> ## Documentation Index
> Fetch the complete documentation index at: https://docs.znapai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Vertex Image editing
***
## Request
```shellscript cURL theme={null}
curl --location 'https://api.znapai.com/v1beta1/projects/default/locations/global/publishers/google/models/gemini-2.5-flash-image:generateContent' \
--header 'Authorization: Bearer $ZnapAI_API_KEY' \
--header 'Content-Type: application/json' \
--header 'spend-logs-metadata: {"user_id": "user-123", "project_id": "proj_abc", "env": "production"}' \
--data '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Edit this image and draw a smiley in it"
},
{
"inlineData": {
"mimeType": "image/jpeg",
"data": "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"
}
}
]
}
],
"generationConfig": {
"responseModalities": ["IMAGE", "TEXT"]
}
}'
```
## Input
## Response
```json theme={null}
{
"candidates": [
{
"content": {
"role": "model",
"parts": [
{
"inlineData": {
"mimeType": "image/png",
"data": "iVBORw0KGgo...uQmCC"
}
}
]
},
"finishReason": "STOP"
}
],
"usageMetadata": {
"promptTokenCount": 1812,
"candidatesTokenCount": 1290,
"totalTokenCount": 3102,
"trafficType": "ON_DEMAND",
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 6
},
{
"modality": "IMAGE",
"tokenCount": 1806
}
],
"candidatesTokensDetails": [
{
"modality": "IMAGE",
"tokenCount": 1290
}
]
},
"modelVersion": "gemini-2.5-flash-image",
"createTime": "2026-04-08T17:50:54.995975Z",
"responseId": "fpXWaYflPLqnpt8P8svDwAE"
}
```
***
## Image from base64 data
.png?fit=max&auto=format&n=YqLy5V4XqDwqd3Qg&q=85&s=9a2d0f35a3e83a0b64671181febdc1bf)
***
## 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 instruction prompt for editing.
The inline image data to be edited.
The IANA media type of the image (e.g. `image/png`, `image/jpeg`).
The base64-encoded image bytes.
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 use to generate the next response. Supported tools are function declarations, code execution, and Google Search.
A list of function declarations the model can call.
The name of the function to call.
A description of what the function does.
Describes the parameters for the function in JSON Schema format.
The type of the parameters object. Usually `"object"`.
A map of parameter names to their schema definitions.
List of required parameter names.
Enables the model to execute code as part of generation. Pass an empty object `{}` to enable.
Tool to support Google Search grounding in model responses. Pass an empty object `{}` to enable.
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 in text
* `"ANY"` — model must call one of the provided functions
* `"NONE"` — model must not call any functions
Optional. When `mode` is `"ANY"`, limits the model to only call functions from this list.
Configuration options for the generation.
Number of generated images to return.
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.
A list of sequences that will stop generation.
Allowed modalities of the output. Use `["IMAGE", "TEXT"]` to request image output.
Settings for the output image.
Aspect ratio of the output 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.
The threshold for blocking.
***
## 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"`. |
| `inline_data`, `mime_type` | Snake case keys are used in the Google GenAI Developer API, but the Vertex AI API requires camelCase (`inlineData`, `mimeType`). |
| `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/Vertex AI request structure. Vertex AI expects prompt text and the image input inside the nested `contents.parts` object using camelCase keys.