Kling 4.0 API, Kling Video V3 Turbo Pro API, Kling Video O3 4K & Kling Image O3 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/kling-video-v4/v1/text-to-video' \
  -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 detective in a black trench coat stands on a rooftop in the rain, looking through a telescope at the street below.", "duration": 5, "resolution": "1080p"}'

Callback Payload (success)

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Failure callback shape

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v4",
  "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

Not available on this API: multi_prompt (a list of prompts, one per shot). A request that sends it is rejected with a 400 before anything is charged.

Good to know

• Each request returns one video. batch_size, num_images, number_of_images, n, count and num_videos are rejected — send one request per video.
• Set the length with duration, in whole seconds from 3 to 30 (5 when you leave it out); seconds, num_frames, frames_per_second and music_length_ms are rejected.
• Set the resolution with resolution: 720p or 1080p, written exactly as listed (1080p when you leave it out).
• Send every field at the top level of the JSON body, with the text in prompt; parameters, input, content and text are rejected.
• Text-to-video takes no images: start_image_url, end_image_url, image_urls, image_url, image, images, reference_image_urls, first_frame_url, last_frame_url and tail_image_url are rejected (use the Image to Video or Reference to Video operation).
• Omit a field instead of sending null.
• Use the JSON types shown: duration is a whole number (5, not "5").
• 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.
• Reference videos are taken only by the Reference to Video operation; videos, video_url, video_urls and audio_url are rejected here.
• Options this API does not offer are rejected: model, multi_prompt, elements, seed, negative_prompt, cfg_scale, generate_audio, shot_type, enable_safety_checker, voice_ids and stream.

Length and Resolution

Set duration to the length you want in whole seconds, from 3 to 30; 5 applies when you leave it out. Set resolution to one of the values below; 1080p applies when you leave it out. Billing is per second of the requested duration at the rate for the requested resolution, so a longer or higher-resolution video costs more.

Example: a 10-second vertical video at 720p

{
  "prompt": "A paper boat drifts down a rain-soaked street at dusk, reflections on the water.",
  "aspect_ratio": "9:16",
  "duration": 10,
  "resolution": "720p"
}

Aspect Ratio

Set aspect_ratio to 16:9, 9:16, 1:1 or 21:9; 16:9 applies when you leave it out. It does not change the amount billed.

Example: a 21:9 wide video

{
  "prompt": "Waves roll onto a quiet beach at sunrise.",
  "aspect_ratio": "21:9",
  "duration": 5,
  "resolution": "1080p"
}

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 request refused for its parameters 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 value that is not allowed (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'resolution' must be one of: \"720p\", \"1080p\" (got \"4K\")",
  "violations": [
    "'resolution' must be one of: \"720p\", \"1080p\" (got \"4K\")"
  ]
}

A value out of range (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'duration' must be <= 30 (got 31)",
  "violations": [
    "'duration' must be <= 30 (got 31)"
  ]
}

A number sent as a string (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'duration' must be integer (got string)",
  "violations": [
    "'duration' must be integer (got string)"
  ]
}

More than one video per request (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'num_images' must be one of:  (got 2); 'num_images' is not supported: Kling 4.0 returns one video per request. Send one request per video.",
  "violations": [
    "'num_images' must be one of:  (got 2)",
    "'num_images' is not supported: Kling 4.0 returns one video per request. Send one request per video."
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the video 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/kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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/kling-video-v4/v1/text-to-video.
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 video from output.media_url.

How Billing Is Measured

Billing is measured per second of the requested duration, at the rate for the requested resolution: the amount is the per-second rate for resolution (1080p when you leave it out) times duration (5 seconds when you leave it out). 1080p videos cost more per second than 720p videos. The prompt and the aspect ratio 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/kling-video-v4/v1/image-to-video' \
  -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": "The subject turns slowly toward the camera and smiles, gentle push-in.", "start_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg", "duration": 5, "resolution": "1080p"}'

Callback Payload (success)

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Failure callback shape

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v4",
  "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

Not available on this API: multi_prompt (a list of prompts, one per shot). A request that sends it is rejected with a 400 before anything is charged.

