Krea 3 API, Krea 2 Turbo API, Krea 2 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/krea-3/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": "A red fox curled up asleep in fresh snow at dawn, soft pink light on the pine trees behind it", "image_size": {"width": 1024, "height": 1024}}'

Callback Payload (success)

{
  "request_id": "krea-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Failure callback shape

{
  "request_id": "krea-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-3",
  "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 every poll while the request is processing (status PROCESSING), plus the final COMPLETED/ERROR callback.
• 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

• Each request returns one image. batch_size, num_images, number_of_images, n and count are rejected — send one request per image.
• This API makes still images and has no length setting. duration, seconds, num_frames, frames_per_second and music_length_ms are rejected.
• Send every field at the top level of the JSON body; parameters, input, content and text are rejected.
• To edit or combine images, use the Krea 3 edit API: POST https://gateway.pixazo.ai/krea-3-edit/v1/edit. image_urls, image_url and image are rejected here.
• Set the output size in image_size as an object with width and height, or leave it out (or send "auto") to let the model choose. Named sizes such as square_hd are not accepted.
• enable_safety_checker is always on: send true or leave it out.
• Use the JSON types shown: prompt, negative_prompt, reasoning_level and output_format are strings, seed is a whole number, enable_safety_checker is true, and image_size is "auto" or an object with whole-number width and height.
• Omit a field instead of sending null.
• Results are always returned as a URL in output.media_url; sync_mode is accepted only as false.
• Webhooks are set with the X-Webhook-URL / X-Webhook-Mode headers; webhook_url, webhook_mode and callback_url in the JSON body are rejected.
• stream is not supported: the result is delivered when the job completes.

Output Size

• Send image_size as an object with width and height: each edge from 256 to 3200 pixels, at most 4,220,160 pixels in total. Each edge is rounded up to a multiple of 16.
• Leave image_size out, or send "auto", and the model chooses the shape of the image at about 4 megapixels.
• The size sets the amount billed: see How Billing Is Measured below.

Example: a wide image

{
  "prompt": "A quiet harbor town at sunrise, fishing boats and soft mist over the water",
  "image_size": {
    "width": 1536,
    "height": 640
  }
}

Example: let the model choose the size

{
  "prompt": "A ceramic teapot on a wooden table, morning light",
  "image_size": "auto"
}

Request Headers

Response Handling

Parameter problems are caught when you submit and returned as a 400, before any hold is placed on your balance. Problems that need the model to run are reported through the status endpoint as status: "ERROR", with a message in error saying what went wrong. Failed requests are not billed — the hold is released in full.

Example error responses

A refused request returns error, a message that joins every problem found, and the same problems one by one in violations.

Missing prompt (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'prompt' is required",
  "violations": [
    "'prompt' is required"
  ]
}

A named size (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_size' must be one of [auto] or object (got \"square_hd\")",
  "violations": [
    "'image_size' must be one of [auto] or object (got \"square_hd\")"
  ]
}

A reasoning level this API does not offer (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'reasoning_level' must be one of: \"low\", \"medium\" (got \"high\")",
  "violations": [
    "'reasoning_level' must be one of: \"low\", \"medium\" (got \"high\")"
  ]
}

An image sent to text to image (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_urls' must be one of:  (got [\"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg\"]); 'image_urls' is not accepted by text to image. Use the Krea 3 edit API to edit or combine images.",
  "violations": [
    "'image_urls' must be one of:  (got [\"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg\"])",
    "'image_urls' is not accepted by text to image. Use the Krea 3 edit API to edit or combine images."
  ]
}

More than one image per request (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'num_images' must be one of:  (got 2); 'num_images' is not supported: each request returns one image. Send one request per image.",
  "violations": [
    "'num_images' must be one of:  (got 2)",
    "'num_images' is not supported: each request returns one image. Send one request per image."
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the image from output.media_url. Treat any status other than QUEUED, PROCESSING or COMPLETED as a failure.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

cURL example

curl 'https://gateway.pixazo.ai/v2/requests/status/krea-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "krea-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Response Fields

Status Values & Flow

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

Typical workflow

1. Send the request to POST https://gateway.pixazo.ai/krea-3/v1/text-to-image.
2. Save the request_id from the 202 response.
3. Poll GET /v2/requests/status/{request_id} every 10 seconds or so, or use a Webhook instead.
4. When status is COMPLETED, download the image from output.media_url.

