curl --request POST \
--url https://api.modellix.ai/api/v1/microsoft/mai-image-2.6 \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "A photorealistic product hero shot of a smartwatch on a reflective surface"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-mai-t2i-26-001",
"model_id": "microsoft/mai-image-2.6",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-mai-t2i-26-001"
}
}
}{
"code": 400,
"message": "Invalid parameters: width x height exceeds the maximum pixel count 1048576"
}{
"code": 401,
"message": "Authentication failed: invalid API key"
}{
"code": 429,
"message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}{
"code": 500,
"message": "Internal server error"
}MAI Image 2.6
[Core Function] MAI Image 2.6 is Microsoft’s latest text-to-image generation model in the MAI Image family. [Strengths] It improves text rendering, portraits, 3D imagery, and commercial photorealistic output compared with MAI Image 2.5. [Best For] Highly recommended for: marketing visuals, product hero shots, portraits, and prompts that need accurate on-image text. [Limitations] Do NOT use this if the requested width or height is below 768, or if width x height exceeds 1,048,576 pixels. Output is always PNG. auto_aspect_ratio and web_grounding are optional booleans; omit them unless the caller sets them. [Routing] Use this model when the latest MAI quality is required. For lower latency or cost, route to MAI Image 2.6 Flash.
curl --request POST \
--url https://api.modellix.ai/api/v1/microsoft/mai-image-2.6 \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "A photorealistic product hero shot of a smartwatch on a reflective surface"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-mai-t2i-26-001",
"model_id": "microsoft/mai-image-2.6",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-mai-t2i-26-001"
}
}
}{
"code": 400,
"message": "Invalid parameters: width x height exceeds the maximum pixel count 1048576"
}{
"code": 401,
"message": "Authentication failed: invalid API key"
}{
"code": 429,
"message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}{
"code": 500,
"message": "Internal server error"
}Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Microsoft MAI Image 2.6 text-to-image request. Shared by MAI Image 2.6 and 2.6 Flash. Width and height must be provided together; their product must not exceed 1,048,576 pixels. Output is always PNG. auto_aspect_ratio and web_grounding are optional; omit them to leave upstream defaults (do not send the fields).
Text description of the image to generate. Platform limit is 32,000 UTF-8 bytes, not Unicode characters.
1 - 32000"A photorealistic concept art poster of a university at sunset, cinematic lighting"
Image width in pixels (>=768). Must be provided together with height; width x height must not exceed 1,048,576.
768 <= x <= 13651024
Image height in pixels (>=768). Must be provided together with width; width x height must not exceed 1,048,576.
768 <= x <= 13651024
Optional. When true, the model chooses the output aspect ratio from the prompt (and any image inputs). Omit this field to leave the requested width and height unchanged. Do not send it unless the caller explicitly wants model-directed framing.
Optional. When true, the model may retrieve current public information (Bing) as extra context for real-world entities, places, or events. Omit this field to generate from the prompt only. Do not send it unless the caller explicitly wants web-grounded generation.