Good to know

• Each request returns one video. batch_size, num_images, number_of_images, n, count and num_videos are rejected — send one request per video.
• Set the length with duration, in whole seconds from 3 to 30 (5 when you leave it out); seconds, num_frames, frames_per_second and music_length_ms are rejected.
• Set the resolution with resolution: 720p or 1080p, written exactly as listed (1080p when you leave it out).
• Send every field at the top level of the JSON body, with the text in prompt; parameters, input, content and text are rejected.
• Send the first frame as start_image_url and, optionally, the last frame as end_image_url; image-to-video takes no frame shape, and image_urls, aspect_ratio, image_url, image, images, reference_image_urls, first_frame_url, last_frame_url and tail_image_url are rejected.
• Omit a field instead of sending null.
• Use the JSON types shown: duration is a whole number (5, not "5").
• 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.
• Reference videos are taken only by the Reference to Video operation; videos, video_url, video_urls and audio_url are rejected here.
• Options this API does not offer are rejected: model, multi_prompt, elements, seed, negative_prompt, cfg_scale, generate_audio, shot_type, enable_safety_checker, voice_ids and stream.

Length and Resolution

Set duration to the length you want in whole seconds, from 3 to 30; 5 applies when you leave it out. Set resolution to one of the values below; 1080p applies when you leave it out. Billing is per second of the requested duration at the rate for the requested resolution, so a longer or higher-resolution video costs more.

Example: a 10-second video at 720p

{
  "start_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "prompt": "Slow orbit around the subject, soft morning light.",
  "duration": 10,
  "resolution": "720p"
}

Source Image

• Send the first frame in start_image_url: a publicly reachable https URL (recommended) or a data URI such as data:image/png;base64,.... A list of images is rejected.
• Optionally send the last frame in end_image_url, in the same form. It does not change the amount billed.
• Use PNG or JPEG files. Each image, the last frame included, must be at most 30 MB, at least 300 px on each side, with a width-to-height ratio from 2:5 to 5:2. For a large image, use an https URL rather than a data URI. Each image is downloaded when you submit: a URL that cannot be downloaded, or a very large file, may be refused at once with a 400, with nothing charged.
• Image-to-video takes no aspect_ratio: your image is the first frame. The video keeps the aspect ratio of your image.
• Describe how the video unfolds in prompt (required).
• Image-to-video output includes generated sound.

Example: a first and a last frame

{
  "start_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "end_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "prompt": "The subject waves at the camera, then turns back to the first pose.",
  "duration": 5,
  "resolution": "720p"
}

Request Headers

Response Handling

Parameter problems are caught when you submit and returned as a 400, before any hold is placed on your balance. An image that cannot be downloaded is also refused at submit with a 400, and its hold is released at once: nothing is charged. 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 request refused for its parameters returns error, a message that joins every problem found, and the same problems one by one in violations. A request refused because an image could not be downloaded or used returns error set to "Asset proxy failed", a message naming the first image that failed and why, and each failed image with its reason in failures.

Missing start_image_url (synchronous 400)

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

A value that is not allowed (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'resolution' must be one of: \"720p\", \"1080p\" (got \"1440p\")",
  "violations": [
    "'resolution' must be one of: \"720p\", \"1080p\" (got \"1440p\")"
  ]
}

A value out of range (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'duration' must be >= 3 (got 2)",
  "violations": [
    "'duration' must be >= 3 (got 2)"
  ]
}

A number sent as a string (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'duration' must be integer (got string)",
  "violations": [
    "'duration' must be integer (got string)"
  ]
}

A field this API does not accept (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'video_url' must be one of:  (got \"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg\"); 'video_url' is not accepted: reference-to-video takes reference videos as a list in 'video_urls' (up to 5).",
  "violations": [
    "'video_url' must be one of:  (got \"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg\")",
    "'video_url' is not accepted: reference-to-video takes reference videos as a list in 'video_urls' (up to 5)."
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the video 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/kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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/kling-video-v4/v1/image-to-video.
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 video from output.media_url.

