285085**\n\nSimilarly, Month 2 Cost: Assuming no further streaming (ingress or egress) of\nvideo and clips Month 2 Cost = Streaming costs (Ingress) + Warehouse costs +\nStreaming costs (Egress)\n\n**Month 2 Cost** = $0 + $0.2 + $0 = **$0.2**\n\nTotal Cost = Month 1 cost + Month 2 cost\n\n**Total Cost** = $0.285085 + $0.2 = **$0.485085**\n\n### Vision Warehouse billing examples for batch videos and images\n\nVision Warehouse for batch videos and images has a different pricing\nmodel than for streaming videos. The pricing consists of:\n\n- Storage cost for images charged as $0.02 per GB, per month.\n- Search query cost charged as $3 per 1k request.\n- Index node hour cost for each virtual machine used to build and host index shards.\n\nThe node hour cost is mainly determined by the number of images and the total duration of batch videos.\nIt consists of a **one-time asset analysis cost** (charged by\n[`AnalyzeAsset`](/vision-ai/docs/reference/rest/v1/projects.locations.corpora.assets/analyze) and [`AnalyzeCorpus`](/vision-ai/docs/reference/rest/v1/projects.locations.corpora/analyze))\nto build the index data and a **continuous index serving cost** (charged by\nthe serving time starting at [`DeployIndex`](/vision-ai/docs/reference/rest/v1/projects.locations.indexEndpoints/deployIndex) and ending at\n[`UndeployIndex`](/vision-ai/docs/reference/rest/v1/projects.locations.indexEndpoints/undeployIndex)).\n\nThe one-time index build cost can be estimated as follows:\n\n- Images index build cost in node hours: 0.043 node-hour per 1k images.\n- Batch video index build cost in node hours: 0.292 node-hour per video hour.\n\nTo estimate the 30-day index serving cost, first divide your index data into\nshards. The number of index serving nodes is total index shards times\ntotal index replicas.\n\n- One index shard can hold up to 40 million images or 12,000 video hours.\n- A deployed index has two replicas per shard.\n- Images index serving cost: (# images / # images-per-shard) \\* # replicas-per-shard \\* hourly cost \\* 720 hours.\n- Batch video index serving cost: (# video-hours / # video-hours-per-shard) \\* # replicas-per-shard \\* hourly cost \\* 720 hours.\n\nHere are some examples of Vision Warehouse cost given different asset data sizes.\nAll examples are based on pricing in `us-central1`.\n\n\\* Assume the average image size is 500 KB.\n\nWhat's next\n-----------\n\n- Read the [Vertex AI Vision documentation](/vision-ai/docs).\n- Get started with [Vertex AI Vision](https://console.cloud.google.com/ai/vision-ai/).\n- Try the [Pricing calculator](/products/calculator).\n- Learn about [Vertex AI Vision solutions and use cases](/architecture?text=Vertex AI Vision).\n\n#### Request a custom quote\n\nWith Google Cloud's pay-as-you-go pricing, you only pay for the services you use. Connect with our sales team to get a custom quote for your organization.\n[Contact sales](/contact?direct=true)"]]
