Seedance 2.0 Spicy
Built on the Seedance 2.0 video architecture, Seedance 2.0 Spicy combines fluid cinematic motion, precise camera control, and unrestricted uncensored visual synthesis.
Related Models
Seedance 2.0 Economy
Seedance 2.0 Economy engineered as a high-value supplementary pipeline for large-scale cost reduction, its transparent pricing model charges exclusively on output duration (in seconds), with zero fees for input videos. Whenever connected, it maintains exceptional motion stability and native audio synchronization. Due to tight compute availability dynamically fluctuating around 60%–70% (with optimal daily throughput windows spanning roughly 6–7 hours), programmatical API integration with automated retry and polling logic is strongly recommended. Seedance 2.0 Economy efficiently powers high-volume e-commerce product videos, automated social media content matrices, and low-cost ad creative pipelines.
Seedance 2.0
Seedance 2.0 offers the highest image quality. It generates 4-15 second videos with text prompts and supports various aspect ratios, audio generation, and enhanced web search capabilities.
Seedance 2.0 Fast
Seedance 2.0-fast offers rapid video generation. It generates 4-15 second videos with text prompts, supports various aspect ratios, audio generation, and enhanced web search capabilities.
Seedance 2.0 Fast Image-to-Video
Seedance 2.0 Fast Image-to-Video offers the highest image quality. It generates 4-15 second videos with text prompts and supports various aspect ratios, audio generation, and enhanced web search capabilities.
Read Me
Seedance 2.0 Spicy API
Seedance 2.0 Spicy is a video generation model developed by ByteDance. It provides the highest image quality, generating 4–15 second videos with support for multiple aspect ratios, audio generation, and enhanced web search capabilities. As a Spicy global version, it offers relaxed content policies for global users.
On the iCreat platform, Seedance 2.0 Spicy is accessed via a two-step asynchronous task API. The endpoint is https://api.icreat.ai/v1/task/submit/bytedance/seedance-2-0-global, and the task result endpoint is https://api.icreat.ai/v1/task/result. It supports 480p, 720p, 1080p, and 4K resolutions, with prices identical to the standard version, starting at $0.068 per second.
Model Positioning
Seedance 2.0 Spicy is positioned as a global, relaxed content policy version of ByteDance's flagship video generation model. It is designed for users who require fewer content restrictions while maintaining the exact same generation quality, speed, and pricing as the standard version. It is ideal for creative professionals and developers needing high-resolution video generation (up to 4K) with multilingual and multimodal reference support.
Core Capabilities
4K Native Video Generation
Seedance 2.0 Spicy supports direct output up to 4K resolution, delivering ultra-high-definition video quality for professional creative workflows.
4–15 Second Video Duration
The model can generate videos ranging from 4 to 15 seconds. The duration can be explicitly set as an integer, or set to -1 to let the model automatically select the optimal length based on the prompt.
Multimodal Reference Input
The content array accepts text, image_url, video_url, and audio_url, enabling highly controllable video generation driven by multiple input modalities.
Native Audio Generation
The model supports native audio generation via the generate_audio parameter, synchronizing sound effects and audio tracks with the generated video content.
Enhanced Web Search
The tools parameter supports enhanced web search capabilities, allowing the model to retrieve up-to-date information to inform video generation.
Adaptive Aspect Ratios
Supports 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive. When set to adaptive, the model automatically selects the most suitable aspect ratio based on the input reference media.
Pricing
| Resolution | Including reference video | Unit price (USD/sec) | 5-second cost |
|---|---|---|---|
| 480p | No | $0.077 | $0.3850 |
| 480p | Yes | $0.068 | $0.3400 |
| 720p | No | $0.164 | $0.8200 |
| 720p | Yes | $0.147 | $0.7350 |
| 1080p | No | $0.409 | $2.0450 |
| 1080p | Yes | $0.366 | $1.8300 |
| 4K | No | $0.83 | $4.1500 |
| 4K | Yes | $0.751 | $3.7550 |
Total cost = Unit price × (Output video duration + Reference video duration). A lower unit price applies when including a reference video. All prices are listed in USD based on iCreat platform pricing.
