Skip to main content

Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.Browse every model at this filtering level
bytedance/seedance-2.5/reference-to-video

ByteDance's Seedance 2.5 reference-to-video builds one shot from your own material: up to 30 images, 10 video clips and 10 audio tracks, with no first frame. Output is 4 to 30 seconds at 480p, 720p or 1080p, with native audio.

From $0.074/s
Run model

Workbench

Send a request

Quickstart

Examples use the selected endpoint’s public parameter definitions. Replace the API key and example media, then send the request from your server.

SDKs & integrations
POSThttps://api.spicyapi.ai/api/v1/jobs/createTask

API authentication

Keep the API key in the server environment variable SPICY_API_KEY. Use Bearer authentication and Content-Type: application/json for JSON requests.

Authorization: Bearer $SPICY_API_KEY
Sample outputUse this example
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $SPICY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
  -d '{
  "model": "bytedance/seedance-2.5/reference-to-video",
  "input": {
    "aspect_ratio": "adaptive",
    "duration_seconds": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "resolution": "720p",
    "reference_image_urls": [
      "https://example.com/reference.png"
    ]
  }
}'

# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $SPICY_API_KEY"

Generated from this model’s input schema — the same one the API validates every request against.

Input parameters

Place these fields inside the request body’s input object. Names and types match the API. Do not assume a default when none is specified.

This model has dependencies between fields. Fields marked conditionally required depend on other inputs; see the complete JSON Schema below for the rules.

promptstringRequired

Required, and here it also does the casting. References are cited in the order you send them, so name which image is which character, what each clip contributes and what the audio is for. Briefs are accepted without review on our side; where Seedance's own layer refuses the wording, a first frame on image-to-video is the route that still gets there.

Default
Not specified
watermarkbooleanOptional

Asks the model to watermark the video as AI-generated, as described in the model’s own documentation. Off by default; switch it on when the place you publish requires AI-made footage to be labelled. No effect on price.

Default
false
return_last_framebooleanOptional

Also returns the clip’s final frame as a separate image next to the video. Send it to image-to-video as the next opening frame to chain shots without exporting a still yourself. Off by default; no effect on price.

Default
false
seedintegerOptional

Integer seed; omit it and each run draws its own. Fix it with everything else held constant to judge what a prompt edit actually changed. It is a comparison tool, not a promise of frame-identical repeats.

Default
Not specified
Constraints
minimum:0
maximum:2147483647
enable_web_searchbooleanOptional

Off by default. Switched on, the model may search the web for information related to your prompt before it renders. It does not change the price.

Default
false
output_formatstringOptional

The container of the returned video: mp4 (the default) or mov. Both carry the same picture; mov keeps the soundtrack as uncompressed PCM, so the file is a little larger and drops straight into editing software that prefers QuickTime. Does not change the price.

Default
"mp4"
Allowed values
"mp4""mov"
generate_audiobooleanOptional

On by default. Produces a native soundtrack synchronized to the picture. Even with `reference_audio_urls` supplied, turning it off means no soundtrack is rendered — reference audio shapes pacing and performance, it is not the output track. Switch it off when the edit will be scored in post.

Default
true
duration_secondsintegerOptionalAffects price

4 to 30 seconds, default 5. Note that this and the length of your reference clips are two independent contributions to the billed quantity, so maxing both is where a single request gets expensive. Validate that the references are being read the way you intended at a short length before committing to the final duration.

Default
5
Allowed values
456789101112131415161718192021222324252627282930
resolutionstringOptionalAffects price

480p, 720p or 1080p, default 720p, and it feeds the billed quantity directly. It sets the output tier only and will not sharpen low-resolution references. While you are still testing whether the references combine, work at 480p or 720p and raise the tier once the relationship reads correctly. No upscaling or enhancement tiers exist here.

Default
"720p"
Allowed values
"480p""720p""1080p"
aspect_ratiostringOptional

Defaults to `adaptive`. When the reference assets do not share a shape, adaptive lets the model find framing that accommodates all of the subjects; locking one ratio makes it more likely that a referenced person or product gets cropped. Name a shape only for a hard delivery requirement. No effect on billing.

Default
"adaptive"
Allowed values
"21:9""16:9""4:3""1:1""3:4""9:16""adaptive"
reference_audio_urlsarray<string>Conditionally required

Up to 10 reference audio files, 2 to 30 seconds each with a combined length of no more than 30 seconds (the previous generation allowed 3 files totalling 15 seconds). They give the model a sonic anchor — delivery, tempo, a musical phrase — which the motion and the cut points align to. Distinct from `generate_audio`: what you supply here is an input, while whether the finished clip carries a soundtrack is still decided by `generate_audio`.

Default
Not specified
Constraints
maxItems:10
reference_video_urlsarray<string>Conditionally requiredAffects price

Up to 10 reference clips supplying motion, pacing or camera language. Each runs 2 to 30 seconds, with a combined length of no more than 30 seconds — the previous generation allowed 3 clips totalling 15 seconds, so the reference budget has doubled and a complete camera move can be referenced whole. The length of a reference clip still counts toward the billed quantity, though: not as a tier switch but as a linear multiplier of the same kind as `duration_seconds`, so a wider budget is not a reason to upload the whole take out of habit. Write the prompt as a new shot that borrows from these clips. Wording that asks to edit the footage itself — remove, replace or restyle something in it — makes Seedance treat the task as a video edit, which needs a duration setting this endpoint does not accept, so the task fails. Asking it to continue a clip also fails unless `aspect_ratio` stays on `adaptive`.

