Vertex AI pricing

Prices are listed in US Dollars (USD). If you pay in a currency other than USD, the prices listed in your currency on Cloud Platform SKUs apply.

This page covers pricing for Generative AI on Vertex AI. For all other Vertex AI pricing including ML Platform and MLOps services please refer to Vertex AI pricing page.

Google foundational models

Multimodal

With the Multimodal models in Vertex AI, you can input either text or media (images, video). Text input is charged by every 1,000 characters of input (prompt) and every 1,000 characters of output (response). Characters are counted by UTF-8 code points and white space is excluded from the count. Prediction requests that lead to filtered responses are charged for the input only. At the end of each billing cycle, fractions of one cent ($0.01) are rounded to one cent. Media input is charged per image or per second (video).

Model Feature Type Price
Gemini 1.0 Pro Multimodal Image Input
Video Input
Text Input
$0.0025 / image
$0.002 / second
$0.000125 / 1k characters
Text Output $0.000375 / 1k characters
Gemini 1.5 Pro Multimodal Image Input
Video Input
Text Input
Audio Input
$0.00265 / image
$0.00265 / second
$0.0025 / 1k characters
$0.00025 / second
Text Output $0.0075 / 1k characters
Grounding with Google Search Text Grounding requests $35 / 1k requests

Prices are listed in US Dollars (USD). If you pay in a currency other than USD, the prices listed in your currency on Cloud Platform SKUs apply.

Image generation

With the Image Generation feature of Vertex AI, you can generate novel images and edit images based on text prompts you provide, or edit only parts of images using a mask area you define along with a host of other capabilities.

Model Feature Description Input Output Price
Imagen Image generation Generate an image Text prompt Image $0.020 per image
Image editing Edit an image using mask free or mask approach Image/Text prompt Image $0.020 per image
Upscaling Increase resolution of a generated image to 2k and 4k Image Image $0.003 per image
Fine-tuning Enable a "subject" provided by the user to used in Imagen prompts (few shot training) Subject(s) with text identifier and 4-8 images per subject Fine-tuned model (after training with user provided subjects) $ per node hour (Vertex AI custom training pricing)
Visual Captioning Generate a short or long text caption for an image Image Text caption $0.0015/image
Visual Q&A Provide an answer based on a question referencing an image Image/Text prompt Text answer $0.0015/image

Prices are listed in US Dollars (USD). If you pay in a currency other than USD, the prices listed in your currency on Cloud Platform SKUs apply.

Multimodal Embeddings API

Model Feature Description Input Output Price
multimodalembeddings Embeddings for Multimodal: Text Generate embeddings using text as an input Text Embeddings $0.0002 / 1k characters input
Embeddings for Multimodal: Image Generate embeddings using image as an input Image Embeddings $0.0001 / image input
Embeddings for Multimodal: Video Video Plus Video Embeddings (up to 15 embeddings per min of video) $0.0020 per second of video
Embeddings for Multimodal: Video Video Standard Video Embeddings (up to 8 embeddings per min of video) $0.0010 per second of video
Embeddings for Multimodal: Video Video Essential Video Embeddings (up to 4 embeddings per min of video) $0.0005 per second of video

Prices are listed in US Dollars (USD). If you pay in a currency other than USD, the prices listed in your currency on Cloud Platform SKUs apply.

Text generation

Generative AI on Vertex AI charges by every 1,000 characters of input (prompt) and every 1,000 characters of output (response). Characters are counted by UTF-8 code points and white space is excluded from the count. During the Preview stage, charges are 100% discounted. Prediction requests that lead to filtered responses are charged for the input only. At the end of each billing cycle, fractions of one cent ($0.01) are rounded to one cent.

Model Type Region Price per 1,000 characters
PaLM 2 for Text (Text Bison) Input Global
  • Online requests: $0.00025
  • Batch requests: $0.00020
Output Global
  • Online requests: $0.0005
  • Batch requests: $0.0004
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Reinforcement Learning from Human Feedback us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
PaLM 2 for Text 32k (Text Bison 32k) Input Global
  • Online requests: $0.00025
  • Batch requests: $0.00020
Output Global
  • Online requests: $0.0005
  • Batch requests: $0.0004
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
PaLM 2 for Text
(Text Unicorn)
Input Global
  • Online requests: $0.0025
  • Batch requests: $0.0020
Output Global
  • Online requests: $0.0075
  • Batch requests: $0.0060
PaLM 2 for Chat (Chat Bison) Input Global
  • Online requests: $0.00025
Output Global
  • Online requests: $0.0005
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Reinforcement Learning from Human Feedback us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
PaLM 2 for Chat 32k (Chat Bison 32k) Input Global
  • Online requests: $0.00025*
Output Global
  • Online requests: $0.0005*
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Embeddings for Text Input Global
  • Online requests: $0.000025
  • Batch requests: $0.00002
Output Global
  • Online requests: No charge
  • Batch requests: No charge
Codey for Code Generation Input Global
  • Online requests: $0.00025
  • Batch requests: $0.00020
Output Global
  • Online requests: $0.0005
  • Batch requests: $0.0004
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Codey for Code Generation 32k Input Global
  • Online requests: $0.00025
Output Global
  • Online requests: $0.0005
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Codey for Code Chat Input Global
  • Online requests: $0.00025
Output Global
  • Online requests: $0.0005
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Codey for Code Chat 32k Input Global
  • Online requests: $0.00025
Output Global
  • Online requests: $0.0005
Supervised Tuning us-central1
europe-west4
$ per node hour Vertex AI custom training pricing
Codey for Code Completion Input Global
  • Online requests: $0.00025
Output Global
  • Online requests: $0.0005

Prices are listed in US Dollars (USD). If you pay in a currency other than USD, the prices listed in your currency on Cloud Platform SKUs apply.

Example cost calculation

If a user sends five separate requests to the PaLM Text Bison model, and each request has a 200-character input and 400-character output, the total charge is calculated as follows:

Input cost:
200 input characters x 5 prompts = 1,000 total input characters;
1,000 total input characters x ($0.00025 / 1000) = $0.00025 input cost.

Output cost:
400 output characters x 5 prompts = 2,000 total output characters;
2,000 total output characters x ($0.0005 / 1000) = $0.001 output cost.

Total cost:
$0.00025 input cost + $0.001 output cost = $0.00125 total cost.

Partner models

Partner models are a curated list of generative AI models developed by Google partners. Partner models are offered as managed APIs. For more information, see Overview of partner models. The following table lists pricing details for Google partner models:

Anthropic’s Claude 3 models

Model Pricing
Claude 3 Opus Input: $15 / million tokens
Output: $75 / million tokens
Claude 3 Sonnet Input: $3 / million tokens
Output: $15 / million tokens
Claude 3 Haiku Input: $0.25 / million tokens
Output: $1.25 / million tokens

Request a custom quote

With 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.
Contact sales