Seedance (ByteDance) API
ByteDance's Seedance 2.0 — realistic video generation with multi-shot consistency
Full Seedance (ByteDance) price list and cost examples →
Overview
Seedance 2.0 is ByteDance's flagship AI video model, optimized for fast realistic generation with strong multi-shot consistency. Access all Seedance variants (1080p/720p/480p, fast/quality modes) through AI Generate.
All 38 Seedance (ByteDance) variants & pricing
Every variant is accessible via the same API endpoint. Switch variants by changing the model parameter. No extra setup.
Use Seedance (ByteDance) via API
Example call with the default variant. Replace model with any slug from the table above.
curl https://aimarcusimage.eu/api/v1/jobs/createTask \
-H "Authorization: Bearer sk-aig-..." \
-H "Content-Type: application/json" \
-d '{
"model": "bytedance-bytedance-seedance-v1-lite-text-to-video-480p",
"input": {
"prompt": "a golden retriever running through autumn leaves, cinematic",
"aspect_ratio": "16:9",
"duration": 5
}
}'
FAQ
How much does Seedance (ByteDance) cost?
Pricing starts at $0.0140 per second for the most affordable variant. You pay per call from your credit balance — no monthly subscription, no minimum commitment. Starter top-up is $10 → 1,430 credits.
Is this an official ByteDance API?
AI Generate is an AI model aggregator that routes calls to ByteDance's upstream API. You get the exact same model outputs with simpler billing (pay per call, no contracts), one API key for 501 models, and the same create-task request shape across all providers.
Can I use Seedance (ByteDance) in production?
Yes. Each API key is rate-limited to 20 requests per 10 seconds. Results are asynchronous: poll /api/v1/jobs/recordInfo with the taskId, or pass a callBackUrl in the create-task body to receive a POST when the task finishes. Daily and monthly spend caps in dashboard settings stop runaway usage.
Which Seedance (ByteDance) variant should I pick?
For first tests, start with the cheapest variant (lowest "Price USD" in the table above). Upgrade to higher-resolution or "Quality" tiers only when you have validated prompts. The Playground runs the most popular models from your browser; every variant in the table is available through the API at the price shown.