How Billing Is Measured

Billing is measured per second of the requested duration, at the rate for the requested resolution: the amount is the per-second rate for resolution (1080p when you leave it out) times duration (5 seconds when you leave it out). 1080p videos cost more per second than 720p videos. The prompt and the first and last frames 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/kling-video-v4/v1/reference-to-video' \
  -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": "The person in @Image1 walks through a busy street market at dusk.", "image_urls": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"], "duration": 5, "resolution": "1080p"}'

Callback Payload (success)

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Failure callback shape

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v4",
  "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

Not available on this API: multi_prompt (a list of prompts, one per shot) and elements (characters or objects, including voices). A request that sends either is rejected with a 400 before anything is charged.

Good to know

• Each request returns one video. batch_size, num_images, number_of_images, n, count and num_videos are rejected — send one request per video.
• Set the length with duration, in whole seconds from 3 to 30 (5 when you leave it out); seconds, num_frames, frames_per_second and music_length_ms are rejected.
• Set the resolution with resolution: 720p or 1080p, written exactly as listed (1080p when you leave it out).
• Send every field at the top level of the JSON body, with the text in prompt; parameters, input, content and text are rejected.
• Send up to 9 reference images in image_urls and up to 5 reference videos in video_urls (at least one image or video) and refer to them in the prompt as @Image1, @Image2 and @Video1, @Video2 and so on; an optional first frame goes in start_image_url; end_image_url, image_url, image, images, reference_image_urls, first_frame_url, last_frame_url and tail_image_url are rejected.
• Omit a field instead of sending null.
• Use the JSON types shown: duration is a whole number (5, not "5").
• 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.
• Reference videos go in video_urls, as a list; videos, video_url and audio_url are rejected.
• Options this API does not offer are rejected: model, multi_prompt, elements, seed, negative_prompt, cfg_scale, generate_audio, shot_type, enable_safety_checker, voice_ids and stream.

Length and Resolution

Set duration to the length you want in whole seconds, from 3 to 30; 5 applies when you leave it out. Set resolution to one of the values below; 1080p applies when you leave it out. Billing is per second of the requested duration at the rate for the requested resolution, so a longer or higher-resolution video costs more.

Example: a 10-second scene at 720p

{
  "prompt": "The person in @Image1 walks along a beach at sunset.",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "duration": 10,
  "resolution": "720p"
}

References

• Send up to 9 images in image_urls (at least one), and refer to them in prompt as @Image1, @Image2 and so on, in the order of the list.
• Optionally set the first frame in start_image_url. Reference images and the first frame do not change the amount billed.
• Use publicly reachable https URLs (recommended) or data URIs, as PNG or JPEG files. Each image, the first frame included, must be at most 30 MB, at least 300 px on each side, with a width-to-height ratio from 2:5 to 5:2. For a large image, use an https URL rather than a data URI. Very many or very large inputs may be refused at once with a 400, with nothing charged; so is any URL that cannot be downloaded.
• Send up to 5 reference videos in video_urls and refer to them in prompt as @Video1, @Video2 and so on, in the order of the list. Each must be an MP4 or MOV file of 3 to 30 seconds and up to 300 MB, at least 700 and at most 4553 pixels on each side, with a width-to-height ratio from 2:5 to 5:2; together they may run at most 30 seconds. Use publicly reachable https URLs: data URIs are not accepted for videos.
• Reference videos are measured when you submit, all of them within 6 seconds. A video that cannot be read or measured in that time, a fragmented MP4 (re-save it as a regular MP4), or one outside these limits is refused at once with a 400, with nothing charged. With any reference video, the request is billed at the reference-video rate on the videos' total length plus duration.
• A reference image or first frame the model cannot use ends the request with status: "ERROR", and its hold is released.

