Seedance 2.5

• Model id: seedance-2.5
• Makes: videos
• From: 30 credits ($0.30)
• Routes: 2

Writing promptsCopy Anchor Link

• Name every file and say what it's for: "img1 walks through the city from img2, moving like the dancer in video1, to the rhythm of audio1." See Files in prompts.
• With reference_mode: "frames" you set the first and last frame. With ingredients, the default, the model uses the files freely.
• Sound is generated with the picture, and you can steer it in the prompt.

Good to knowCopy Anchor Link

• Video among the files costs much more. Those prices have with_video: true, because the seconds of your video are billed too. All videos together: up to 30 s. Photos and audio files don't change the price.
• Reference videos showing a person may be refused as a real person, even when they're AI-made. Video without people, or a photo, is safer.
• Long clips take minutes: 5 to 10 is normal. Poll.

Call itCopy Anchor Link

# A new Idempotency-Key for each new thing you want made, the same one when you retry it.
curl https://api.nocamclub.com/v1/generations \
  -H "Authorization: Bearer $NOCAM_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: seedance-2.5-$(date +%s)" \
  -d '{
  "model": "seedance-2.5",
  "input": {
    "prompt": "img1 walks along a rainy street at night, neon signs, slow camera move",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "9:16",
    "images": [
      "https://docs.nocamclub.com/examples/mascot.jpg"
    ]
  }
}'

Then poll GET /v1/generations/{id} until it finishes. See Generations.

OptionsCopy Anchor Link

Any other field is refused. How files work: Uploads and Files in prompts.

PricesCopy Anchor Link

In credits (1 credit = $0.01), as of 2026-11-07. For the current list: GET /v1/models/seedance-2.5.

With a video among the files (with_video):