\n"
},
"groundingChunks": [
{
"web": {
"uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQH6YE7qjDm9XDBfg2DNU5jaK9nYfQ1W8k-vb-Xg0aqbkJn8LWkT5SaBDFlsreSeVrFVl4mjFlLjQuVZKrZZRpUPnSVBkabkENWLUc4srlaDzhr2-egP0K7y_sSQ67KWpbeplLE5WtFyVoL_tFRp5pUfUn4RBpgMllFp",
"title": "sftourismtips.com"
}
},
{
"web": {
"uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHwiuxln0bc0hLj-q141I8u3JbRDx9Vo8kYoFJP5svPXlRainK9o7uM5tRlZrDWM1uu3EeMOp_SY_uv7jSZ3KyISJnfMU0F4lzNDMgkHX4LL2MP9k7RNcyoiqfpOh9JEIpCAGjndtVH3xuDCG0wpcJbX7ti8OHbPE4L9mmnbUnJx-V97dSt",
"title": "accuweather.com"
}
},
{
"web": {
"uri": "https://www.google.com/search?q=weather+in+San Francisco, CA,+US",
"title": "google.com"
}
}
],
"webSearchQueries": [
"",
"San Francisco 5-day weather forecast April 2026",
"San Francisco current weather and clothing recommendation"
]
}
}
],
"usageMetadata": {
"promptTokenCount": 32,
"candidatesTokenCount": 1796,
"totalTokenCount": 1828,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 32
}
],
"candidatesTokensDetails": [
{
"modality": "IMAGE",
"tokenCount": 1120
}
]
},
"modelVersion": "gemini-3.1-flash-image-preview",
"responseId": "NHrNafm2FZaWg8UPo-TQ6Ak"
}
```
***
## Parameters
An optional header used for spend logging metadata, containing JSON properties like `user_id`, `project_id`, and `env`.
The conversation history or input prompts as an array of content objects.
The role of the creator of the content (e.g. `"user"` or `"model"`).
An ordered list of parts that constitute a single message turn.
The text prompt or description for image generation.
Instructions to the model that dictate how it should behave.
An ordered list of parts that constitute the system instruction.
The text of the system instruction.
A list of tools the model may call. Supports `google_search` for search grounding.
Tool configuration for any `Tool` specified in the request.
Configuration for function calling behavior.
Controls how the model uses the provided functions. One of:
* `"AUTO"` — model decides whether to call a function or respond
* `"ANY"` — model must call one of the provided functions
* `"NONE"` — model must not call any functions
Optional. Limits the model to only call functions from this list when `mode` is `"ANY"`.
Configuration options for the generation.
Controls the randomness of the output.
The maximum cumulative probability of tokens to consider when sampling.
The maximum number of tokens to consider when sampling.
The maximum number of tokens to include in a candidate.
Number of generated responses to return. Currently only `1` is supported for image generation.
A list of sequences that will stop generation.
Allowed modalities of the output. Use `["TEXT", "IMAGE"]` to request image output.
Settings for generating images.
Aspect ratio of the generated image (e.g. `16:9`, `1:1`).
Output image resolution level (e.g. `1K`, `2K`, `4K`).
A list of unique safety settings for blocking unsafe content.
The category for this setting (e.g., `HARM_CATEGORY_HATE_SPEECH`).
The threshold for blocking (e.g., `BLOCK_MEDIUM_AND_ABOVE`).
***
## Params to Avoid
| Param | Reason |
| ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt`, `n`, `size`, `quality` | OpenAI/Azure OpenAI parameters; sending these at the root level will fail schema validation. Use `contents` and `generationConfig` instead. |
| `response_format`, `output_format` | Not supported by the Gemini API. Response format is determined by `responseModalities`. |
| `background`, `output_compression`, `style` | OpenAI/Azure specific parameters; not supported by Gemini models. |
| `generationConfig.responseMimeType: "application/json"` | Not supported when `responseModalities` includes `"IMAGE"`. |
| `spend-logs-metadata` | This metadata must be passed as an HTTP header, not in the JSON request body |
Ensure you do not mix OpenAI or Azure-specific parameters (such as `prompt`, `size`, `quality`, or `n`) with Gemini's request structure. Gemini expects prompt text inside the nested `contents.parts` object.
```json theme={null}
{
"candidates": [
{
"content": {
"parts": [
{
"inlineData": {
"mimeType": "image/jpeg",
"data": "/9j/4AAQSkZJRgABAQEBLAEsAAD/+JpoOGMBqHGeRke60T7CXodaqWL92nEd0z8JH8Nvu24UMiCgWZSpq0jSaejI2QA3Y8NFdzPJtcHM4IqqhRR4WUV359PPHxmn/Vkn2yowWe3OXfCfXQhtSiN0hUk2KrjFmI5TyG18="
}
],
"role": "model"
},
"finishReason": "STOP",
"index": 0
}
],
"usageMetadata": {
"promptTokenCount": 9,
"candidatesTokenCount": 1586,
"totalTokenCount": 1595,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 9
}
],
"candidatesTokensDetails": [
{
"modality": "IMAGE",
"tokenCount": 1120
}
]
},
"modelVersion": "gemini-3.1-flash-image-preview",
"responseId": "Y3Lead_eL62Ag8UP-tun8QU"
}
```
***
# Image generation using Gemini model with additional parameters and tool calling
## Request
.jpg?fit=max&auto=format&n=evv7zK2wdD9gNlYj&q=85&s=3b15547c7fff7fec33ded4c562a8b934)
```json theme={null}
{
"candidates": [
{
"content": {
"parts": [
{
"inlineData": {
"mimeType": "image/jpeg",
"data": "/9j/4AAQSkZJRgABAQEBLAEsAAD/P2oO6jEwp8Kpx9u64pFvqRiLEPY0UjEW2XmNMgbG4E8u0G9BMV+IN8Bo1UFcJ5dIUw=="
}
],
"role": "model"
},
"finishReason": "STOP",
"index": 0,
"groundingMetadata": {
"searchEntryPoint": {
"renderedContent": "\n