Example: two reference images in a square frame

{
  "prompt": "The people in @Image1 and @Image2 share a meal at a street cafe.",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "aspect_ratio": "1:1",
  "duration": 6,
  "resolution": "1080p"
}

Aspect Ratio

Set aspect_ratio to auto, 16:9, 9:16, 1:1 or 21:9; 16:9 applies when you leave it out, and auto adapts the frame shape to your references. It does not change the amount billed.

Request Headers

Response Handling

Parameter problems are caught when you submit and returned as a 400, before any hold is placed on your balance. An input that cannot be downloaded is also refused at submit with a 400, and so may be very many or very large inputs; the hold is then released at once: nothing is charged. 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 request refused for its parameters returns error, a message that joins every problem found, and the same problems one by one in violations. A request refused because an image could not be downloaded or used returns error set to "Asset proxy failed", a message naming the first image that failed and why, and each failed image with its reason in failures.

Missing prompt (synchronous 400)

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

More than 9 reference images (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'image_urls' must have at most 9 items (got 10)",
  "violations": [
    "'image_urls' must have at most 9 items (got 10)"
  ]
}

A value that is not allowed (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'aspect_ratio' must be one of: \"auto\", \"16:9\", \"9:16\", \"1:1\", \"21:9\" (got \"32:9\")",
  "violations": [
    "'aspect_ratio' must be one of: \"auto\", \"16:9\", \"9:16\", \"1:1\", \"21:9\" (got \"32:9\")"
  ]
}

A length field other than duration (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'seconds' must be one of:  (got 8); 'seconds' is not supported. Set the length with 'duration' (whole seconds, 3-30).",
  "violations": [
    "'seconds' must be one of:  (got 8)",
    "'seconds' is not supported. Set the length with 'duration' (whole seconds, 3-30)."
  ]
}

More than one video per request (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'num_images' must be one of:  (got 2); 'num_images' is not supported: Kling 4.0 returns one video per request. Send one request per video.",
  "violations": [
    "'num_images' must be one of:  (got 2)",
    "'num_images' is not supported: Kling 4.0 returns one video per request. Send one request per video."
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the video 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/kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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/kling-video-v4/v1/reference-to-video.
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 video from output.media_url.

How Billing Is Measured

Without reference videos, billing is measured per second of the requested duration, at the rate for the requested resolution: the amount is the per-second rate for resolution (1080p when you leave it out) times duration (5 seconds when you leave it out). With reference videos in video_urls, the whole request is billed at the reference-video rate for the resolution instead, on the total length of the reference videos plus duration, and never on less than twice duration: a 5-second video with one 3-second reference video is billed as 10 seconds, and with one 12-second reference video as 17 seconds. The reference videos are measured from the files when you submit, and their total is rounded up to a whole second. 1080p videos cost more per second than 720p videos, with or without reference videos. The prompt, aspect ratio, first frame and reference images 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/kling-video-v4/v1/v2v-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": "Change the background of @Video1 to a sunny beach, keeping the person and the motion as they are.", "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-5s.mp4", "duration": 5, "resolution": "1080p"}'

Callback Payload (success)

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-10-09T10:04:54.387Z",
  "completed_at": "2026-10-09 10:06:21"
}

Failure callback shape

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v4",
  "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

Not available on this API: multi_prompt (a list of prompts, one per shot) and elements (characters or objects, including voices). A request that sends either is rejected with a 400 before anything is charged.

