SeedVR2 API: Pricing, Documentation
by Seed VR
SeedVR2 API, developers can upscale visual content to higher resolutions suitable for large displays, print, and professional production. The API handles both static images and video frames, making it a comprehensive solution for quality enhancement workflows.

Models Version
Get $5 Free Credit on First Payment
No strings attached — add funds and get $5 bonus instantly
SeedVR2 7B API Documentation
https://gateway.pixazo.ai/seedvr2-7b-upscale/image-request
Authentication
All requests require an API key passed via header.
| Header | Type | Required | Description |
|---|---|---|---|
| Ocp-Apim-Subscription-Key | string | Yes | Your API subscription key |
Image Upscale Request - SeedVR2 7B
Request Code
POST https://gateway.pixazo.ai/seedvr2-7b-upscale/image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY
{
"image_url": "https://your-cdn.com/source.png"
}
import requests
url = "https://gateway.pixazo.ai/seedvr2-7b-upscale/image-request"
headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
"image_url": "https://your-cdn.com/source.png"
}
response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/seedvr2-7b-upscale/image-request';
const headers = {
'Content-Type': 'application/json',
'Cache-Control': 'no-cache',
'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
image_url: 'https://your-cdn.com/source.png'
};
fetch(url, {
method: 'POST',
headers: headers,
body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -X POST "https://gateway.pixazo.ai/seedvr2-7b-upscale/image-request" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
--data-raw '{
"image_url": "https://your-cdn.com/source.png"
}'
Output
{
"request_id": "seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
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
| Header | Required | Default | Description |
|---|---|---|---|
X-Webhook-URL | Yes (to enable) | — | HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed). |
X-Webhook-Mode | No | terminal | terminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates. |
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": "seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "seedvr2-7b-upscale",
"error": null,
"output": {
"media_url": [
"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedvr2-7b-upscale_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": "seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "seedvr2-7b-upscale",
"error": "Description of the error",
"output": null,
"created_at": "...",
"updated_at": "...",
"completed_at": "..."
}
Delivery semantics
- terminal mode (default) — exactly one
POSTwhen the request reaches a terminal status. No callback duringPROCESSING. - sync mode —
POSTon every status poll (with delay capped at ~15s) plus a finalPOSTat terminal status. Use when you want progress updates. - Idempotency — use
request_idas your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates. - Response — respond
200 OKwithin 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 - Image Upscale Request
| Parameter | Required | Type | Default | Allowed values / range | Description |
|---|---|---|---|---|---|
| image_url | Yes | string (URI) | — | Any reachable HTTPS image URL | Source image to upscale (PNG, JPEG, or WebP). |
| upscale_factor | No | number | 2.0 | 1.0 – 8.0 | Scale multiplier applied to the source image. |
| res_h | No | integer | auto | 256 – 4096 | Target output height in pixels. Overrides upscale_factor when provided. |
| res_w | No | integer | auto | 256 – 4096 | Target output width in pixels. Overrides upscale_factor when provided. |
| output_format | No | string | png | "png", "jpg", "webp" | Encoding for the upscaled image. Use "jpg" for JPEG output — "jpeg" is not accepted. |
| noise_scale | No | number | 0.0 | 0.0 – 1.0 | Detail / noise injection strength. Higher values add more synthetic detail. |
| seed | No | integer | random | 0 – 2147483647 | Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time. |
| job_id | No | string | auto | Any client-supplied id | Optional client-provided identifier. The gateway returns its own request_id regardless. |
Content Item Types & Limits
| Type | Max | Format / Size | Description |
|---|---|---|---|
| image | 1 | JPG, PNG, WEBP | Image to upscale. |
Example Request
{
"image_url": "https://your-cdn.com/source.png",
"upscale_factor": 4.0,
"res_h": 2048,
"res_w": 2048,
"output_format": "webp",
"noise_scale": 0.0,
"seed": 12345
}
Response
{
"request_id": "seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Request Headers
| Header | Value |
|---|---|
| Content-Type | application/json |
| Cache-Control | no-cache |
| Ocp-Apim-Subscription-Key | YOUR_API_KEY |
Response Handling
Common status codes.