How Billing Is Measured

Billing is measured per megapixel of the output image (1 megapixel = 1,048,576 pixels), with each edge rounded up to a multiple of 16 and to at least 256 pixels. A request without a size, or with "auto", is billed at the largest size, 4,220,160 pixels. The prompt and the other settings do not change the amount. The amount is placed as a hold when the request is submitted and released in full if the request fails. The current rate is 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/krea-3-edit/v1/edit' \
  -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": "Turn <image-1> into a soft watercolor painting", "image_urls": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"], "image_size": {"width": 1024, "height": 1024}}'

Callback Payload (success)

{
  "request_id": "krea-3-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-3-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Failure callback shape

{
  "request_id": "krea-3-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-3-edit",
  "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 every poll while the request is processing (status PROCESSING), plus the final COMPLETED/ERROR callback.
• 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

• Each request returns one image. batch_size, num_images, number_of_images, n and count are rejected — send one request per image.
• This API makes still images and has no length setting. duration, seconds, num_frames, frames_per_second and music_length_ms are rejected.
• Send every field at the top level of the JSON body; parameters, input, content and text are rejected.
• Send one to eight images in image_urls, as publicly reachable https URLs (recommended) or base64 data URIs. Their order sets the tags <image-1> to <image-8> you can use in prompt.
• image_url and image are rejected: send the images as a list in image_urls.
• Set the output size in image_size as an object with width and height, or leave it out (or send "auto") to let the model choose. Named sizes such as square_hd are not accepted.
• enable_safety_checker is always on: send true or leave it out.
• Use the JSON types shown: image_urls is a list of strings, prompt, negative_prompt, reasoning_level and output_format are strings, seed is a whole number, enable_safety_checker is true, and image_size is "auto" or an object with whole-number width and height.
• Omit a field instead of sending null.
• Results are always returned as a URL in output.media_url; sync_mode is accepted only as false.
• Webhooks are set with the X-Webhook-URL / X-Webhook-Mode headers; webhook_url, webhook_mode and callback_url in the JSON body are rejected.
• stream is not supported: the result is delivered when the job completes.

Images and Size

• Send one to eight images in image_urls. Their order sets the tags <image-1> to <image-8> you can use in prompt.
• Set the output size in image_size as for text to image, or leave it out to let the model choose at about 4 megapixels.
• Each image you send is billed too, at no more than the size of the output: see How Billing Is Measured below.

Example: combine two images

{
  "prompt": "Place the subject of <image-1> in the setting of <image-2>",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "image_size": {
    "width": 1024,
    "height": 1024
  }
}

Example: a careful edit with high reasoning

{
  "prompt": "Replace the background of <image-1> with a quiet beach at sunset",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "reasoning_level": "high",
  "image_size": {
    "width": 1024,
    "height": 1024
  }
}

Request Headers

Response Handling

Parameter problems are caught when you submit and returned as a 400, before any hold is placed on your balance. Problems that need the model to run are reported through the status endpoint as status: "ERROR", with a message in error saying what went wrong. Failed requests are not billed — the hold is released in full.

Example error responses

A refused request returns error, a message that joins every problem found, and the same problems one by one in violations.

Missing image_urls (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_urls' is required",
  "violations": [
    "'image_urls' is required"
  ]
}

More than 8 images (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_urls' must have at most 8 items (got 9)",
  "violations": [
    "'image_urls' must have at most 8 items (got 9)"
  ]
}

An image sent as image_url (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_urls' is required; 'image_url' must be one of:  (got \"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg\"); 'image_url' is not accepted. Send the images as 'image_urls': a list of 1 to 8 public URLs or base64 data URIs.",
  "violations": [
    "'image_urls' is required",
    "'image_url' must be one of:  (got \"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg\")",
    "'image_url' is not accepted. Send the images as 'image_urls': a list of 1 to 8 public URLs or base64 data URIs."
  ]
}

A named size (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_size' must be one of [auto] or object (got \"square_hd\")",
  "violations": [
    "'image_size' must be one of [auto] or object (got \"square_hd\")"
  ]
}

