Seedance 2.0 API
Try Seedance 2.0 before you integrate the API.
Test Seedance 2.0 output quality, estimate credit usage, and generate a sample before you formally integrate.
Create a Sample
Pick a video mode, enter your prompt, and set the parameters.Off by default. Turn on to relax content restrictions (billed at +10%); illegal and prohibited content is always blocked.
Know your testing cost before you add credits.
Start from the cost of a single sample and pick a testing budget. Expand for detailed rates.
First Test Cost
Fast Text-to-Video - 5s - 480pOne 5s 480p Fast sample
About 27 tests with $10 in credits.
Iterate prompts in Fast 480p to save credits, then switch to 720p or 1080p for the final quality check.
Testing Budget Guide
Pick an amount based on how many tests you expect.Good for a first validation.
Good for prompt iteration.
Good before production integration.
Common Cost Examples
Estimated cost for a 5-second output. Final cost may vary by mode, references, and add-ons.
Model Pricing
| Mode | 480p | 720p | 1080p | 4K | Billing |
|---|---|---|---|---|---|
| Text-to-VideoStandard | $0.092/s6.2775 cr/s | $0.199/s13.5 cr/s | $0.496/s33.75 cr/s | $1.012/s68.85 cr/s | Output video seconds |
| Image-to-VideoStandard | $0.092/s6.2775 cr/s | $0.199/s13.5 cr/s | $0.496/s33.75 cr/s | $1.012/s68.85 cr/s | Output video seconds |
| Reference-to-VideoImage or audio reference | $0.092/s6.2775 cr/s | $0.199/s13.5 cr/s | $0.496/s33.75 cr/s | $1.012/s68.85 cr/s | Output video seconds |
| Reference-to-VideoVideo reference | $0.056/s3.834 cr/s | $0.121/s8.2215 cr/s | $0.302/s20.52 cr/s | $0.625/s42.525 cr/s | Input + output seconds |
Billed by video duration and resolution. Video reference input may be billed by input + output duration.
What Seedance 2.0 can create.
Generate 4-15 second videos from text, images, or reference material, with real-person-style subjects, product scenes, camera motion, and synchronized audio.
Effect Preview
Product Ad
Anthropomorphic Pet Chat
Street Documentary Style
What You Can Do
Use Reference Images or Video
Generate Video with Audio
Real-Person-Style Video
Short Dramas & Stories
Seedance 2.0 vs other video models
| Feature | Seedance 2.0 | Kling 3.0 | Happy Horse |
|---|---|---|---|
| Price (720p 5s) | ~$0.99 | ~$0.40 | ~$0.69 |
| Video + Audio | Yes | No | No |
| Reference Input | Image + Video + Audio | Image only | Image + reference images |
| Duration | 4-15s | 3-15s | 3-15s |
| Real-Person Style | Yes | Limited | Yes |
| Best For | Production, ads, UGC | Creative, animation | Real-person style, video editing, multi-reference |
Key Details
One Model, Many Modes
Generate video from text, images, or reference material — all on the same Seedance 2.0 API page.
Fast vs Standard
Use Fast mode for cheap drafts, then switch to Standard mode when you are ready to check the final quality.
Prompting Tips
Describe the subject, camera motion, lighting, visual style, scene continuity, and the audio you want.
Why use Seedance 2.0 through EvoLink
Clear Costs Before You Generate
See estimated credits, per-second pricing, and sample cost before you add credits.
Unified API
One API key works across Seedance, Kling, Sora, Veo, image, and LLM models.
Unified Balance
Track credits, spending, and model usage in one console.
Task Status Tracking
See whether a video task is submitted, processing, completed, or failed.
Real-Person-Style & UGC Video
Test product ads, creator clips, spokesperson videos, and short UGC scenes.
Seedance Model Family

Seedance 2.5
Next-generation Seedance route for teams evaluating longer clips, stronger reference control, and future production migration.
View →
Seedance 2.0 Mini
Lightweight, lower-cost Seedance route for drafts, ad variants, prompt testing, and high-volume iteration.
View →
Seedance 1.5 Pro
Previous generation with excellent motion quality. Great for non-realistic creative video.
