Vertex AI Agent Builder pricing
Prices are listed in US Dollars (USD).
Pricing for listed Generally Available (GA) functionality is invoked on Sep 1, 2023.
Vertex AI Agent Builder 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
Trial Credits & Support
$ 1,000 in FREE trial credits are awarded for use with Vertex AI Agent Builder. These credits are valid for 1 year period beginning from account signup with Vertex AI Agent Builder starting on Jul 18, 2023.
Questions about GA functionality or Preview features packaging and pricing?
Contact your Google Cloud sales team for more information.
Vertex AI Agents pricing
Vertex AI Agent Builder provides the ability to quickly build virtual agents (chatbots) that generate answers based on the content (website, documents) you include in data stores. Using Vertex AI Agents, you can create a new Dialogflow CX virtual agent OR add the feature to an existing Dialogflow CX virtual agent.
To add additional generative AI capabilities to your Dialogflow CX virtual agents, you can leverage Generative Fallbacks which use a large language model (LLM) to gracefully handle scenarios where there is no match to the user's intent. Generators empower your bot builders to inject generative actions anywhere in your conversational flow — this could be to summarize a conversation, personalize an interaction, or chain multiple LLM calls together to create an entire generative workflow.
Pricing for Vertex AI Agents GA functionality
Vertex AI Agents Chat* | $12.00 / 1,000 query** |
---|---|
Vertex AI Agents Voice* | $0.002 / second† |
Dialogflow CX Chat***(Standard, non-Generative AI capabilities for Chat) | $7.00 / 1,000 query** |
Dialogflow CX Voice***(Standard, non-Generative AI capabilities for Voice) | $0.001 / second† |
*All generative AI features - Data store agents, Generative Fallbacks, Generators, and Agent apps are covered by Vertex AI Agents Chat and Voice SKU pricing. If you use multiple types of Generative AI features in a single request, you will be charged separately for each feature as per its usage. *Customers can combine Dialogflow CX (non-generative) and Vertex AI Agents (generative) queries/seconds in the same agent or flow, and will automatically be charged for the actual usage of each feature set. This allows you to selectively leverage generative AI where applicable and only pay for what you actually use. **Request (or Query): Billing metered per individual Request or Query. A request or query is defined as any API call to the Dialogflow service or Vertex AI Agents service, whether direct with API usage or indirect with integration or console usage. For example, a user asking a virtual agent (chatbot) a question and the chatbot responding is 1 Request. A user interaction with the chatbot can be made up of multiple Requests to accomplish a task. † Includes speech recognition, speech-to-text (STT), speech synthesis, text-to-speech (TTS), and telephony. The total billed audio processing duration is independent of any no-charge, non-audio processing (API latency, webhook processing, and so on) which may occur before, during, or after audio processing. * Dialogflow CX Chat and Dialogflow CX Voice are not eligible for the $1,000 FREE trial credits. Dialogflow CX has an additional trial credits program that can be combined with this Vertex AI Agent Builder FREE trial credit program. See additional definitions of Dialogflow CX metering here. |
Pricing Example for Vertex AI Agents GA functionality
Example of mixing intent-based and generative answers: Customer Support on Website
- Intent-based, deterministic flows are used for some customer-specific questions (Billing, Payment)
- Generative answers used to handle questions where no intent defined but answer is on the website
Assumptions:
- 100M annual website visits
- 5% of visitors use the chatbot, 3 queries per use, 50% generative, 50% intent-based
SKU Volume | Rate | Total List Price |
---|---|---|
Dialogflow CX Chat (intent-based) | ||
7.5M annual 100M*5% use*3 queries*50% intent-based |
* $7.00 / 1k queries = | $52,500 |
Dialogflow CX Enterprise Chat (generative) | ||
7.5M annual 100M*5% use*3 queries*50% generative |
* $12.00 / 1k queries = | $90,000 |
Data Indexed | ||
50GB annual 10GB free so 40GB used in price calc |
* $5.00 / GB * 12 month = | $2,400 |
Vertex AI Search pricing
Vertex AI Agent Builder 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
Search Standard Edition | $2.00 / 1,000 query | |