Good to know

• Each request returns one video. batch_size, num_images, number_of_images, n, count and num_videos are rejected — send one request per video.
• Set the length of the edited video with duration, in whole seconds from 3 to 30 (the length of your video, rounded up to a whole second, when you leave it out); seconds, num_frames, frames_per_second and music_length_ms are rejected.
• Set the resolution with resolution: 720p or 1080p, written exactly as listed (1080p when you leave it out).
• Send every field at the top level of the JSON body, with the text in prompt; parameters, input, content and text are rejected.
• Send the video to edit in video_url, as one https URL of an MP4 or MOV file, and refer to it in the prompt as @Video1; optional reference images go in image_urls (@Image1, @Image2 and so on). Video Editing takes no frame shape and no first or last frame: aspect_ratio, start_image_url, end_image_url, image_url, image, images, reference_image_urls, first_frame_url, last_frame_url and tail_image_url are rejected.
• Omit a field instead of sending null.
• Use the JSON types shown: duration is a whole number (5, not "5").
• 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.
• The video to edit goes in video_url, as one URL; videos, video_urls and audio_url are rejected (reference videos are taken only by the Reference to Video operation).
• Options this API does not offer are rejected: model, multi_prompt, elements, seed, negative_prompt, cfg_scale, generate_audio, shot_type, enable_safety_checker, voice_ids and stream.

Length and Resolution

Set duration to the length of the edited video in whole seconds, from 3 to 30; when you leave it out, the edited video is as long as your video, rounded up to a whole second. Set resolution to one of the values below; 1080p applies when you leave it out. Billing counts the length of your video plus the length of the edited video, at the rate for the requested resolution (see How Billing Is Measured), so a longer video or a higher resolution costs more.

Example: a 10-second edit at 720p

{
  "prompt": "Turn @Video1 into a watercolor painting.",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-5s.mp4",
  "duration": 10,
  "resolution": "720p"
}

Source Video

• Send the video to edit in video_url: one publicly reachable https URL of an MP4 or MOV file. A list of videos and data URIs are not accepted.
• The video must be 3 to 30 seconds long and at most 300 MB, at least 700 and at most 4553 pixels on each side, with a width-to-height ratio from 2:5 to 5:2.
• Your video is read and measured when you submit, within 6 seconds. A video that cannot be read or measured in that time, a malformed or fragmented MP4 (re-save it as a regular MP4), a file with no video track, a file whose length cannot be told for sure (one that starts late on its own timeline, or whose header or a timecode or subtitle track runs past its video: the error names the cause and an ffmpeg command that fixes it), a file with less than 3 seconds of actual video, or one outside these limits is refused at once with a 400, with nothing charged. Its measured length counts toward the amount billed: the file's length as ffprobe reports it, so longer audio counts too.
• Refer to the video in prompt as @Video1 and say what to change.
• Optionally send up to 10 reference images in image_urls, referred to as @Image1, @Image2 and so on, in the order of the list: publicly reachable https URLs (recommended) or data URIs, as PNG or JPEG files of at most 30 MB, at least 300 px on each side, with a width-to-height ratio from 2:5 to 5:2. They do not change the amount billed.
• Video Editing takes no aspect_ratio, start_image_url or end_image_url. The edited video keeps the aspect ratio of your video.
• Video Editing output includes sound.

Example: a new background from a reference image

{
  "prompt": "Replace the background of @Video1 with the place in @Image1.",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-5s.mp4",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "duration": 5,
  "resolution": "720p"
}

Request Headers

Response Handling

Parameter problems are caught when you submit and returned as a 400, before any hold is placed on your balance. The video is read and measured when you submit, and a video that cannot be read or measured, or is outside the limits, is refused with a 400 before any hold. A reference image that cannot be downloaded is also refused at submit with a 400, and its hold is released at once: nothing is charged. 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 request refused for its parameters returns error, a message that joins every problem found, and the same problems one by one in violations. A request refused because an image could not be downloaded or used returns error set to "Asset proxy failed", a message naming the first image that failed and why, and each failed image with its reason in failures. A video that cannot be read or measured, or is outside the limits, returns error set to "Invalid request parameters" with the reason in message and violations.

