Ming Image API: Pricing, Documentation

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state. Provide a Webhook URL via header on the submit request.

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/ming-image/v1/text-to-image' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"prompt": "Minimalist event poster, bold title \"PIXAZO SUMMIT 2026\", date line \"October 12\", geometric shapes, warm orange and navy", "output_format": "png"}'

Callback Payload (success)

{
  "request_id": "ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ming-image",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-09-24T08:44:03.986Z",
  "completed_at": "2026-09-24T08:45:54.402Z"
}

Failure callback shape

{
  "request_id": "ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ming-image",
  "error": "Description of the failure"
}

Delivery semantics

• terminal mode: one Webhook callback when the request is COMPLETED or ERROR.
• sync mode: a Webhook callback on each status change.
• Callbacks are idempotent on request_id — de-duplicate on it.
• Respond 200 within a few seconds; the Webhook endpoint must be HTTPS.

Request Parameters

Good to know

• One request produces one image. There is no batch option: num_images, n, count, batch_size and number_of_images are rejected.
• image_url, num_layers, size and enhance_prompt belong to Layer Decomposition and are rejected here; the canvas size is chosen by the service.
• The current rates are in the pricing panel on this page.

Request Headers

Response Handling

Only what can be judged from the request body itself is rejected synchronously. Everything that needs an input to be fetched or the model to run is reported through the status endpoint instead, as status: "ERROR". Failed requests are not billed — the hold is released in full.

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED (or FAILED/ERROR), then download the result from output.media_url. Most requests finish in under two minutes, so poll every 5–10 seconds rather than continuously.

curl 'https://gateway.pixazo.ai/v2/requests/status/ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ming-image",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-09-24T08:44:03.986Z",
  "completed_at": "2026-09-24T08:45:54.402Z"
}

Text to Image returns one image on a canvas the model chooses from your prompt, about 4 megapixels (for example 2048 x 2048 square, or 1440 x 2560 portrait). Layer Decomposition returns one RGBA image per returned layer, front to back, each the full working canvas with transparency around its content; the model can return fewer layers than requested.

Response Fields

Status Values & Flow

QUEUED → PROCESSING → COMPLETED (success) or FAILED/ERROR (failure).

How billing is measured

Billing follows what the model actually produced, measured in image tokens. Text to Image: the larger the canvas the model chooses, the higher the charge — never more than for a 2048 × 2048 image. Layer Decomposition: the source image plus each layer returned, at the resolution tier the service used (512 < 1k < 2k). When you submit, a hold is placed for the largest possible charge — every requested layer at the requested tier, with auto held at the 2k rate — and it is settled down to the actual usage when the request completes. If the request fails, the hold is released in full.

The current rates are shown in the pricing panel on this page.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state. Provide a Webhook URL via header on the submit request.

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/ming-image/v1/layer-decompose' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/meshy-7/multi-1.png", "num_layers": 2, "prompt": "1 statue, 2 background", "size": "1k"}'

Callback Payload (success)

{
  "request_id": "ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ming-image",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output_0.png",
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output_1.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-09-24T08:44:03.986Z",
  "completed_at": "2026-09-24T08:45:54.402Z"
}

Failure callback shape

{
  "request_id": "ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ming-image",
  "error": "Description of the failure"
}

Delivery semantics

• terminal mode: one Webhook callback when the request is COMPLETED or ERROR.
• sync mode: a Webhook callback on each status change.
• Callbacks are idempotent on request_id — de-duplicate on it.
• Respond 200 within a few seconds; the Webhook endpoint must be HTTPS.

Request Parameters

Good to know

• One request decomposes one image. There is no batch option: num_images, n, count, batch_size and number_of_images are rejected.
• Only Text to Image generates from a prompt alone; this operation always needs an image_url.
• The current rates are in the pricing panel on this page.

Request Headers

Response Handling

Only what can be judged from the request body itself is rejected synchronously. Everything that needs an input to be fetched or the model to run is reported through the status endpoint instead, as status: "ERROR". Failed requests are not billed — the hold is released in full.

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED (or FAILED/ERROR), then download the result from output.media_url. Most requests finish in under two minutes, so poll every 5–10 seconds rather than continuously.

curl 'https://gateway.pixazo.ai/v2/requests/status/ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "ming-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ming-image",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output_0.png",
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output_1.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-09-24T08:44:03.986Z",
  "completed_at": "2026-09-24T08:45:54.402Z"
}

Text to Image returns one image on a canvas the model chooses from your prompt, about 4 megapixels (for example 2048 x 2048 square, or 1440 x 2560 portrait). Layer Decomposition returns one RGBA image per returned layer, front to back, each the full working canvas with transparency around its content; the model can return fewer layers than requested.

Response Fields

Status Values & Flow

QUEUED → PROCESSING → COMPLETED (success) or FAILED/ERROR (failure).

How billing is measured

Billing follows what the model actually produced, measured in image tokens. Text to Image: the larger the canvas the model chooses, the higher the charge — never more than for a 2048 × 2048 image. Layer Decomposition: the source image plus each layer returned, at the resolution tier the service used (512 < 1k < 2k). When you submit, a hold is placed for the largest possible charge — every requested layer at the requested tier, with auto held at the 2k rate — and it is settled down to the actual usage when the request completes. If the request fails, the hold is released in full.

The current rates are shown in the pricing panel on this page.