---|---|---|
Search Enterprise Edition | $4.00 / 1,000 query | |
LLM Add-On (can be added to both Standard Edition and Enterprise Edition) |
Basic | +$4.00 / 1,000 user input query |
Advanced | +$10.00 / 1,000 user input query | |
Search Standard Edition – Unstructured Search capabilities Search Enterprise Edition – Unstructured Search + Website Search capabilities Basic LLM Add-On – Provide answers and summaries to simple single/multi-turn queries, with ability to process simple queries, compound queries , long queries, multi-turn queries,supporting models including TextBison, Gemini 1.0 Series, Gemini 1.5 Flash (Link) Advanced LLM Add-On - Provide answers and summaries to multi-hop queries (A query which contains two or more nested questions, the answer to one clarifying the next question which must be answered), supporting models including TextBison, Gemini 1.0 Series, Gemini 1.5 Flash (Link) . We charge by # of user input queries, not by # of hops Private Preview – Structured Search + New GenAI capabilities (contact sales for latest features) 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. LLM Add-On is added to a Query to augment the processing to use a Generative AI feature, LLM Add-On can be used interchangeably with either Search Standard Edition or Search Enterprise Edition. Example: executing a Search Enterprise query with a Summarization request = 1 Search Enterprise query + 1 LLM Add-On 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 10M LLM Summarization queries annually
- 100K documents @ ~1mb each
SKU Volume | Rate | Total List Price |
---|---|---|
Standard Search | ||
10M annual | * $2.00 / 1k queries = | $20,000 |
Search Enterprise | ||
10M annual | * $4.00 / 1k queries = | $40,000 |
Basic Search LLM Add-On Each query added to either Standard or Enterprise query |
||
10M annual | * +$4.00 / 1k user input queries = | +$40,000 |
Advanced Search LLM Add-On Each query added to either Standard or Enterprise query |
||
10M annual | * +$10.00 / 1k user input queries = | +$100,000 |
Data Indexed | ||
100GB annual 10GB free so 90GB used in price calc | * $5.00 / GB * 12 month = | $5,400 |
Data Index pricing
Pricing for Vertex AI Agent Builder Index Data Storage
Data Indexed | $5.00 / GiB per month |
---|---|
* Free quota of 10 GiB per month provided ** Shared across Vertex AI Agent Builder *** Storage is calculated as 500 kibibytes (KiB) * "number of pages on website", where 1 KiB is 1,024 bytes. (500 KiB is ~0.000477 GiB; so data indexing pricing for a 1000 page website is $2.38 per month.) |
Vertex AI Search for Healthcare pricing
Vertex AI Search for Healthcare provides the ability to quickly build medically tuned Search Engines over healthcare data.
Healthcare Search | $20.00 / 1,000 query |
---|
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.
Vertex AI Agent Builder: 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 | Price per 1000 predictions |
---|---|
Up to 20,000,000 | $0.27 |
Next 280,000,000 | $0.18 |
After 300,000,000 | $0.10 |
Feature | Price |
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
SKU Volume | Rate | Total List Price |
---|---|---|
First 20M predictions | * $0.27 / 1k predictions = | $5,400 |
Next 280M predictions | * $0.18 / 1k predictions = | $50,400 |
Next 700M predictions | * $0.10 / 1k predictions = | $70,000 |
500 node hours (Training) | * $2.50 / hour = | $1,250 |
100 node hours (Tuning) | * $2.50 / hour = | $250 |
Total | $127,300 |
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.
Input prompt (includes user prompt, system instructions, and inline grounding facts) | Charged at the price of the selected Gemini model. |
Output | Charged at the price of the selected Gemini model. |
Grounded Generation for grounding on your own retrieved data | $2.50 / 1,000 requests |
Grounded Generation for grounding on Google Search | See Grounding on Google Search. |
The additional charges for data retrieval are determined by the select retrieval system (e.g. Vertex AI Search). |
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).
Check grounding | $0.00075 per 1,000 answer characters |
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
Layout Parser (Includes initial chunking) | $10 per 1,000 pages |
*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
Ranking | $1 per 1,000 queries |
---|
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 Vertex AI Agent Builder documentation.
- Try the Pricing calculator.