AI Applications pricing
Prices are listed in US Dollars (USD).
Pricing for listed Generally Available (GA) functionality is invoked on Sep 1, 2023.
AI Applications lets developers, even those with limited machine learning skills, tap into the power of Google's foundation large language models, search expertise, and conversational AI technologies to create enterprise-grade generative AI applications
Vertex AI Search pricing
AI Applications provides the ability to quickly build Search Engines for website, unstructured data, structured data to retrieve information and generate grounded answers. You can read more about the features available in Vertex AI Search .
Pricing for Vertex AI Search GA functionality
Free Trial: You'll have access to 10,000 queries per account, per month at no cost to explore Vertex AI Search without an initial investment. Excludes Advanced Generative Answers.
includes Core Generative Answers (AI Mode)
(can be added to both Standard Edition and Enterprise Edition)
Search Enterprise Edition – Unstructured Search + Structured Search + Website Search capabilities
Vertex AI Search Enterprise Edition includes core Generative Answers (AI Mode). Provide answers, summaries and follow ups at no additional cost. Note: Core Generative Answers do not include suggested follow ups, complex query handling, long query handling, and multimodality. Advanced Generative Answers includes advanced features such as suggested follow ups, complex query handling, and multimodality. Query: Billing metered per individual Request or Query Input A request or query is defined as any API call to Enterprise Search, whether direct with API usage or indirect with integration or console usage. For example, when a user asks a natural language question, and the search engine responds that is one query. Advanced Generative Answers (AI Mode) is added to a Query to augment the processing to use a Generative AI feature,
Advanced Generative Answers (AI Mode) can be used interchangeably with either Search Standard Edition or Search Enterprise Edition.
Example: executing a Search Enterprise query with a multimodal request = 1 Search Enterprise query + 1 Advanced Generative Answers (AI Mode) query
Pricing Example for Vertex AI Search GA functionality
Example of unstructured data : Document Search
Assumption:
- 10M Standard Edition queries annually
- 10M Enterprise Edition queries with 2M Advanced Generative Answers (AI Mode) queries annually
- 100K documents @ ~1mb each
Each query added to either Standard or Enterprise query
Index storage pricing
Pricing for AI Applications Index Data Storage
Vertex AI Search for Healthcare pricing
Vertex AI Search for Healthcare provides the ability to quickly build medically tuned Search Engines over healthcare data.
Vertex AI Search for Healthcare includes some features in Preview such as GenAI answers, streaming updates to the index, and others. These features may be priced differently than the current listed price when they are released to General Availability.
Pricing Example for Healthcare Search
Assumption:
-
1,000,000 healthcare search requests a month
-
1,000 GiB of healthcare data indexed
| SKU Volume | Rate | Total List Price |
|---|---|---|
|
1,000,000 searches
|
$20/1000 | $20,000 |
|
1,000 GiB
|
$5/GiB | $5,000 |
Vertex AI Search for Media pricing
Vertex AI Search for Media enables you to provide highly relevant video results, leveraging Google's query and contextual understanding to improve discovery across your media site.
| AI Applications: Data Index | $5.00 / GB per month |
|---|---|
| Vertex AI Search: Media Search API Request Count | $2.00 / 1,000 query |
Vertex AI Search for Media Recommendations pricing
The only Media Recommendations operations that incur charges are training, tuning, or requesting predictions by calling the recommend method. There's no charge for importing or managing user events or document information.
Training (per node per hour) costs are charged on a daily basis if your model is actively training or if you have submitted a request to resume training. After you pause or delete a model, you are no longer charged. See the documentation for managing training .
Tuning (per node per hour) costs for active models are charged after the tune completes successfully. You are only charged for an incomplete tune if you pause or delete a model during an ongoing tune. In this case, you are then charged for the node hours that were consumed before the model tuning stopped. See the documentation for managing tuning .
| Predictions requests per month | $0.20 / 1,000 predictions |
|---|---|
| Training and Tuning | $2.50 per node per hour |
Pricing Example for Media Recommendations
Assumption:
-
1,000,000,000 prediction requests a month
-
Trains a single model per day, which automatically retrains once per day
-
Amounts to about 500 node hours of model training and 100 hours of model tuning per month
Google Cloud Observability charges
Media Recommendations logs an error to Google Cloud Observability for each API request that results in an error, such as a user event request that contains malformed JSON, or a document import request with a negative price. Media Recommendations also logs an error for every prediction request with a document that is not in the imported datastore.