| Code | Meaning |
|---|---|
| 202 | Accepted — Request queued |
| 400 | Bad Request |
| 401 | Unauthorized |
| 402 | Insufficient Balance |
| 403 | Forbidden |
| 429 | Too Many Requests |
| 500 | Internal Server Error |
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 'seedvr2-7b-upscale' not found or is disabled"
}
Error via Status/Webhook
{
"request_id": "seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "seedvr2-7b-upscale",
"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 Example
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
"https://gateway.pixazo.ai/v2/requests/status/seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
Response (Completed)
{
"request_id": "seedvr2-7b-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "seedvr2-7b-upscale",
"error": null,
"output": {
"media_url": [
"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedvr2-7b-upscale_019dxxxx-xxxx/output.png"
],
"media_type": "image/png"
},
"created_at": "2026-05-12T10:00:00.000Z",
"updated_at": "2026-05-12T10:00:15.000Z",
"completed_at": "2026-05-12T10:00:15.000Z"
}
Response Fields
| Field | Type | Description |
|---|---|---|
| request_id | string | Unique request identifier |
| status | string | QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR |
| model_id | string | Model that processed the request |
| error | string|null | Error message if failed |
| output.media_url | array | URLs to the upscaled image(s) on R2 CDN |
| output.media_type | string | MIME type of the output (image/png by default) |
| created_at | string | When request was created |
| completed_at | string|null | When request completed |
| polling_url | string | Status URL (initial response only) |
Status Values
| Status | Description |
|---|---|
| QUEUED | Request accepted, waiting to be processed |
| PROCESSING | Being processed by the model |
| COMPLETED | Done — output contains the result |
| FAILED | Failed — check error field |
| ERROR | System error — not charged |
Status Flow
QUEUED → PROCESSING → COMPLETED
→ FAILED
→ ERROR
Typical Workflow
- Send an upscale request to the API endpoint
- Save the
request_idfrom the response - Poll every 5-10 seconds:
GET /v2/requests/status/{request_id} - When
statusis"COMPLETED", download fromoutput.media_url
Tip: Use X-Webhook-URL header to get a callback instead of polling.
SeedVR2 7B API Pricing
SeedVR2 3B API Documentation
https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-image/generate
Authentication
All requests require an API key passed via header.
| Header | Type | Required | Description |
|---|---|---|---|
| Ocp-Apim-Subscription-Key | string | Yes | Your API subscription key |
Upscale Image Request - SeedVR Upscale API
Request Code
POST https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-image/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
{
"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/vt_human.jpg",
"upscale_factor": 2,
"output_format": "png"
}
import requests
url = "https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-image/generate"
headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/vt_human.jpg",
"upscale_factor": 2,
"output_format": "png"
}
response = requests.post(url, json=data, headers=headers)
print(response.json())
async function upscaleImage() {
const response = await fetch('https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-image/generate', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Cache-Control': 'no-cache',
'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
},
body: JSON.stringify({
image_url: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/vt_human.jpg',
upscale_factor: 2,
output_format: 'png'
})
});
const data = await response.json();
console.log(data);
}
upscaleImage();
curl -X POST https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-image/generate \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
-d '{
"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/vt_human.jpg",
"upscale_factor": 2,
"output_format": "png"
}'
Output
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
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
| Header | Required | Default | Description |
|---|---|---|---|
X-Webhook-URL | Yes (to enable) | — | HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed). |
X-Webhook-Mode | No | terminal | terminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates. |
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": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "seedvr-upscale",
"error": null,
"output": {
"media_url": [
"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedvr-upscale_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": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "seedvr-upscale",
"error": "Description of the error",
"output": null,
"created_at": "...",
"updated_at": "...",
"completed_at": "..."
}
Delivery semantics
- terminal mode (default) — exactly one
POSTwhen the request reaches a terminal status. No callback duringPROCESSING. - sync mode —
POSTon every status poll (with delay capped at ~15s) plus a finalPOSTat terminal status. Use when you want progress updates. - Idempotency — use
request_idas your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates. - Response — respond
200 OKwithin 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 - Upscale Image Request
| Parameter | Required | Type | Default | Allowed values / range | Description |
|---|---|---|---|---|---|
| image_url | Yes | string | — | — | The input image to upscale. Must be a publicly accessible URL (HTTPS recommended). Common formats: PNG, JPEG, WebP. |
| upscale_mode | No | string | factor | `factor`, `target` | How to scale the image: `factor` multiplies the dimensions by `upscale_factor`; `target` upscales to a fixed `target_resolution`. |
| upscale_factor | No | number | 2 | 1-10 | Multiplier applied to width and height when `upscale_mode` is `factor`. Higher values produce a larger output. Values outside 1-10 are rejected. |
| target_resolution | No | string | 1080p | `720p`, `1080p`, `1440p`, `2160p` | Target output resolution. Used only when `upscale_mode` is `target`. |
| noise_scale | No | number | 0.1 | 0.0-1.0 | Noise scale for the restoration process. Lower preserves fine detail and texture; higher produces a smoother, cleaner result. |
| output_format | No | string | jpg | `jpg`, `png`, `webp` | Output image format. |
| seed | No | integer | — | — | Random seed for reproducibility. Reuse the same seed with identical settings to reproduce a result; leave empty for a different output each time. |
| sync_mode | No | boolean | false | `true`, `false` | If true, the finished image is returned inline as a data URI (base64) instead of a hosted URL, and is not stored in request history. Useful for quick tests; leave off for normal use. |
| webhook | No | string | — | — | Callback URL for completion notification. A POST request is sent with the upscaling result when processing completes. |
| webhook_events_filter | No | array | — | — | Which events trigger the webhook. Valid values: `["*"]` (all events) or `["completed"]` (success/failure only). |
Content Item Types & Limits
| Type | Max | Format / Size | Description |
|---|---|---|---|
| image | 1 | JPG, PNG, WEBP | Image to upscale. |
Example Request
{
"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/vt_human.jpg",
"upscale_factor": 2,
"output_format": "png"
}
Response
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Request Headers
| Header | Value |
|---|---|
| Content-Type | application/json |
| Cache-Control | no-cache |
| Ocp-Apim-Subscription-Key | YOUR_SUBSCRIPTION_KEY |
Response Handling
Common status codes.
