Running a model
SkyworkText to videoSkywork SkyReels V4
Unified multimodal video model for generation, inpainting, and editing with synchronized audio
One of Auray's catalogue models: the same key, the same credits, the same job lifecycle as every other address.
Its request shape is published below. Whether it runs right now is GET /v1/catalogue's word, with no key needed: its addresses say connected for an address that runs, and a submit to any other is refused before anything is charged — described answers 501 model_not_connected, paused 503 model_disabled.
Category text-to-video · Scope video:write (or external:write on an older key) · Price Credits per second of output (counted as duration): 13.3508 for resolution=480p; 16.9918 for resolution=720p; 42.4795 for resolution=1080p. Each band has its own least and most a request is counted at. Plus 339.6 credits when the request sends inputs.referenceVideos.[].video at resolution=480p (counted as any:inputs.referenceVideos.[].video). Plus 884.375 credits when the request sends inputs.referenceVideos.[].video at resolution=720p (counted as any:inputs.referenceVideos.[].video). Plus 1179.166667 credits when the request sends inputs.referenceVideos.[].video at resolution=1080p (counted as any:inputs.referenceVideos.[].video). Plus 21.225 credits per second of output when the request sends inputs.referenceVideos.[].video at resolution=480p (counted as any:inputs.referenceVideos.[].video*duration), up to 15 seconds of output. Plus 58.958334 credits per second of output when the request sends inputs.referenceVideos.[].video at resolution=720p (counted as any:inputs.referenceVideos.[].video*duration), up to 15 seconds of output. Plus 73.697917 credits per second of output when the request sends inputs.referenceVideos.[].video at resolution=1080p (counted as any:inputs.referenceVideos.[].video*duration), up to 15 seconds of output. An MP4 or MOV clip in inputs.referenceVideos.[].video that you uploaded through POST /v1/uploads, that one of your jobs made on a catalogue model or an auray-ai/ model, or that is a file of a Cinema Studio project you can open, is held for its own length instead, where its length can be read from the file: 22.64 credits for each second it runs at resolution=480p, 58.958333 at resolution=720p, 78.611111 at resolution=1080p, rounded up to the next whole second, up to 15 seconds. Any other clip — a WebM, a file whose length cannot be read, or a clip sent by any other link — is held for the full 15 seconds; credits_quoted says which hold was taken. Quoted when you submit, at the most the request can cost; the charge settles to what the job cost and never above the quote. The submit's answer carries the quote as credits_quoted, and credits_charged says what has been taken.
#What it can do
t2v— Text → Videofirst-frame— First frame: 1 first framefirst-last— First + last frame: 1 first frame; 1 last framekeyframes— Keyframes: 2 to 8 keyframesaudio-to-video— Audio → Video: 1 track- Length: 3 to 15 seconds
- Aspect ratios: 1:1, 16:9, 3:4, 4:3, 9:16
- Resolutions: 480p, 720p, 1080p
- Prompt: up to 5,120 characters
- Sound: makes its own sound when asked to
- Priced by:
second_out(the whole rule is under Price)
Find the addresses that do any of these with GET /v1/models?operation=<id>; the openapi.json carries them as data under x-auray-capability.
