Input
Lower-cost official route and the default for new requests and API keys.
Default: "adaptive"
Default: "720p"
Seedance 2.0 Mini
Lightweight video generation for high-throughput, cost-sensitive workloads with text, keyframes, references, and synchronized audio.
Output
Ready for a predictionAdjust the inputs, then run the model.
Examples
View more examples ↗Pricing
Video is billed on the output tokens each task returns. The estimate changes with resolution, duration, route, and video references.
Learn more about pricing ↗All video rates
Per million output tokens, with an estimate per second of video. Requests that include a reference video (video_urls) are billed at the video reference rate.
| Resolution | officialNo reference | officialVideo reference | official-cheapNo reference | official-cheapVideo reference |
|---|---|---|---|---|
| 480p | $3.5 / 1M tokens≈ $0.045 / s | $2.1 / 1M tokens≈ $0.027 / s | $3.22 / 1M tokens≈ $0.042 / s | $1.932 / 1M tokens≈ $0.025 / s |
| 720p | $3.5 / 1M tokens≈ $0.095 / s | $2.1 / 1M tokens≈ $0.057 / s | $3.22 / 1M tokens≈ $0.087 / s | $1.932 / 1M tokens≈ $0.052 / s |
Readme
Seedance 2.0 Mini is available through MLMux with one request shape and two explicit route tiers.
High-throughput generation
Build prompt tests, commerce assets, social variations, and batch workflows with predictable latency and cost.
Core Seedance controls
Keep text, keyframe, multimodal reference, audio, ratio, resolution, and duration controls in the lighter endpoint.
Explicit routing
Use official or official-cheap on every request to select the pricing tier.
Frequently asked questions
What is Seedance 2.0 Mini?
Seedance 2.0 Mini is a video generation model from ByteDance. On MLMux you can run it in the browser or call it through one API. Lightweight video generation for high-throughput, cost-sensitive workloads with text, keyframes, references, and synchronized audio.
How do I use the Seedance 2.0 Mini API?
Create an API key in the MLMux Console, then send a POST request to https://api.mlmux.com/v1/videos/generations with the key in the Authorization header and model set to bytedance/seedance-2.0-mini. The request returns a task: poll it, or receive a webhook when the video is ready.
What can Seedance 2.0 Mini do?
Generation modes: Text to video, Image to video, First & last frame, and Multimodal reference. Clips run 4 to 15 seconds at 480p or 720p, in aspect ratios such as 16:9, 21:9, 4:3, 1:1, 3:4, and 9:16, with up to 9 reference images. Seedance 2.0 Mini can also generate audio together with the video.
How much does Seedance 2.0 Mini cost?
MLMux is pay as you go, with no subscription or monthly fee, and 1 credit equals 1 US dollar. One second of 720p Seedance 2.0 Mini video without a reference video costs about $0.087 on the default official-cheap route and $0.095 on the official route, billed on the output tokens each task actually uses. Rates for every resolution are listed in the pricing section of this page.
Can I try Seedance 2.0 Mini without writing code?
Yes. Sign in and use the playground at the top of this page to run Seedance 2.0 Mini with the same settings as the API. The API tab shows the matching request in Node.js, Python, and HTTP.
More video models
Explore all models ↗
Seedance 2.5
Next-generation video generation for longer cinematic clips, multimodal references, keyframes, and synchronized audio.
Seedance 2.0
Multimodal video generation for text, keyframes, image, video, and audio references with stable subjects and natural motion.
Seedance 2.0 Fast
Faster video generation for short-form clips, prompt iteration, keyframes, and multimodal image references.
Seedance 2.0 Mini
Lightweight video generation for high-throughput, cost-sensitive workloads with text, keyframes, references, and synchronized audio.
Seedance 2.5
Next-generation video generation for longer cinematic clips, multimodal references, keyframes, and synchronized audio.
Seedance 2.0
Multimodal video generation for text, keyframes, image, video, and audio references with stable subjects and natural motion.
Seedance 2.0 Fast
Faster video generation for short-form clips, prompt iteration, keyframes, and multimodal image references.