Missing video_url (synchronous 400)

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

A value that is not allowed (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'resolution' must be one of: \"720p\", \"1080p\" (got \"4K\")",
  "violations": [
    "'resolution' must be one of: \"720p\", \"1080p\" (got \"4K\")"
  ]
}

A value out of range (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'duration' must be <= 30 (got 31)",
  "violations": [
    "'duration' must be <= 30 (got 31)"
  ]
}

A field this operation does not accept (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'video_urls' must be one of:  (got [\"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-5s.mp4\"]); 'video_urls' is accepted only by reference-to-video. v2v-edit takes the one video to edit in 'video_url'.",
  "violations": [
    "'video_urls' must be one of:  (got [\"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-5s.mp4\"])",
    "'video_urls' is accepted only by reference-to-video. v2v-edit takes the one video to edit in 'video_url'."
  ]
}

More than one video per request (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'num_images' must be one of:  (got 2); 'num_images' is not supported: Kling 4.0 returns one video per request. Send one request per video.",
  "violations": [
    "'num_images' must be one of:  (got 2)",
    "'num_images' is not supported: Kling 4.0 returns one video per request. Send one request per video."
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the video 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/kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "kling-video-v4_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v4",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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/kling-video-v4/v1/v2v-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 video from output.media_url.

How Billing Is Measured

Billing is measured per second of video, on the length of your video plus the length of the edited video, and never on less than twice the length of the edited video, at the rate for resolution (1080p when you leave it out). The length of your video is measured from the file when you submit and rounded up to a whole second; the length of the edited video is duration, or the length of your video rounded up when you leave it out. For example, editing a 3-second video without duration is billed as 6 seconds, editing a 12-second video into a 5-second video as 17 seconds, and editing a 3-second video into a 10-second video as 20 seconds. 1080p videos cost more per second than 720p videos. The prompt and the reference images 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)

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 - Kling Video V3 Turbo Pro Text to Video 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 'kling-video-v3-turbo-pro-text-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-v3-turbo-pro-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v3-turbo-pro-text-to-video",
  "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/kling-video-v3-turbo-pro-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-v3-turbo-pro-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v3-turbo-pro-text-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-v3-turbo-pro-text-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "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 - Kling Video V3 Turbo Pro Image to Video generate request

Content Item Types & Limits

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 'kling-video-v3-turbo-pro-image-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-v3-turbo-pro-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v3-turbo-pro-image-to-video",
  "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/kling-video-v3-turbo-pro-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-v3-turbo-pro-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v3-turbo-pro-image-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-v3-turbo-pro-image-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "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 submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-video-o3-4k-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-text-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-video-o3-4k-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-text-to-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Text to Video

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 'kling-video-o3-4k-text-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-o3-4k-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-text-to-video",
  "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/kling-video-o3-4k-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-o3-4k-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-text-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-text-to-video_019dxxxx-xxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-04-07T10:00:00.000Z",
  "updated_at": "2026-04-07T10:02:30.000Z",
  "completed_at": "2026-04-07T10:02:30.000Z"
}

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 submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-video-o3-4k-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-image-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-video-o3-4k-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-image-to-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Video O3 4K Image to Video generate request

Content Item Types & Limits

Request Headers

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-video-o3-4k-reference-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-reference-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-reference-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-video-o3-4k-reference-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-reference-to-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Video O3 4K Reference to Video generate request

Content Item Types & Limits

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 'kling-video-o3-4k-reference-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-o3-4k-reference-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-reference-to-video",
  "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/kling-video-o3-4k-reference-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-o3-4k-reference-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-reference-to-video",
  "error": null,
  "output": { "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-reference-to-video_019dxxxx/output.mp4"], "media_type": "video/mp4" },
  "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 submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-video-to-video-reference",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-video-to-video-reference",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Video O3 4K Video to Video Reference generate request

Response

{
  "request_id": "kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Response Handling

Common status codes for Kling Video O3 4K Video to Video Reference generate request.

