モデル/ByteDance/Seedance 2.5 Fast
ByteDancevideo3つのルート

Seedance 2.5 Fast API

Seedance 2.5 on dedicated, faster compute: your renders start straight away on capacity kept for this model instead of queueing behind shared traffic, so each video comes back sooner and large batches run side by side. 480p, 720p and 1080p, up to 30 seconds with sound, reference images and audio, and first and last frames.

seedance-2.5-fastClaudeに接続APIキーを取得

料金 動画1秒あたり

解像度1秒あたり
480p$0.10lowest10クレジット
720p$0.24524.5 credits
1080p$0.5555クレジット
480p+動画入力あり$0.066クレジット
720p+動画入力あり$0.1515クレジット
1080p+動画入力あり$0.3434クレジット

動画1秒あたりのクレジットで課金されます(100クレジット = $1、1クレジット単位に切り上げ)。課金は、成功したルートに対する1回のみです。失敗した試行は$0.00です。

リクエスト

# One Idempotency-Key per request, made once and sent again with every resend of it
KEY=$(uuidgen)

# 1. Submit. max_cost_usd is your cap: the most this may cost (it lists at $0.98).
#    No id after a timeout, a 429 or a 5xx? Run step 1 again: the same $KEY never makes a second one.
RESP=$(curl -s https://api.revana.si/v1/generations \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $KEY" \
  -d '{
    "model": "seedance-2.5-fast",
    "input": {
      "prompt": "A slow dolly shot through a neon-lit night market in the rain, steam rising from food stalls",
      "resolution": "720p",
      "duration": 4,
      "aspect_ratio": "16:9",
      "audio": true
    },
    "max_cost_usd": 1.5
  }')
ID=$(echo "$RESP" | jq -r '.id // empty')
echo "${ID:-no id: ${RESP:-no answer}}"

# 2. Poll it until status is "succeeded" or "failed". A failed one is free; to try it again,
#    make a new key first (KEY=$(uuidgen)): the old one answers with the failure.
curl -s https://api.revana.si/v1/generations/${ID:?no id from step 1} \
  -H "Authorization: Bearer $REVANA_API_KEY"

# 3. Download the file once it has succeeded
curl -L https://api.revana.si/v1/generations/${ID:?no id from step 1}/content \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -o out.mp4

REVANA_API_KEY にキーを設定してください。完全なリファレンスはクイックスタートにあります。

オプション

タスク
テキストから動画画像から動画最初と最後のフレーム参照から動画動画から動画
解像度
480p720p1080p
長さ
4 s5 s6 s7 s8 s9 s10 s11 s12 s13 s14 s15 s16 s17 s18 s19 s20 s21 s22 s23 s24 s25 s26 s27 s28 s29 s30 s
アスペクト比
16:99:161:14:33:421:9adaptive
音声
対応
入力画像
最大30枚
課金単位
動画1秒あたり
モデルID
seedance-2.5-fast

3つのルート

すべてのリクエストは、最も安いルートから始まります。失敗した場合、ジョブは自動的に次のルートに移ります。

About the Seedance 2.5 Fast API

How much does the Seedance 2.5 Fast API cost?

Seedance 2.5 Fast costs from $0.10 per second of video on Revana (480p: $0.10; 720p: $0.245; 1080p: $0.55; 480p + with video input: $0.06; 720p + with video input: $0.15; 1080p + with video input: $0.34). You pay in prepaid credits, 100 credits to the dollar, with no subscription or monthly minimum. A generation that fails costs nothing.

How do I call Seedance 2.5 Fast from code?

Send POST https://api.revana.si/v1/generations with {"model": "seedance-2.5-fast", "input": {...}} and your Revana API key as a Bearer token, poll GET /v1/generations/{id} until it succeeds, then download GET /v1/generations/{id}/content. Every model on Revana takes the same request shape.

What happens if a Seedance 2.5 Fast generation fails?

Revana has 3 routes for Seedance 2.5 Fast. A job starts on the cheapest and moves to the next automatically if one fails. You are charged once, only for the route that delivers. A failed generation costs $0.00.

What can Seedance 2.5 Fast do on Revana?

Seedance 2.5 Fast supports text to video, image to video, first + last frame, reference to video and video to video, resolutions 480p, 720p, 1080p, durations 4 to 30 seconds, aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive, generated audio and up to 30 input images. A value it does not offer is refused with 422 before anything is charged.

Can my AI agent use Seedance 2.5 Fast?

はい。Claude、ChatGPT、Cursor、CodexにRevanaのMCPサーバー(https://revana.si/api/mcp)を接続するか、エージェントにREST APIを呼び出させます。エージェントは、モデルの一覧表示、無料の見積もり、あなたのクレジットでの生成を行えます。

類似のモデルと比較

エージェント向けのMarkdown版もあります。すべてのモデルと料金はmodels.jsonにあります。