--- title: "Vertex AI Image Generation" url: "/docs/providers/vertex_image" canonical_url: "https://docs.litellm.ai/docs/providers/vertex_image" type: "docs" last_updated: "2026-10-06" summary: "Vertex AI supports two types of image generation:" related: - "/docs/providers/vertex_embedding" - "/docs/providers/vertex_speech" --- # Vertex AI Image Generation > Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt Vertex AI supports two types of image generation: 1. **Gemini Image Generation Models** (Nano Banana 🍌) - Conversational image generation using `generateContent` API 2. **Imagen Models** - Traditional image generation using `predict` API | Property | Details | |----------|---------| | Description | Vertex AI Image Generation supports both Gemini image generation models | | Provider Route on LiteLLM | `vertex_ai/` | | Provider Doc | [Google Cloud Vertex AI Image Generation ↗](https://cloud.google.com/vertex-ai/docs/generative-ai/image/generate-images) | | Gemini Image Generation Docs | [Gemini Image Generation ↗](https://ai.google.dev/gemini-api/docs/image-generation) | ## Quick Start ### Gemini Image Generation Models Gemini image generation models support conversational image creation with features like: - Text-to-Image generation - Image editing (text + image → image) - Multi-turn image refinement - High-fidelity text rendering - Up to 4K resolution (Gemini 3 Pro) ```python showLineNumbers title="Gemini 2.5 Flash Image" import litellm # Generate a single image response = await litellm.aimage_generation( prompt="A nano banana dish in a fancy restaurant with a Gemini theme", model="vertex_ai/gemini-2.5-flash-image", vertex_ai_project="your-project-id", vertex_ai_location="us-central1", n=1, size="1024x1024", ) print(response.data[0].b64_json) # Gemini returns base64 images ``` ```python showLineNumbers title="Gemini 3 Pro Image Preview (4K output)" import litellm # Generate high-resolution image response = await litellm.aimage_generation( prompt="Da Vinci style anatomical sketch of a dissected Monarch butterfly", model="vertex_ai/gemini-3-pro-image-preview", vertex_ai_project="your-project-id", vertex_ai_location="us-central1", n=1, size="1024x1024", # Optional: specify image size for Gemini 3 Pro # imageSize="4K", # Options: "1K", "2K", "4K" ) print(response.data[0].b64_json) ``` ### Google Search Grounding Gemini image models (e.g. `gemini-3.1-flash-image-preview`, `gemini-3-pro-image-preview`) support Google Search on `/v1/images/generations`. LiteLLM maps `web_search_options` or OpenAI-style `web_search` tools to Gemini's `googleSearch` tool on the underlying `generateContent` request. ```python showLineNumbers title="Image generation with Google Search" import litellm response = await litellm.aimage_generation( prompt="Generate an image of the latest iPhone design", model="vertex_ai/gemini-3.1-flash-image-preview", vertex_ai_project="your-project-id", vertex_ai_location="us-central1", web_search_options={}, ) print(response.data[0].b64_json) ``` ```python showLineNumbers title="Using OpenAI-style web_search tool" import litellm response = await litellm.aimage_generation( prompt="Generate an image of the latest iPhone design", model="vertex_ai/gemini-3.1-flash-image-preview", vertex_ai_project="your-project-id", vertex_ai_location="us-central1", tools=[{"type": "web_search"}], ) ``` Via LiteLLM Proxy (`/v1/images/generations`): ```bash showLineNumbers title="Proxy request with web_search_options" curl -X POST 'http://localhost:4000/v1/images/generations' \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $LITELLM_API_KEY" \ -d '{ "model": "gemini-3.1-flash-image-preview", "prompt": "Generate an image of the latest iPhone design", "web_search_options": {} }' ``` ### Passing imageConfig (Gemini models) Gemini image generation models support the full [`ImageConfig`](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#imageconfig) object. Pass it as `imageConfig` on any `/v1/images/generations` request and LiteLLM will forward all fields verbatim to `generationConfig.imageConfig`. | Field | Type | Description | |---|---|---| | `aspectRatio` | string | `"1:1"`, `"16:9"`, `"9:16"`, `"4:3"`, `"3:4"`, `"4:5"`, `"5:4"`, `"2:3"`, `"3:2"`, `"21:9"` | | `imageSize` | string | `"1K"`, `"2K"`, `"4K"` (supported on