More than one image per request (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'num_images' must be one of:  (got 2); 'num_images' is not supported: each request returns one image. Send one request per image.",
  "violations": [
    "'num_images' must be one of:  (got 2)",
    "'num_images' is not supported: each request returns one image. Send one request per image."
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the image from output.media_url. Treat any status other than QUEUED, PROCESSING or COMPLETED as a failure.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

cURL example

curl 'https://gateway.pixazo.ai/v2/requests/status/krea-3-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "krea-3-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-3-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Response Fields

Status Values & Flow

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

Typical workflow

1. Send the request to POST https://gateway.pixazo.ai/krea-3-edit/v1/edit.
2. Save the request_id from the 202 response.
3. Poll GET /v2/requests/status/{request_id} every 10 seconds or so, or use a Webhook instead.
4. When status is COMPLETED, download the image from output.media_url.

How Billing Is Measured

Billing is measured per megapixel (1 megapixel = 1,048,576 pixels): the output image, plus each image you send, an image counted at no more than the size of the output. The output size is set as for text to image, each edge rounded up to a multiple of 16 and to at least 256 pixels; without a size, or with "auto", it is billed at the largest size, 4,220,160 pixels. reasoning_level high adds 5 megapixels. The amount is placed as a hold when the request is submitted and released in full if the request fails. The current rate is shown in the pricing panel on this page.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Krea 2 Turbo generate request

Request Headers

Response Handling

Common status codes.

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'krea-2-turbo' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "krea-2-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-2-turbo",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/krea-2-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "krea-2-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-turbo",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/krea-2-turbo_019dxxxx/output.png"],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Status Values

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

1. Send a generate request to the API endpoint
2. Save the request_id from the response
3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Krea 2 Turbo LoRA generate request

Request Headers

Response Handling

Common status codes.

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'krea-2-turbo-lora' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "krea-2-turbo-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-2-turbo-lora",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/krea-2-turbo-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "krea-2-turbo-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-turbo-lora",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/krea-2-turbo-lora_019dxxxx/output.png"],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Status Values

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

1. Send a generate request to the API endpoint
2. Save the request_id from the response
3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive an HTTP callback when the request reaches a terminal state. Pass the webhook URL via the X-Webhook-URL header on the submit request.

Webhook Headers

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/krea-2-large/v1/text-to-image" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Webhook-URL: https://your-server.com/webhooks/krea" \
  -d '{"prompt":"a serene mountain lake","aspect_ratio":"16:9","resolution":"1K"}'

Callback Payload (Success)

{
  "request_id": "krea-2-large_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-large",
  "output": {
    "media_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/krea-2-large/019dxxxx-result.png",
    "media_type": "image/png"
  },
  "completed_at": "2026-06-23T10:00:18.000Z"
}

Callback Payload (Failure)

{
  "request_id": "krea-2-large_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-2-large",
  "error": "GENERATION_FAILED: ",
  "output": null
}

Delivery semantics

• terminal mode (default): one webhook fires when the request reaches COMPLETED or ERROR.
• sync mode: a progress webhook fires on every poll cycle (carrying the current status) plus the terminal webhook.
• Deliveries are idempotent on request_id — de-duplicate on your side.
• Respond 200 within a few seconds; non-2xx may be retried.
• The webhook URL must be HTTPS.

Request Parameters - Text to Image

Content Item Types & Limits

Note: Krea 2 Large is text-to-image only. The image inputs above (image_style_references, moodboards) are style/conditioning references — there is no image-to-image or editing mode.

Request Headers

Response Handling

Error Responses

Submit-time errors are returned synchronously; generation errors are reported on the status response (and webhook) with status: "ERROR".

// 402 Insufficient balance
{ "error": "Insufficient balance. Required amount: $0.06" }

// 400 Validation error
{ "success": false, "error": { "message": "aspect_ratio is required and must be one of: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16", "code": "VALIDATION_ERROR" } }

// Generation failure (via status / webhook)
{ "request_id": "krea-2-large_019dxxxx-...", "status": "ERROR", "model_id": "krea-2-large", "error": "GENERATION_FAILED: ", "output": null }

Retrieving Results

Poll the universal status endpoint with the request_id from the submit response until status is terminal (COMPLETED / FAILED / ERROR).

