Seedance 2.5 Flash API

Seedance 2.5 Flash is the faster version of Seedance 2.5 from ByteDance (November 2026). ByteDance says it gets close to the full model's results at roughly twice the generation speed. It makes 4 to 30 second clips at 480p or 720p with sound - speech, effects and music - in the same pass. Three ways in: text only, an image as the first frame (with an optional last frame), or references - up to 10 images, 5 clips and 5 audio tracks.

What it's good for

• Fast drafts of a shot before you spend more on a 1080p final
• 9:16 reels and 16:9 ads with sound in one pass
• Animating a product photo or moving between two frames
• The same character or product across shots, guided by reference images

How it differs from Seedance 2.5

• Resolution. Flash tops out at 720p. The full Seedance 2.5 also does 1080p.
• References. Flash: up to 10 images, 5 clips, 5 audio tracks. Full model: 30 images, 10 clips, 10 tracks.
• Editing. The full model edits and extends existing video. Flash only makes new shots.
• Speed. Flash is meant to be about twice as fast.

Side-by-side with prices: Seedance 2.5 vs 2.5 Flash.

Prompting tips

• In reference mode, point to files in upload order: @Image 1, @Video 1, @Audio 1.
• With a start frame the aspect ratio comes from the image - describe only motion, camera and sound.
• Describe the sound you want (surf, footsteps, music). Turn off generate_audio if you don't need it.
• Check motion and framing at 480p, render the final at 720p.

FAQ

How much does Seedance 2.5 Flash cost per second?

It's from $0.264 per second at 480p, and 720p costs twice that. Reference clips add their own seconds. Failed generations are free. The calculator shows the exact amount.

Does Seedance 2.5 Flash do 1080p?

No, only 480p and 720p. For 1080p use Seedance 2.5.

Does it generate audio?

Yes, by default together with the picture. Switch it off with generate_audio.

Can I use it via API and in Claude?

Yes. The same model works in Studio, over REST /v1 and through the MCP server in Claude, Claude Code, Codex and Cursor.

How to call Seedance 2.5 Flash via API

curl https://jantaris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-2.5-flash",
  "input": {
    "prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
  }
}'

import os, time, requests

API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}

task = requests.post(f"{API}/generate", headers=H, json={
    "model": "seedance-2.5-flash",
    "input": {
        "prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
        "aspect_ratio": "16:9",
        "resolution": "720p",
        "duration": 5
    }
}).json()
while task["status"] in ("queued", "running"):
    time.sleep(3)
    task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()

print(task["status"], task["cost"], [o["url"] for o in task["output"]])

const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };

let task = await (await fetch(`${API}/generate`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "seedance-2.5-flash",
    "input": {
      "prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
      "aspect_ratio": "16:9",
      "resolution": "720p",
      "duration": 5
    }
  }),
})).json();

while (task.status === "queued" || task.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));

Parameters

The same schema is available from GET /v1/models/seedance-2.5-flash.