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 'kling-video-o3-4k-video-to-video-reference' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-video-to-video-reference",
  "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/kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-video-to-video-reference",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-video-to-video-reference_019dxxxx-xxxx/output.ext"
    ],
    "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.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-video-to-video-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-video-to-video-edit",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Video O3 4K Video to Video Edit generate request

Response

{
  "request_id": "kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Response Handling

Common status codes for Kling Video O3 4K Video to Video Edit generate request.

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 'kling-video-o3-4k-video-to-video-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-o3-4k-video-to-video-edit",
  "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/kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-o3-4k-video-to-video-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-o3-4k-video-to-video-edit_019dxxxx-xxxx/output.ext"
    ],
    "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.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-image",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-image",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Image O3 Text to Image - Kling Image API

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. Required: $0.028"
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'kling-image' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-image",
  "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/kling-image_019d7186-b8be-7937-493d-23360408abdb0"

{
  "request_id": "kling-image_019d7186-b8be-7937-493d-23360408abdb0",
  "status": "COMPLETED",
  "model_id": "kling-image",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-image_019d7186-b8be-7937-493d-23360408abdb0/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-04-09T09:15:47.804Z",
  "updated_at": "2026-04-09 09:16:53",
  "completed_at": "2026-04-09 09:16:53"
}

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 submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-image-o3-i2i_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-image-o3-i2i",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-image-o3-i2i_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-image-o3-i2i_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-image-o3-i2i",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Image O3 Image to Image - Kling Image O3 i2i API

Content Item Types & Limits

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. Required: $0.028"
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'kling-image-o3-i2i' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-image-o3-i2i_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-image-o3-i2i",
  "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/kling-image-o3-i2i_019d7185-ed08-7995-df07-aee084160a265"

{
  "request_id": "kling-image-o3-i2i_019d7185-ed08-7995-df07-aee084160a265",
  "status": "COMPLETED",
  "model_id": "kling-image-o3-i2i",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-image-o3-i2i_019d7185-ed08-7995-df07-aee084160a265/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-04-09T09:15:47.804Z",
  "updated_at": "2026-04-09 09:16:53",
  "completed_at": "2026-04-09 09:16:53"
}

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 submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-video-v2-6-standard-motion-control_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v2-6-standard-motion-control",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-v2-6-standard-motion-control_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-video-v2-6-standard-motion-control_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v2-6-standard-motion-control",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling Video v2.6 Standard Motion Control generate request

Content Item Types & Limits

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 'kling-video-v2-6-standard-motion-control' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-video-v2-6-standard-motion-control_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-video-v2-6-standard-motion-control",
  "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/kling-video-v2-6-standard-motion-control_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-video-v2-6-standard-motion-control_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-video-v2-6-standard-motion-control",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-video-v2-6-standard-motion-control_019dxxxx-xxxx/output.ext"
    ],
    "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.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-3-0-text-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-3-0-text-to-video-standard",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-3-0-text-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-3-0-text-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-3-0-text-to-video-standard",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling 3.0 Text to Video Standard generate request

Request Headers

Request Parameters - Kling 3.0 Text to Video Standard check status

Request Headers

Response Handling

Common status codes for Kling 3.0 Text to Video Standard check status.

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 'kling-3-0-text-to-video-standard' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "kling-3-0-text-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-3-0-text-to-video-standard",
  "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/kling-3-0-text-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "kling-3-0-text-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-3-0-text-to-video-standard",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-3-0-text-to-video-standard_019dxxxx-xxxx/output.ext"
    ],
    "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.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "kling-3-0-image-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "kling-3-0-image-to-video-standard",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/kling-3-0-image-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "kling-3-0-image-to-video-standard_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "kling-3-0-image-to-video-standard",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

• terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
• sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
• Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
• Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
• HTTPS required — plain http:// URLs are rejected.

Request Parameters - Kling 3.0 Image to Video Standard generate request

Content Item Types & Limits

Request Headers

Request Parameters - Kling 3.0 Image to Video Standard check status

Request Headers

Response Handling

Common status codes for Kling 3.0 Image to Video Standard check status.