LiteLLMModels

Gemini 3 Pro Image API Pricing

As of October 10, 2026, Gemini 3 Pro Image costs $0.134 per image on Google AI Studio, plus $2.00 per 1M input tokens. It has a 65,536-token context window and returns up to 32,768 tokens per response.

By GoogleModel ID gemini/gemini-3-pro-imagePrices updated Checked
Per image
$0.134
Input
$2.00 / 1M tokens
Output
$12.00 / 1M tokens
Context window
65,536 tokens
Max output
32,768 tokens
Providers
3
Added to LiteLLM
June 29, 2026

Gemini 3 Pro Image pricing by provider

3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMPer imageInputOutputImage outputCache readBatch inBatch outContext
Google AI Studiogemini/gemini-3-pro-image$0.134$2.00$12.00$120.00–$1.00$6.0064K
Google Vertex AIvertex_ai/gemini-3-pro-image$0.134$2.00$12.00$120.00$0.20$1.00$6.0064K
Databricksdatabricks/databricks-gemini-3-pro-image–––––––64K

Other Gemini 3 Pro Image prices on Google AI Studio

Priority input$3.60 per 1M tokens
Priority output$21.60 per 1M tokens
Flex input$1.00 per 1M tokens
Flex output$6.00 per 1M tokens
Input image$0.0011 per image
Web search$14.00 per 1K searches

What Gemini 3 Pro Image costs in practice

Generating 1,000 images

Google AI Studio$134.00
Google Vertex AI$134.00

Gemini 3 Pro Image features

Input: text, image. Output: text, image.

Use Gemini 3 Pro Image with LiteLLM

Call Gemini 3 Pro Image through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/images/generations. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import image_generation

response = image_generation(
    model="gemini/gemini-3-pro-image",
    prompt="A cute baby sea otter",
)
Proxy config.yaml
model_list:
  - model_name: gemini-3-pro-image
    litellm_params:
      model: gemini/gemini-3-pro-image
      api_key: os.environ/GEMINI_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gemini-3-pro-image",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "size": "1024x1024"
  }'

Gemini 3 Pro Image FAQ

How much does Gemini 3 Pro Image cost?

Gemini 3 Pro Image costs $0.134 per image on Google AI Studio, plus $2.00 per 1M input tokens. Batch requests cost $1.00 per 1M input tokens and $6.00 per 1M output tokens.

What is the context window of Gemini 3 Pro Image?

Gemini 3 Pro Image has a 65,536-token context window and returns up to 32,768 tokens per response.

Which providers offer Gemini 3 Pro Image?

Gemini 3 Pro Image is available from 3 providers through LiteLLM: Google AI Studio, Google Vertex AI and Databricks.

How do I call Gemini 3 Pro Image with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gemini/gemini-3-pro-image", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/images/generations from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Gemini 3 Pro Image support?

Gemini 3 Pro Image supports image input, reasoning and web search. It does not support function calling, structured output and prompt caching.

When did LiteLLM add Gemini 3 Pro Image?

Gemini 3 Pro Image was added to LiteLLM's model price file on June 29, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Google AI Studio, Google Vertex AI, Databricks.

Provider pages: Google AI Studio, Google Vertex AI, Databricks.