| Code | Meaning |
|---|---|
| 202 | Accepted — Request queued |
| 400 | Bad Request |
| 401 | Unauthorized |
| 402 | Insufficient Balance |
| 403 | Forbidden |
| 429 | Too Many Requests |
| 500 | Internal Server Error |
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 'seedvr-upscale' not found or is disabled"
}
Error via Status/Webhook
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "seedvr-upscale",
"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 Example
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
"https://gateway.pixazo.ai/v2/requests/status/seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
Response (Completed)
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "seedvr-upscale",
"error": null,
"output": {
"media_url": [
"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedvr-upscale_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
| Field | Type | Description |
|---|---|---|
| request_id | string | Unique request identifier |
| status | string | QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR |
| model_id | string | Model that processed the request |
| error | string|null | Error message if failed |
| output.media_url | array | URLs to generated media (R2 CDN) |
| output.media_type | string | MIME type of the output |
| created_at | string | When request was created |
| completed_at | string|null | When request completed |
| polling_url | string | Status URL (initial response only) |
Status Values
| Status | Description |
|---|---|
| QUEUED | Request accepted, waiting to be processed |
| PROCESSING | Being processed by the model |
| COMPLETED | Done — output contains the result |
| FAILED | Failed — check error field |
| ERROR | System error — not charged |
Status Flow
QUEUED → PROCESSING → COMPLETED
→ FAILED
→ ERROR
Typical Workflow
- Send a generate request to the API endpoint
- Save the
request_idfrom the response - Poll every 5-10 seconds:
GET /v2/requests/status/{request_id} - When
statusis"COMPLETED", download fromoutput.media_url
Tip: Use X-Webhook-URL header to get a callback instead of polling.
SeedVR2 3B API Pricing
SeedVR2 3B API Documentation
https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-video/generate
Authentication
All requests require an API key passed via header.
| Header | Type | Required | Description |
|---|---|---|---|
| Ocp-Apim-Subscription-Key | string | Yes | Your API subscription key |
Upscale Video Request - SeedVR Upscale API
Request Code
POST https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-video/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
{
"video_url": "https://example.com/my-video.mp4",
"upscale_factor": 2
}
import requests
url = "https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-video/generate"
headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
"video_url": "https://example.com/my-video.mp4",
"upscale_factor": 2
}
response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-video/generate';
const headers = {
'Content-Type': 'application/json',
'Cache-Control': 'no-cache',
'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const body = {
video_url: 'https://example.com/my-video.mp4',
upscale_factor: 2
};
fetch(url, {
method: 'POST',
headers: headers,
body: JSON.stringify(body)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -v -X POST "https://gateway.pixazo.ai/seedvr-upscale/v1/upscale-video/generate" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
"video_url": "https://example.com/my-video.mp4",
"upscale_factor": 2
}'
Output
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
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
| Header | Required | Default | Description |
|---|---|---|---|
X-Webhook-URL | Yes (to enable) | — | HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed). |
X-Webhook-Mode | No | terminal | terminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates. |
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": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "seedvr-upscale",
"error": null,
"output": {
"media_url": [
"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedvr-upscale_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": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "seedvr-upscale",
"error": "Description of the error",
"output": null,
"created_at": "...",
"updated_at": "...",
"completed_at": "..."