Default
Not specified
Constraints
maxItems:10
reference_image_urlsarray<string>Conditionally required

Up to 30 reference images, used to hold a character, a style or a set — the previous generation allowed only 9, so there is real room here. Two or three angles of the same character usually work better than ten near-identical frames. Note that this endpoint has no first- or last-frame parameter: reference mode and frame mode are mutually exclusive, so switch to image-to-video when the opening frame must be exact. Seedance's own input check may turn away a reference photo or clip that shows a real, identifiable person's face. Each side must be between 300 and 6000 pixels; a smaller plate is rejected by the input check before you are charged.

Default
Not specified
Constraints
maxItems:30

Track the task

HTTP 202 means the task was accepted, not completed. Save the returned taskId and query that task. Do not create another task while waiting for its result.

Accepted response
HTTP/1.1 202 Accepted
Location: /api/v1/jobs/recordInfo?taskId=job_01k3m8x9q2z4v7n5p6r8s0t1w3

{
  "code": 200,
  "msg": "success",
  "request_id": "req_example_create",
  "data": {
    "taskId": "job_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "state": "queued",
    "estimatedCost": "0.750000"
  }
}

The accepted response includes the estimate so your app can show the same amount in task history and billing.

Read the job
curl --get "https://api.spicyapi.ai/api/v1/jobs/recordInfo" \
  --data-urlencode "taskId=$TASK_ID" \
  -H "Authorization: Bearer $SPICY_API_KEY"

Start polling at about 2 seconds and gradually increase the interval. Stop at a terminal state. After a connection failure, query the original taskId. Retry creation only with the original idempotency key and body.

Or let the callback find you
import { verifyWebhook } from "@spicyapi/sdk";

// express.raw keeps the bytes we signed; express.json never matches.
app.post("/hooks/spicy", express.raw({ type: "application/json" }), (req, res) => {
  const { payload } = verifyWebhook({
    rawBody: req.body,
    timestamp: req.header("X-Webhook-Timestamp"),
    signature: req.header("X-Webhook-Signature"),
    payloadVersion: Number(req.header("X-Webhook-Payload-Version")),
    secret: process.env.SPICY_WEBHOOK_SECRET,
  });
  res.status(200).end();
  void handleFinishedTask(payload);
});

Pass callBackUrl when you create the task and the finished record is POSTed to you — no polling loop at all. Every delivery carries X-Webhook-Timestamp, X-Webhook-Signature and X-Webhook-Payload-Version. The signature is a base64 HMAC-SHA256 over taskId.timestamp.sha256(body), so it must be checked against the raw bytes: parsing the JSON and re-serialising it changes them and the check will fail. Failed deliveries are retried, so the same taskId can arrive twice — make the handler idempotent. Answer 2xx first and do the work afterwards; a slow handler is treated as a failed delivery.

Read the result

Consume output only when state is succeeded. On failure, use errorCode, errorMessage and request_id to investigate. Example costs and states do not represent an actual bill.

Completed response example
{
  "code": 200,
  "msg": "success",
  "request_id": "req_example_record",
  "data": {
    "taskId": "job_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "bytedance/seedance-2.5/reference-to-video",
    "state": "succeeded",
    "output": {
      "assets": [
        {
          "key": "tasks/2026/08/28/job_01k3m8x9q2z4v7n5p6r8s0t1w3/3f7a1c9e5b2d48f0a6c1e3d5b7f9a1c3.mp4",
          "mime": "video/mp4",
          "url": "https://example.r2.cloudflarestorage.com/results/job_01k3m8x9q2z4v7n5p6r8s0t1w3/result.mp4?X-Amz-Signature=SIGNATURE_FROM_RESPONSE",
          "expiresAt": "2026-08-28T12:20:08.000Z"
        }
      ]
    },
    "cost": "0.750000",
    "settled": true,
    "createdAt": "2026-08-28T12:00:00Z",
    "completedAt": "2026-08-28T12:00:30Z"
  }
}

For each available asset, open or download assets[].url directly without an API Authorization header. The signed URL expires at expiresAt; poll the task again to refresh it while the asset remains within its retention period. A pending or unavailable asset has no URL. Treat signed URLs as private.

SDKs & integrations

Use SpicyAPI in your app, terminal, AI assistant or visual workflow. Choose a setup guide below.

SDKs
TypeScript · Python · Go · PHP · Java
CLI
Terminal commands and automation scripts.
MCP
Claude Code · Cursor · Codex
Agent Skill
Reusable instructions for your AI assistant.
n8n
Self-hosted community nodes and importable HTTP Request templates for n8n Cloud.
ComfyUI
Image, video and audio workflows on a node canvas.

More integrations

SillyTavernTelegram / DiscordApp proxyOpenAI SDKLangChainVercel AI SDK
Browse ready-to-use workflows

Use it in ComfyUI

Install the SpicyAPI nodes from ComfyUI Manager or with the command below, then search for Seedance 2.5 · Reference to Video on the canvas. The node has the same options as this page and shows its price before it runs.

cd ComfyUI/custom_nodes
git clone https://github.com/spicyapi-ai/comfyui-spicyapi
Workflow examplesSetup guideSource on GitHub