View →Other video models on EvoLink




FAQ
How much does Seedance 2.0 cost?
Billed by video duration and resolution. A 5s 480p Fast sample is about 25.4 credits, roughly $0.37.
Can I preview before integrating the API?
Yes. Test output quality and estimate credits in the Playground before integrating the API.
What if a generation fails?
You can check task status and billing details in the console. Failed tasks are not charged.
Does it support image / reference input?
Yes. Seedance 2.0 supports Text-to-Video, Image-to-Video, Reference-to-Video, and Fast mode.
Is Seedance 2.1 available yet?
Not confirmed yet. We will update this page once it is officially released.
Where do I go after topping up?
Return to the Playground to keep testing, or create an API key in the console to start integrating.
What is the difference between Fast and Standard mode?
Fast mode is quicker and cheaper, ideal for prompt iteration and drafts; Standard mode offers higher quality for final output.
Do generated videos have a watermark?
Videos generated through the EvoLink API have no watermark and can be used commercially.
Which video resolutions are supported?
We support 480p, 720p, and 1080p. We recommend iterating quickly in 480p, then rendering the final at a higher resolution.
API Reference
Select endpoint
Authentication
All APIs require Bearer Token authentication.
Authorization:
Bearer YOUR_API_KEY/v1/videos/generationsCreate Text-to-Video
Generate video from text prompts using Seedance 2.0. Supports optional web search for enhanced real-time content.
Now supports AIGC-generated realistic human materials.
Asynchronous processing — use the returned task ID to query status. Video links are valid for 24 hours.
Request Parameters
modelstringRequiredDefault: seedance-2.0-text-to-videoFixed value: seedance-2.0-text-to-video
seedance-2.0-text-to-videopromptstringRequiredText prompt describing the video to generate. Supports Chinese and English.
Notes
- Chinese: ≤ 500 characters
- English: ≤ 1000 words
- This model does NOT support image_urls, video_urls, or audio_urls
A cinematic drone shot over a coastal city at golden hourdurationintegerOptionalDefault: 5Video duration in seconds.
| Value | Description |
|---|---|
| 4-15 | Any integer between 4 and 15 |
Notes
- Duration directly affects billing
8qualitystringOptionalDefault: 720pVideo resolution.
| Value | Description |
|---|---|
| 480p | Lower resolution, lower cost |
| 720p | Standard (default) |
| 1080p | High quality |
| 4k | Ultra HD 4K (highest cost) |
720paspect_ratiostringOptionalDefault: 16:9Video aspect ratio.
| Value | Description |
|---|---|
| 16:9 | Landscape (3840×2160 / 1920×1080 / 1280×720 / 864×496) |
| 9:16 | Portrait (2160×3840 / 1080×1920 / 720×1280 / 496×864) |
| 1:1 | Square (2880×2880 / 1440×1440 / 960×960 / 640×640) |
| 4:3 | Standard (3326×2494 / 1664×1248 / 1112×834 / 752×560) |
| 3:4 | Portrait standard (2494×3326 / 1248×1664 / 834×1112 / 560×752) |
| 21:9 | Ultrawide (4398×1886 / 2206×946 / 1470×630 / 992×432) |
| adaptive | Auto-select based on prompt |
16:9generate_audiobooleanOptionalDefault: trueWhether to generate synchronized audio. No extra charge.
Notes
- Place dialogue within double quotes in prompt for better results
truecontent_filterbooleanOptionalDefault: trueContent filter, enabled by default. Setting it to false relaxes content restrictions (billed at +10%); illegal and prohibited content is always enforced regardless.
truemodel_params.web_searchbooleanOptionalDefault: falseWeb search — model autonomously decides whether to search internet content based on the prompt.
Notes
- May increase latency
- Fees are only charged when searches are actually triggered
- Multiple searches may occur once enabled
- Wrapped inside model_params object
falsecallback_urlstringOptionalHTTPS callback URL for task completion notification.
Notes
- Triggered on completion, failure, or cancellation
- HTTPS only, max 2048 chars
https://your-domain.com/webhooks/video-done