}
Delivery semantics
- terminal mode (default) — exactly one
POSTwhen the request reaches a terminal status. No callback duringPROCESSING. - sync mode —
POSTon every status poll (with delay capped at ~15s) plus a finalPOSTat terminal status. Use when you want progress updates. - Idempotency — use
request_idas your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates. - Response — respond
200 OKwithin 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 - Upscale Video Request
| Parameter | Required | Type | Default | Allowed values / range | Description |
|---|---|---|---|---|---|
| video_url | Yes | string | — | — | The input video to upscale. Must be a publicly accessible URL (HTTPS recommended). Common formats: MP4, MOV, WebM. |
| upscale_mode | No | string | factor | `factor`, `target` | How to scale: `factor` multiplies the dimensions by `upscale_factor`; `target` upscales to a fixed `target_resolution`. |
| upscale_factor | No | number | 2 | 1-10 | Multiplier applied to width and height when `upscale_mode` is `factor`. Higher values produce a larger output. Values outside 1-10 are rejected. |
| target_resolution | No | string | 1080p | `720p`, `1080p`, `1440p`, `2160p` | Target output resolution. Used only when `upscale_mode` is `target`. |
| noise_scale | No | number | 0.1 | 0.0-1.0 | Noise scale for the restoration process. Lower preserves detail and grain; higher produces a smoother, cleaner result. |
| output_format | No | string | X264 (.mp4) | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Output video container/codec. |
| output_quality | No | string | high | `low`, `medium`, `high`, `maximum` | Output video quality. Higher means better quality and a larger file. |
| output_write_mode | No | string | balanced | `fast`, `balanced`, `small` | Encoder write mode for the output video. `fast` favours encoding speed, `balanced` trades speed against file size, `small` produces the smallest file. |
| seed | No | integer | — | — | Random seed for reproducibility. Reuse the same seed with identical settings to reproduce a result; leave empty for a different output each time. |
| sync_mode | No | boolean | false | `true`, `false` | If true, the finished video is returned inline as a data URI instead of a hosted URL, and is not stored in request history. Useful for quick tests; leave off for normal use. |
| webhook | No | string | — | — | Callback URL for completion notification. A POST request is sent with the upscaling result when processing completes. |
| webhook_events_filter | No | array | — | — | Which events trigger the webhook. Valid values: `["*"]` (all events) or `["completed"]` (success/failure only). |
Content Item Types & Limits
| Type | Max | Format / Size | Description |
|---|---|---|---|
| video | 1 | MP4, MOV, WEBM | Video to upscale. |
Example Request
{
"video_url": "https://example.com/my-video.mp4",
"upscale_factor": 2
}
Response
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Request Headers
| Header | Value |
|---|---|
| Content-Type | application/json |
| Cache-Control | no-cache |
| Ocp-Apim-Subscription-Key | YOUR_SUBSCRIPTION_KEY |
Response Handling
Common status codes.
| Code | Meaning |
|---|---|
| 202 | Accepted — Request queued |
| 400 | Bad Request |
| 401 | Unauthorized |
| 402 | Insufficient Balance |
| 403 | Forbidden |
| 429 | Too Many Requests |
| 500 | Internal Server Error |
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 'seedvr-upscale' not found or is disabled"
}
Error via Status/Webhook
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "seedvr-upscale",
"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 Example
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
"https://gateway.pixazo.ai/v2/requests/status/seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
Response (Completed)
{
"request_id": "seedvr-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "seedvr-upscale",
"error": null,
"output": {
"media_url": [
"https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedvr-upscale_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
| Field | Type | Description |
|---|---|---|
| request_id | string | Unique request identifier |
| status | string | QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR |
| model_id | string | Model that processed the request |
| error | string|null | Error message if failed |
| output.media_url | array | URLs to generated media (R2 CDN) |
| output.media_type | string | MIME type of the output |
| created_at | string | When request was created |
| completed_at | string|null | When request completed |
| polling_url | string | Status URL (initial response only) |
Status Values
| Status | Description |
|---|---|
| QUEUED | Request accepted, waiting to be processed |
| PROCESSING | Being processed by the model |
| COMPLETED | Done — output contains the result |
| FAILED | Failed — check error field |
| ERROR | System error — not charged |
Status Flow
QUEUED → PROCESSING → COMPLETED
→ FAILED
→ ERROR
Typical Workflow
- Send a generate request to the API endpoint
- Save the
request_idfrom the response - Poll every 5-10 seconds:
GET /v2/requests/status/{request_id} - When
statusis"COMPLETED", download fromoutput.media_url
Tip: Use X-Webhook-URL header to get a callback instead of polling.