Application Scenarios
- High-definition short video generation for social media and marketing campaigns
- Professional film and animation prototyping with multimodal references
- Creative projects requiring relaxed content policies for global audiences
- Audio-visual synchronized content generation for digital advertising
- Automated video production pipelines leveraging web search for real-time information
Model Comparison
Comparison Table 1: Seedance 2.0 Series
| Model | Resolutions | Price (No reference, USD/sec) | Price (With reference, USD/sec) | Content Policy | Key Features |
|---|---|---|---|---|---|
| Seedance 2.0 Spicy | 480p/720p/1080p/4K | $0.077 / $0.164 / $0.409 / $0.83 | $0.068 / $0.147 / $0.366 / $0.751 | Relaxed (Global) | need_review, tools (web search) |
| Seedance 2.0 (Standard) | 480p/720p/1080p/4K | $0.077 / $0.164 / $0.409 / $0.83 | $0.068 / $0.147 / $0.366 / $0.751 | Standard | need_review, tools (web search) |
| Seedance 2.0 Economy | 480p/720p | $0.077 / $0.164 | N/A | Standard | Low-cost, high concurrency |
| Seedance 2.0 Fast | 480p/720p | $0.062 / $0.132 | $0.055 / $0.118 | Standard | Fast generation |
| Seedance 2.0 Mini | 480p/720p | $0.0385 / $0.082 | $0.034 / $0.0735 | Standard | Lightweight, minimal |
Comparison Table 2: Cross-Vendor Flagship Video Model Comparison
| Model | Developer | Max Resolution | Max Duration | Audio | Reference Inputs | Price |
|---|---|---|---|---|---|---|
| Seedance 2.0 Spicy | ByteDance | 4K | 15 sec (-1 auto) | Native | Multi-modal (image/video/audio) | $0.751/sec (4K w/ ref) |
| Kling V3 Omni | Kuaishou | 4K | 15 sec | Optional | Standard | $0.42 / 5 sec (Standard) |
| MiniMax H3 | MiniMax | 2K | 15 sec | Native stereo | 9 images + 3 videos + 3 audios | $0.10 (768p) |
Note: Seedance 2.0 Spicy is the only model among the three offering a 4K official discount tier (with reference at $0.751/sec) and a need_review copyright verification mechanism.
Why Choose Seedance 2.0 Spicy?
- Relaxed content policies tailored for global users, enabling broader creative freedom
- Direct 4K video output for professional-grade visual quality
- Supports multimodal references including text, images, videos, and audio
- Enhanced web search capabilities via the tools parameter for informed generation
- Flexible duration control from 4 to 15 seconds, plus automatic selection mode
- Official copyright review mechanism via need_review for compliant content generation
- Adaptive aspect ratio selection for optimized framing based on input
Specifications
| Field | Value |
|---|---|
| Model Name | Seedance 2.0 Spicy |
| Developer | ByteDance |
| Model ID | bytedance/seedance-2-0-global |
| Model Type | Video Generation Model (Spicy Global Version) |
| Endpoint | https://api.icreat.ai/v1/task/submit/bytedance/seedance-2-0-global |
| Task Result Endpoint | https://api.icreat.ai/v1/task/result |
| Authentication | Authorization: Bearer ${ICREAT_API_KEY} |
| Input Modalities | Text, Image, Video, Audio |
| Output Modalities | Video (with optional Audio) |
| Supported Resolutions | 480p, 720p, 1080p, 4k |
| Aspect Ratios | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive |
| Duration per Request | 4–15 seconds (integer) or -1 (auto) |
| Audio Generation | Supported via generate_audio |
| Special Parameters | tools, need_review, generate_audio, watermark |
| Billing Unit | USD per second |
| API Mode | Asynchronous two-step (submit → poll result) |
Architecture
Seedance 2.0 Spicy operates on an asynchronous two-step API architecture. The request body uses a top-level flat structure, where the content array and all parameters are at the same level without input/parameters nesting.
In the first step, a task is submitted to the endpoint with the content array and desired parameters. The API returns a task_id. In the second step, the client polls the task result endpoint using the same task_id. While the task is processing, the result array is empty. A polling interval of 2–5 seconds is recommended. Once the status becomes SUCCEEDED, the result array contains the generated video resource with url and download_url, along with the costUSD field indicating the total cost.
Notes
- Both steps use the same task_id; while processing, result is an empty array and polling should continue.
- FAILED is a terminal state; check request parameters or reference media if this occurs.
- If reference materials contain human faces or copyrighted IP, need_review should be set to true to submit for official review.
- The tools parameter supports enhanced web search capabilities.
- duration accepts integers from 4 to 15, or -1 for automatic selection.
- ratio supports adaptive for automatic aspect ratio selection.
- A lower unit price tier applies when including a reference video; total cost = unit price × (output duration + reference video duration).
- The request body uses a top-level flat structure; the content array and parameters are at the same level.
Frequently Asked Questions
How do I call Seedance 2.0 Spicy?
The API uses a two-step asynchronous process: submit the task to the endpoint and then poll https://api.icreat.ai/v1/task/result using the returned task_id. Authentication is done via the Authorization header with a Bearer token.
How is the cost calculated?
Total cost = Unit price × (Output video duration + Reference video duration). A lower unit price tier applies when including a reference video. Example: 1080p with a reference video, 5 seconds output + 5 seconds reference = $0.366 × 10 = $3.66.
What is the difference between the Spicy global version and the standard version?
The endpoint path differs (using the -global suffix), and the content policy is relaxed for global users. The model capabilities and pricing are exactly the same as the standard version.
When should I use need_review?
Set need_review to true when the reference materials contain human faces or copyrighted IP, submitting them for official review to ensure compliance.
What resolutions and aspect ratios are supported?
Supported resolutions are 480p, 720p, 1080p, and 4K. Supported aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive.
How do I set the duration?
The duration parameter accepts integers from 4 to 15, or -1 for the model to automatically select the optimal length. To generate audio, use the generate_audio parameter.