#Input
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
inputs | object | no | — | |
inputs.referenceImages | object[] | no | — | |
inputs.referenceImages[].type | string | no | — | Reference mode for this group. One of "grid", "image". |
inputs.referenceImages[].audio | string | no | — | Audio input (an http(s) URL). Voice timbre reference for lip-sync. Max 15 seconds. This model may keep the voice in a recording here: a recording you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send acceptance: {"real_people": "2026-11-03"} with the request, or accept in the Auray app — and is refused 403 acceptance_required until then, before anything is charged. Or send the request without it. While uploads are paused here, a recording you upload, or a link from anywhere else, is refused 403 voice_sample_not_made_here instead, before anything is charged; send the request without it. The files the examples here send are ours, and are taken. A URL. |
inputs.referenceImages[].images | string[] | no | — | Image inputs (an http(s) URL) for this reference group. Documented range: 1 to 5. When the request also sends inputs.referenceImages[].audio, this model makes the person in a picture here speak or move: a picture you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send acceptance: {"real_people": "2026-11-03"} with the request, or accept in the Auray app — and is refused 403 acceptance_required until then, before anything is charged. A picture made here — a job's result — asks nothing. While uploads are paused here, a picture you upload, or a link from anywhere else, is refused 403 likeness_not_made_here instead, before anything is charged. The files the examples here send are ours, and are taken. |
inputs.referenceImages[].tag | string | no | — | Group identifier that links this reference to a mention in the prompt. Must start with @ (e.g. @actor1, @style). |
inputs.frameImages | string[] | no | — | Images that pin frames of the video, as a list of image URLs: one image is the first frame, two are the first and the last, and three or more anchor the first and the last with the rest spread evenly between. Each item is a plain URL; the object form that names a frame or a timestamp is not accepted here. Documented range: 1 to 8. When the request also sends inputs.referenceImages[].audio, this model makes the person in a picture here speak or move: a picture you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send acceptance: {"real_people": "2026-11-03"} with the request, or accept in the Auray app — and is refused 403 acceptance_required until then, before anything is charged. A picture made here — a job's result — asks nothing. While uploads are paused here, a picture you upload, or a link from anywhere else, is refused 403 likeness_not_made_here instead, before anything is charged. The files the examples here send are ours, and are taken. |
inputs.referenceVideos | object[] | no | — | |
inputs.referenceVideos[].type | string | no | — | Reference mode for the video. One of "reference", "extend". |
inputs.referenceVideos[].tag | string | no | — | Video reference identifier that links to a mention in the prompt. Must start with @ (e.g. @video1). |
inputs.referenceVideos[].video | string | no | — | Video input (an http(s) URL). Max 15 seconds. Minimum 1,866,240 total pixels (e.g. 1920×972). Sent as type reference, the clip runs as long as this video, whatever duration asks. This model may keep the sound of a clip here as a voice: a clip you upload with a sound track, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send acceptance: {"real_people": "2026-11-03"} with the request, or accept in the Auray app — and is refused 403 acceptance_required until then, before anything is charged. A clip you upload with no sound track asks nothing, nor does one made here. When the request also sends inputs.referenceImages[].audio, this model makes the person in a clip here speak or move: a clip you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send acceptance: {"real_people": "2026-11-03"} with the request, or accept in the Auray app — and is refused 403 acceptance_required until then, before anything is charged. A clip made here — a job's result — asks nothing. While uploads are paused here, a clip you upload with a sound track, or a link from anywhere else, is refused 403 voice_sample_not_made_here instead, before anything is charged. While uploads are paused here, a clip you upload, or a link from anywhere else, is refused 403 likeness_not_made_here instead, before anything is charged. The files the examples here send are ours, and are taken. A URL. |
positivePrompt | string | yes | — | Text prompt describing elements to include in the generated output. Documented range: up to 5,120 characters. |
width | integer | no | 1920 | Width of the generated media in pixels. |
height | integer | no | 1088 | Height of the generated media in pixels. |
resolution | string | no | "1080p" | Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input. One of "480p", "720p", "1080p". |
duration | integer | no | 5 | Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps). Not used beside a reference video of type reference: the clip then runs as long as that video. Documented range: 3 to 15. |