Gemini 3 Pro and newer) | | `personGeneration` | string | `"DONT_ALLOW"`, `"ALLOW_ADULT"`, `"ALLOW_ALL"` | | `imageOutputOptions` | object | `{"mimeType": "image/jpeg"\|"image/png"\|"image/webp", "compressionQuality": 0–100}` | ```python showLineNumbers title="Passing imageConfig via Python SDK" import litellm response = await litellm.aimage_generation( model="vertex_ai/gemini-3.1-flash-image", prompt="A nano banana on a desk", vertex_ai_project="your-project-id", vertex_ai_location="us-central1", imageConfig={ "aspectRatio": "16:9", "imageSize": "2K", "personGeneration": "DONT_ALLOW", "imageOutputOptions": { "mimeType": "image/jpeg", "compressionQuality": 85, }, }, ) ``` ```bash showLineNumbers title="Passing imageConfig via Proxy" curl -X POST 'http://localhost:4000/v1/images/generations' \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $LITELLM_API_KEY" \ -d '{ "model": "gemini-3.1-flash-image", "prompt": "A nano banana on a desk", "imageConfig": { "aspectRatio": "16:9", "imageSize": "2K", "personGeneration": "DONT_ALLOW", "imageOutputOptions": { "mimeType": "image/jpeg", "compressionQuality": 85 } } }' ``` You can also use flat params as shorthand for `aspectRatio` and `imageSize`: ```python showLineNumbers title="Flat param shorthand" response = await litellm.aimage_generation( model="vertex_ai/gemini-3.1-flash-image", prompt="A nano banana on a desk", aspect_ratio="16:9", # or aspectRatio="16:9" image_size="2K", # or imageSize="2K" vertex_ai_project="your-project-id", vertex_ai_location="us-central1", ) ``` Flat params (`aspect_ratio`, `image_size`, `aspectRatio`, `imageSize`) override the same key inside `imageConfig` when both are present. ### Imagen Models ```python showLineNumbers title="Imagen Image Generation" import litellm # Generate a single image response = await litellm.aimage_generation( prompt="An olympic size swimming pool with crystal clear water and modern architecture", model="vertex_ai/imagen-4.0-generate-001", vertex_ai_project="your-project-id", vertex_ai_location="us-central1", n=1, size="1024x1024", ) print(response.data[0].b64_json) # Imagen also returns base64 images ``` ### LiteLLM Proxy #### 1. Configure your config.yaml ```yaml showLineNumbers title="Vertex AI Image Generation Configuration" model_list: - model_name: vertex-imagen litellm_params: model: vertex_ai/imagen-4.0-generate-001 vertex_ai_project: "your-project-id" vertex_ai_location: "us-central1" vertex_ai_credentials: "path/to/service-account.json" # Optional if using environment auth ``` #### 2. Start LiteLLM Proxy Server ```bash title="Start LiteLLM Proxy Server" litellm --config /path/to/config.yaml # RUNNING on http://0.0.0.0:4000 ``` #### 3. Make requests with OpenAI Python SDK ```python showLineNumbers title="Basic Image Generation via Proxy" from openai import OpenAI # Initialize client with your proxy URL client = OpenAI( base_url="http://localhost:4000", # Your proxy URL api_key="your-proxy-api-key" # Your proxy API key ) # Generate image response = client.images.generate( model="vertex-imagen", prompt="An olympic size swimming pool with crystal clear water and modern architecture", ) print(response.data[0].url) ``` ## Supported Models ### Gemini Image Generation Models - `vertex_ai/gemini-2.5-flash-image` - Fast, efficient image generation (1024px resolution) - `vertex_ai/gemini-3.1-flash-image-preview` - Fast image generation with Google Search grounding - `vertex_ai/gemini-3-pro-image-preview` - Advanced model with 4K output, Google Search grounding, and thinking mode - `vertex_ai/gemini-2.0-flash-preview-image` - Preview model - `vertex_ai/gemini-2.5-flash-image-preview` - Preview model ### Imagen Models - `vertex_ai/imagegeneration@006` - Legacy Imagen model - `vertex_ai/imagen-4.0-generate-001` - Latest Imagen model - `vertex_ai/imagen-3.0-generate-001` - Imagen 3.0 model :::tip **We support ALL Vertex AI Image Generation models, just set `model=vertex_ai/` as a prefix when sending litellm requests** ::: For the complete and up-to-date list of supported models, visit: [https://models.litellm.ai/](https://models.litellm.ai/) ## Related pages - [Vertex AI Embedding](https://docs.litellm.ai/docs/providers/vertex_embedding.md) - [Vertex AI Text to Speech](https://docs.litellm.ai/docs/providers/vertex_speech.md)