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}

cURL Example

curl "https://gateway.pixazo.ai/v2/requests/status/krea-2-large_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY"

Response (Completed)

{
  "request_id": "krea-2-large_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-large",
  "error": null,
  "output": {
    "media_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/krea-2-large/019dxxxx-result.png",
    "media_type": "image/png"
  },
  "created_at": "2026-06-23T10:00:00.000Z",
  "completed_at": "2026-06-23T10:00:18.000Z"
}

Response Fields

Status Values

Status Flow

QUEUED → PROCESSING → COMPLETED (or FAILED / ERROR)

Typical Workflow

1. POST to /krea-2-large/v1/text-to-image → receive request_id + polling_url.
2. Poll GET /v2/requests/status/{request_id} every few seconds (or use a webhook).
3. When status is COMPLETED, download output.media_url.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive an HTTP callback when the request reaches a terminal state. Pass the webhook URL via the X-Webhook-URL header on the submit request.

Webhook Headers

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/krea-2-large-fast/v1/text-to-image" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Webhook-URL: https://your-server.com/webhooks/krea" \
  -d '{"prompt":"a serene mountain lake","aspect_ratio":"16:9","resolution":"1K"}'

Callback Payload (Success)

{
  "request_id": "krea-2-large-fast_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-large-fast",
  "output": {
    "media_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/krea-2-large-fast/019dxxxx-result.png",
    "media_type": "image/png"
  },
  "completed_at": "2026-06-23T10:00:18.000Z"
}

Callback Payload (Failure)

{
  "request_id": "krea-2-large-fast_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-2-large-fast",
  "error": "GENERATION_FAILED: ",
  "output": null
}

Delivery semantics

• terminal mode (default): one webhook fires when the request reaches COMPLETED or ERROR.
• sync mode: a progress webhook fires on every poll cycle (carrying the current status) plus the terminal webhook.
• Deliveries are idempotent on request_id — de-duplicate on your side.
• Respond 200 within a few seconds; non-2xx may be retried.
• The webhook URL must be HTTPS.

Request Parameters - Text to Image

Content Item Types & Limits

Note: Krea 2 Large Fast is text-to-image only. The image inputs above (image_style_references, moodboards) are style/conditioning references — there is no image-to-image or editing mode.

Request Headers

Response Handling

Error Responses

Submit-time errors are returned synchronously; generation errors are reported on the status response (and webhook) with status: "ERROR".

// 402 Insufficient balance
{ "error": "Insufficient balance. Required amount: $0.03" }

// 400 Validation error
{ "success": false, "error": { "message": "aspect_ratio is required and must be one of: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16", "code": "VALIDATION_ERROR" } }

// Generation failure (via status / webhook)
{ "request_id": "krea-2-large-fast_019dxxxx-...", "status": "ERROR", "model_id": "krea-2-large-fast", "error": "GENERATION_FAILED: ", "output": null }

Retrieving Results

Poll the universal status endpoint with the request_id from the submit response until status is terminal (COMPLETED / FAILED / ERROR).

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}

cURL Example

curl "https://gateway.pixazo.ai/v2/requests/status/krea-2-large-fast_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY"

Response (Completed)

{
  "request_id": "krea-2-large-fast_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-large-fast",
  "error": null,
  "output": {
    "media_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/krea-2-large-fast/019dxxxx-result.png",
    "media_type": "image/png"
  },
  "created_at": "2026-06-23T10:00:00.000Z",
  "completed_at": "2026-06-23T10:00:18.000Z"
}

Response Fields

Status Values

Status Flow

QUEUED → PROCESSING → COMPLETED (or FAILED / ERROR)

Typical Workflow

1. POST to /krea-2-large-fast/v1/text-to-image → receive request_id + polling_url.
2. Poll GET /v2/requests/status/{request_id} every few seconds (or use a webhook).
3. When status is COMPLETED, download output.media_url.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Krea 2 Trainer generate request

Request Headers

Response Handling

Common status codes.

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'krea-2-trainer' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "krea-2-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "krea-2-trainer",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/krea-2-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "krea-2-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "krea-2-trainer",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/krea-2-trainer_019dxxxx/output.safetensors",
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/krea-2-trainer_019dxxxx/config.json"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Status Values

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

1. Send a generate request to the API endpoint
2. Save the request_id from the response
3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.