settings | object | no | — | |
settings.audio | boolean | no | — | Sound effect generation for the output video. |
settings.promptExtend | boolean | no | true | Automatic prompt expansion and refinement via LLM for higher visual fidelity and alignment. |
outputType | string | no | "URL" | Video output type. One of "URL". |
outputFormat | string | no | "MP4" | Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - `JPG`: Best for photorealistic images with smaller file sizes (no transparency). - `PNG`: Lossless compression, supports high quality and transparency (alpha channel). - `WEBP`: Modern format providing superior compression and transparency support. - `MP4`: Widely supported video container (H.264), recommended for general use. - `WEBM`: Optimized for web delivery. - `MOV`: QuickTime format, common in professional workflows (Apple ecosystem). - `GIF`: Animated image format (no audio), suitable for short loops or previews. - `MP3`: Compressed audio, smaller file size. - `WAV`: Uncompressed, high-quality audio. - `FLAC`: Lossless compression. - `OGG`: Open-source compressed audio format (Vorbis codec). - `SVG`: Scalable Vector Graphics. - `TIFF`: High-quality output supporting layers. - `GLB`: Binary glTF format for 3D models, including geometry, textures, and PBR materials. > [!NOTE] > **Transparency**: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., `PNG`, `WEBP`, `TIFF`). `JPG` does not support transparency. One of "MP4", "WEBM", "MOV". |
outputQuality | integer | no | 95 | Compression quality of the output. Higher values preserve quality but increase file size. Documented range: 20 to 99. |
safety | object | no | — | |
safety.checkContent | boolean | no | — | Enable or disable content safety checking. Increases total generation time. Always on: a false is sent as true. |
safety.mode | string | no | "fast" | Safety checking mode for video generation. Only fast or full is sent here: any other value is sent as fast. One of "fast", "full". |
idempotency_key | string | no | — | Your own name for this request. Send the same one twice and the second call is answered with the first request rather than charged again. Idempotency-Key: as a header is accepted as an alias — that is the spelling a retrying proxy replays, and the one to use when running a model on auray.run, where a request that outlives its connection is answered 504 and recovered by replay. Omit it and the platform mints one. 1 to 64 characters. |
acceptance | object | no | — | Your account's one acceptance, sent with the request that first needs it: a file of a real person's face or voice you upload, in a field this model makes speak or move, copies the voice of or puts into a clip, is taken once your account has accepted, one time, that you have the right to the faces and voices you use. Kept for your account before anything is charged, so no later request asks again — in any app or through the API — and asked of no file made here. You can accept in the Auray app (Account → Privacy) instead; an assistant cannot accept for you, so through MCP it is accepted in the app. |
acceptance.real_people | string | no | — | The version of the words you accept: that you have the right to every face and voice you upload, and to any voice or style you pick that sounds like a real person — it is yours, or you have permission — and that you are responsible for what you make with them. One of "2026-11-03". |
#Rules
Across fields, as the model's documentation states them. Each is judged before anything is charged — warned with a Deprecation header until enforcement starts — and listed as JSON Schema under x-auray-rules in the openapi.json.
- Send
heightwheneverwidthis sent. Sendwidthwheneverheightis sent. - Do not send
inputs.frameImagestogether withinputs.referenceImages. - Do not send
inputs.frameImagestogether withinputs.referenceVideos. - When
inputs.frameImagesis sent,inputs.referenceImagesis sent orinputs.referenceVideosis sent, do not send a request wherewidthis sent, or whereheightis sent. - When
inputs.referenceVideosis sent and every item ofinputs.referenceVideosmatches (inputs.referenceVideos[].typeis "extend" or is not sent), do not sendinputs.referenceImages. - When
widthis sent orheightis sent,widthandheightmust be one of these: 480p (16:9): width 848, height 480; 480p (9:16): width 480, height 848; 480p (~4:3): width 736, height 560; 480p (~3:4): width 560, height 736; 480p (1:1): width 640, height 640; 720p (16:9): width 1280, height 720; 720p (9:16): width 720, height 1280; 720p (~4:3): width 1088, height 832; 720p (~3:4): width 832, height 1088; 720p (1:1): width 960, height 960; 1080p (16:9): width 1920, height 1088; 1080p (9:16): width 1088, height 1920; and 3 more (15 in all). - When
resolutionis sent, send at least one ofinputs.frameImages,inputs.referenceImagesorinputs.referenceVideos. inputs.referenceImagesmust hold 1 to 3 items. In every item ofinputs.referenceImages:inputs.referenceImages[].tag,inputs.referenceImages[].typeandinputs.referenceImages[].imagesare required.inputs.referenceVideosmust hold exactly 1 item. In every item ofinputs.referenceVideos:inputs.referenceVideos[].tag,inputs.referenceVideos[].typeandinputs.referenceVideos[].videoare required.
