Chat interface - supports text-to-image, image-to-image, and pure conversation

Universal chat interface supporting Gemini model's text-to-image, image-to-image, and pure conversation features.

Interface features:

Supports streaming output: Receive generation progress in real-time

Shows reasoning process: Returns the model's reasoning process (reasoning_content)

More flexible interaction: Can chat without generating images, or generate images

Multimodal support: Naturally mix text and image inputs in conversations

Fast generation: Faster generation speed compared to Pro version

Request

Authorization

API Key

Add parameter in header

Authorization

Example:

Authorization: ********************

Body Params application/jsonRequired

Examples

Text-to-image exampleImage-to-image examplePure conversation exampleSpecify aspect ratio

{
"model": "gemini-2.5-flash-image",
"stream": true,
"messages": [
{
"role": "user",
"content": "Draw a cute orange cat sitting on a windowsill watching the sunset"
}
]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200Success

application/json

Request successful

Bodyapplication/json

Example

{
    "id": "chatcmpl-2f8236e9f2b34bd391289576d0e23e72",
    "object": "chat.completion",
    "created": 1764574464,
    "model": "gemini-2.5-flash-image",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "",
                "reasoning_content": "**Analyzing the request**\n\nProcessing the image generation task...",
                "images": [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABYAAAAMACAIAAAASU1SbA.........."
                        },
                        "index": 0
                    }
                ]
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 19,
        "completion_tokens": 1120,
        "total_tokens": 1139,
        "prompt_tokens_details": {
            "text_tokens": 19
        },
        "completion_tokens_details": {
            "reasoning_tokens": 100,
            "image_tokens": 1020
        }
    }
}

🟠400Invalid request

🟠401Unauthorized

🔴500Internal server error