UPDATES
Try Bifrost Enterprise free for 14 days.
Explore now

gemini-3-pro-image-preview Cost Calculator - Vertex AI

Calculate the cost of using gemini-3-pro-image-preview from Vertex AI for your AI applications

gemini-3-pro-image-preview Cost Calculator

Mode: Image Generation

Cost Breakdown

Input Cost$0.002000
Image Cost$0.134000
Total Cost$0.136000

Pricing Details

Input: $0.00000200 per token
Output: $0.00001200 per token
Input Image: $0.001100 per image
Output Image: $0.134000 per image
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Book a Demo
or, Get started here

Model Specifications

Capabilities

✓Vision
✓Web Search

Limits

Max Input Tokens65,536
Max Output Tokens32,768
Max Tokens32,768

About gemini-3-pro-image-preview

gemini-3-pro-image-preview is a powerful image generation AI model offered by Vertex AI. This comprehensive guide provides detailed pricing information, technical specifications, and capabilities to help you understand the costs and features of using gemini-3-pro-image-preview in your applications.

Pricing Information

Input Cost$2.00 per 1M tokens
Output Cost$12.00 per 1M tokens
Image Input Cost$0.0011 per image
Image Output Cost$0.1340 per image

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

Technical Specifications

Maximum Input Tokens65,536
Maximum Output Tokens32,768
Maximum Total Tokens32,768

Pro Tip

Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 65,536 input tokens. The maximum output length is 32,768 tokens.

Model Capabilities

✓Vision - Process and understand images
✓Web Search - Access real-time web information
✓Prompt Caching - Optimize repeated prompts
✓System Messages - Configure model behavior
✓Response Schema - Structured output formatting
When should you use gemini-3-pro-image-preview?

gemini-3-pro-image-preview is best suited for the following scenarios:

  • Image generation from prompts (creative and product mockups)
  • Variant generation and iterative creative workflows
  • Image-heavy content pipelines (ads, thumbnails, concepts)
When should you avoid gemini-3-pro-image-preview?
  • Long-form conversational AI
  • Pure embedding or reranking workloads
  • Audio transcription or text-to-speech (use audio models)
How does gemini-3-pro-image-preview compare to similar models?

This is an image generation model. Compared to text-only models, costs often depend on images generated (and sometimes prompt tokens). When comparing alternatives, consider output quality/style control, throughput, and per-image pricing.

Understanding gemini-3-pro-image-preview pricing
  • gemini-3-pro-image-preview is a image generation model provided by Vertex AI.
  • Input tokens are priced at $2.00 per 1M tokens.
  • Output tokens are priced at $12.00 per 1M tokens.
  • Image input is priced at $0.0011 per image.
  • Image output is priced at $0.1340 per image.
  • The model supports a maximum input capacity of 65,536 tokens.
  • Maximum output length is 32,768 tokens.
  • For this model, input tokens are less expensive than output tokens, so optimizing your prompts can help manage costs.
  • The model includes vision capabilities for processing and analysing images.
  • Includes real-time web search capabilities for accessing current information.
  • Features prompt caching to optimize costs for repeated prompts.
  • Vertex AI offers gemini-3-pro-image-preview for image generation workloads — prompt-to-image creative workflows and image-heavy content pipelines.

How to Use This Calculator

Step 1: Enter the number of input tokens you expect to use. Input tokens include your prompt, system messages, and any context you provide to the model.

Step 2: Specify the number of output tokens you anticipate. Output tokens are the text generated by the model in response to your input.

Step 3: Review the cost breakdown to see the total estimated cost for your usage. The calculator automatically updates as you adjust the token counts.

← Back to All ModelsView All Vertex AI Models