#Example
curl -X POST https://queue.auray.run/auray-serverless/skywork/skyreels-v4 \
-H "Authorization: Bearer $AURAY_API_KEY" \
-H "content-type: application/json" \
-d '{
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}'import { createClient } from "@auray/client";
const auray = createClient(); // reads AURAY_API_KEY
const result = await auray.subscribe("auray-serverless/skywork/skyreels-v4", {
input: {
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
},
onQueueUpdate: (update) => console.log(update.status),
});
console.dir(result, { depth: null });from auray_client import Client
auray = Client() # reads AURAY_API_KEY
result = auray.subscribe(
"auray-serverless/skywork/skyreels-v4",
input={
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
},
on_queue_update=lambda update: print(update["status"]),
)
print(result){
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run_model",
"arguments": {
"address": "auray-serverless/skywork/skyreels-v4",
"input": {
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}
}
}
}const res = await fetch("https://queue.auray.run/auray-serverless/skywork/skyreels-v4", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AURAY_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}),
});
console.log(await res.json());import os, requests
r = requests.post(
"https://queue.auray.run/auray-serverless/skywork/skyreels-v4",
headers={"Authorization": f"Bearer {os.environ['AURAY_API_KEY']}"},
json={
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
},
)
r.raise_for_status()
print(r.json())package main
import (
"bytes"
"fmt"
"io"
"net/http"
"os"
)
func main() {
body := []byte(`{
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}`)
req, err := http.NewRequest("POST", "https://queue.auray.run/auray-serverless/skywork/skyreels-v4", bytes.NewReader(body))
if err != nil {
panic(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("AURAY_API_KEY"))
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer res.Body.Close()
out, _ := io.ReadAll(res.Body)
fmt.Println(res.Status, string(out))
}<?php
$ch = curl_init("https://queue.auray.run/auray-serverless/skywork/skyreels-v4");
curl_setopt_array($ch, [
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer " . getenv("AURAY_API_KEY"),
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => json_encode([
"positivePrompt" => "a brass orrery on a walnut desk, morning light from a window to the left",
], JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE),
]);
$response = curl_exec($ch);
echo curl_getinfo($ch, CURLINFO_HTTP_CODE), " ", $response, PHP_EOL;require "net/http"
require "json"
uri = URI("https://queue.auray.run/auray-serverless/skywork/skyreels-v4")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{ENV.fetch("AURAY_API_KEY")}"
req["Content-Type"] = "application/json"
req.body = {
"positivePrompt" => "a brass orrery on a walnut desk, morning light from a window to the left"
}.to_json
res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
puts res.code, res.bodyimport java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class Main {
public static void main(String[] args) throws Exception {
String body = """
{
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://queue.auray.run/auray-serverless/skywork/skyreels-v4"))
.header("Authorization", "Bearer " + System.getenv("AURAY_API_KEY"))
.header("Content-Type", "application/json")
.method("POST", HttpRequest.BodyPublishers.ofString(body))
.build();
HttpResponse<String> response = HttpClient.newHttpClient()
.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.statusCode() + " " + response.body());
}
}using System.Net.Http.Headers;
using System.Text;
using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization =
new AuthenticationHeaderValue("Bearer", Environment.GetEnvironmentVariable("AURAY_API_KEY"));
using var request = new HttpRequestMessage(HttpMethod.Post, "https://queue.auray.run/auray-serverless/skywork/skyreels-v4");
var body = """
{
"positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}
""";
request.Content = new StringContent(body, Encoding.UTF8, "application/json");
using var response = await client.SendAsync(request);
Console.WriteLine($"{(int)response.StatusCode} {await response.Content.ReadAsStringAsync()}");The same body on https://auray.run runs synchronously and answers the result — unless it usually takes longer than a run may hold its connection, which is refused 400 model_not_synchronous before anything is charged. Options — ?webhook=, ?wait=, priority and timeout headers — are on Submit a request.
#Machine contracts
- openapi.json — this page as an OpenAPI 3.1 document, public.
- llms.txt — the same, written for an agent.
