curl --request POST \
--url https://api.tikway.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "microsoft/mai-image-2.5-pro",
"prompt": "雨夜的未来城市，写实摄影",
"size": "1024x1024",
"response_format": "url"
}
'{
"created": 1788923928,
"data": [
{
"index": 0,
"b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
}
],
"model": "microsoft/mai-image-2.5-pro",
"output_format": "png",
"size": "1024x1024",
"usage": {
"input_tokens": 36,
"input_tokens_details": {
"text_tokens": 36
},
"output_tokens": 1024,
"output_tokens_details": {
"image_tokens": 1024
},
"total_tokens": 1060
}
}Image generation
microsoft/mai-image-2.5-pro supports text-to-image and image-to-image through the generation endpoint. The optional images array accepts one JPEG or PNG reference image. Each request produces one PNG. Both dimensions must be at least 768 pixels, with no more than 1,048,576 total pixels.
curl --request POST \
--url https://api.tikway.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "microsoft/mai-image-2.5-pro",
"prompt": "雨夜的未来城市，写实摄影",
"size": "1024x1024",
"response_format": "url"
}
'{
"created": 1788923928,
"data": [
{
"index": 0,
"b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
}
],
"model": "microsoft/mai-image-2.5-pro",
"output_format": "png",
"size": "1024x1024",
"usage": {
"input_tokens": 36,
"input_tokens_details": {
"text_tokens": 36
},
"output_tokens": 1024,
"output_tokens_details": {
"image_tokens": 1024
},
"total_tokens": 1060
}
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Use Doubao Seedream 5.0 Pro to generate images from text.
Required. Use a model ID or available alias returned by Get Models.
1"microsoft/mai-image-2.5-pro"
Required. Describe the image to generate.
1"一座漂浮在云海上的未来城市，日出时分，电影级光影，建筑细节丰富"
Output size as WIDTHxHEIGHT, or auto for the model default. Supported sizes depend on the selected model.
^[1-9][0-9]*x[1-9][0-9]*$Response format: url returns image URLs; b64_json returns Base64 image data.
b64_json, url Optional reference images for image-to-image generation. Omit for text-to-image generation. Image limits depend on the selected model.
1 element1Response
Unify transformed OpenAI Images responses.
Unix timestamp of the image creation time, in seconds.
1788480000
Generate a list of results.
The model ID that actually executes the request.
Actual output format.
actual generated size.
The usage information generated this time.
Hide child attributes
Hide child attributes
Enter the number of tokens.
Output the number of tokens.
Total number of tokens.