Google Cloud Observability charges by the GiB of logs stored and for retention beyond the default retention period. For details about the free allotment and data retention, see the Google Cloud Observability pricing page .
The size of the logging data depends on the size of your JSON payload, but a GiB would be approximately 200,000 Media Recommendations errors.
Grounded Generation API pricing
The Grounded Generation API enables you to create generative answers to your prompts using information on Google Search or your own data.
Example #1: Grounding on Vertex AI Search and inline grounding facts
The user uses Vertex AI Search and additional grounding facts to generate grounded answers. Each input prompt is 2,500 characters (including inline grounding facts) and each output prompt 200 characters long. The user has selected Gemini 1.5 Flash.
| Volume per request | Price per 1,000 requests | |
|---|---|---|
|
Input prompt
|
2,500 characters | 1,000 requests * $0.000125 per 1,000 characters * 2,500 characters per request = $0.3125 per 1,000 requests |
|
Output
|
200 characters | 1,000 requests * $0.000375 per 1,000 characters * 2 characters per request = $0.075 per 1,000 requests |
|
Grounded Generation for grounding on your own retrieved data
|
1 request | $2.50 per 1,000 requests |
|
Data Retrieval: Vertex AI Search (Enterprise edition)
|
1 request | $4.00 per 1,000 requests |
| |
Total: $6.8875 per 1,000 requests |
Example #2: Grounding on Google Search
The user uses Google Search to generate grounded answers. Each input prompt is 500 characters and each output prompt 200 characters long. The user has selected Gemini 1.5 Flash.
| Volume per request | Price per 1,000 requests | |
|---|---|---|
|
Input prompt
|
500 characters | 1,000 requests * $0.000125 per 1,000 characters * 500 characters per request = $0.0625 per 1,000 requests |
|
Output
|
200 characters | 1,000 requests * $0.000375 per 1,000 characters * 200 characters per request = $0.075 per 1,000 requests |
|
Grounded Generation for grounding on Google Search
|
1 request | $35.00 per 1,000 requests |
| |
Total: $35.1375 per 1,000 requests |
Check Grounding API pricing
Check grounding provides the ability to determine how grounded a piece of text (the answer candidate) is in a given set of reference texts (the facts).
Document AI feature pricing
For full pricing information of all Document AI features, refer to the Document AI pricing page .
For the Document AI features integrated with and billed through Vertex AI Search, refer to the tables below.
Digitize text
| Processor | 1 - 5,000,000 pages/month * | 5,000,001+ pages/month |
|---|---|---|
|
Enterprise Document OCR Processor
|
$1.50 per 1,000 pages | $0.60 per 1,000 pages |
Extract structures and entities from documents
*The size of a page depends on the file format.:
-
Images (JPEG/JPG, PNG, BMP, HEIF): Each image = 1 page
-
PDF: Each page in the PDF = 1 page
-
TIFF: Each image in the TIFF = 1 page
-
Word (DOCX): Up to 3,000 characters = 1 page
-
Excel (XLSX): Each tab = 1 page
-
Powerpoint (PPTX): Each slide = 1 page
-
HTML: Up to 3,000 characters = 1 page
-
Parsed Documents: Up to 3,000 characters = 1 page
Ranking API pricing
The ranking API takes a list of documents and reranks those documents based on how relevant the documents are to a query.
Compared to embeddings, which look only at the semantic similarity of a document and a query, the ranking API can give you precise scores for how well a document answers a given query.
The ranking API can be used to improve the quality of search results after retrieving an initial set of candidate documents.
Rank documents
A query is defined as having up to 100 documents, though a user can specify more than 100 documents per query. In the case where more than 100 documents are specified, pricing increases by 1 for every multiple of 100 documents.
For example:
-
132 documents to rank = 2 queries
-
200 documents to rank = 2 queries
-
399 documents to rank = 4 queries
-
401 documents to rank = 5 queries
What's next
- Read the AI Applications documentation .
- Try the Pricing calculator .
