modelstringSelects the route — one of the six model IDs above.
Access ByteDance Seedance 2.0 through EvoLink's unified video API. Test Standard and Fast text-to-video, image-to-video, and reference-to-video first.
Next in the family: Seedance 2.5 is now live — watch official samples with full prompts, then generate in the playground.
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 here. The API still supports it — send content_filter: false to relax content restrictions (billed at +10%). Illegal and prohibited content is always blocked.
Results are kept for 24 hours — download anything you want to keep.
Start from the cost of a single sample and pick a testing budget. Expand for detailed rates.
-25%Limited-time offer — Seedance 2.0 Fast is 25% off through October 6, 2026 (UTC+8). Discount included below; Standard pricing is unchanged.
First Test Cost
Fast Text-to-Video, 4s at 480p — the cheapest possible request, no reference filesOne 4s 480p Fast sample
About 42 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
At the first-test settings: Fast 4s at 480pGood for a first validation.
Good for prompt iteration.
Good before production integration.
Estimated cost for a 5-second output. Final cost may vary by mode, references, and add-ons.
| Mode | 480p | 720p | 1080p | 4K | Billing |
|---|---|---|---|---|---|
| Text-to-VideoStandard | $0.093/s6.2775 cr/s | $0.199/s13.5 cr/s | $0.497/s33.75 cr/s | $1.013/s68.85 cr/s | Output video seconds |
| Image-to-VideoStandard | $0.093/s6.2775 cr/s | $0.199/s13.5 cr/s | $0.497/s33.75 cr/s | $1.013/s68.85 cr/s | Output video seconds |
| Reference-to-VideoImage or audio reference | $0.093/s6.2775 cr/s | $0.199/s13.5 cr/s | $0.497/s33.75 cr/s | $1.013/s68.85 cr/s | Output video seconds |
| Reference-to-VideoVideo reference | $0.057/s3.834 cr/s | $0.121/s8.2215 cr/s | $0.302/s20.52 cr/s | $0.626/s42.525 cr/s | Input + output seconds |
Billed as output duration (seconds) × the per-second resolution rate; audio adds no extra cost. When Reference-to-Video receives a video input, the lower video-reference rate applies and input duration is billed too: billable input = max(total input video duration, output duration), cost = (billable input + output) × rate.
| Item | Use Case | Price | Credits |
|---|---|---|---|
| Web SearchPer search | Use when the prompt needs current events, products, or real-world references. | $0.0006 / search | 0.04 cr |
Most first tests only pay the video generation fee. Logged-in users can view live pricing in the console.
Generate 4-15 second videos from text, images, or reference material, with real-person-style subjects, product scenes, camera motion, and synchronized audio.
Six routes on one endpoint: Standard for final quality, Fast for cheap drafts. Copy a model ID and pass it as the model field in the request body.
seedance-2.0-text-to-videoGenerate 4–15 second videos with synchronized audio from a text prompt; optional web search for time-sensitive topics.
seedance-2.0-image-to-videoUse 1 image as the first frame, or 2 images as first and last frames, to control composition and motion.
seedance-2.0-reference-to-videoCombine up to 9 images, 3 videos, and 3 audio tracks to control character, camera, rhythm, and style.
seedance-2.0-fast-text-to-videoSame request shape at a lower rate, limited to 480p / 720p — built for prompt iteration and drafts.
seedance-2.0-fast-image-to-videoLower-cost image-to-video drafts with the same 1–2 first/last-frame input rules.
seedance-2.0-fast-reference-to-videoLower-cost multimodal reference route with the same reference limits as Standard.
modelstringSelects the route — one of the six model IDs above.
promptstringRequired. Up to about 500 Chinese characters or 1,000 English words.
durationinteger4–15 seconds, default 5. Billing follows output duration.
qualitystringStandard: 480p, 720p, 1080p, or 4k. Fast: 480p or 720p. Default 720p.
aspect_ratiostringadaptive (default), 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9.
generate_audiobooleanDefault true — synchronized audio at no extra charge.
content_filterbooleanDefault true. false relaxes review and bills at +10%; illegal content is always blocked.
image_urlsstring[]Image-to-Video: 1–2 first/last-frame images. Reference-to-Video: up to 9. jpeg/png/webp, 300–6000 px, ≤30MB each.
video_urlsstring[]Reference-to-Video only: up to 3 videos, 2–15s each and ≤15s total, mp4/mov, ≤50MB. Input duration is billed.
audio_urlsstring[]Reference-to-Video only: up to 3 tracks, wav/mp3. Requires at least one image or video reference.
model_params.web_searchbooleanText-to-Video routes only. Enables web search; billed for each search the model runs.
callback_urlstringPublic HTTPS URL notified when the task reaches a final state; keep the task ID for polling.
All six routes post to /v1/videos/generations; the model field selects the route and each route validates its own parameter whitelist. Full constraints and response fields are in the API tab.
Use the EvoLink API for product integration and batch jobs, or call it from Codex, Claude, or Gemini for fast creative and development workflows. Both paths share the same EvoLink API key, balance, model routes, and task history.
Best for: product backends, batch jobs, automated workflows
Call EvoLink’s unified video API from your server and control the model ID, parameters, task queue, callbacks, and result storage.
Best for: creative and development tasks in Codex, Claude, and Gemini
Give the Agent your output goal, assets, and acceptance criteria. It can choose the route, assemble the request, track the task, and return the result without requiring you to hand-code every step.
This example shows the shortest runnable flow: create a task, save the returned task ID, then poll or wait for an HTTPS callback. Open the API tab for the complete parameter and response reference.
curl -X POST https://api.evolink.ai/v1/videos/generations \
-H "Authorization: Bearer $EVOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0-text-to-video",
"prompt": "A macro lens on a glass frog, focus shifting to its beating heart",
"duration": 8,
"quality": "720p",
"aspect_ratio": "16:9",
"generate_audio": true,
"callback_url": "https://your-domain.com/webhooks/video-task-completed"
}'
# Save the returned task ID, then query:
curl https://api.evolink.ai/v1/tasks/{task_id} \
-H "Authorization: Bearer $EVOLINK_API_KEY"Check every value against the parameter cards above: ranges, allowed options, asset counts, and file types must match the selected route.
Check the Authorization bearer token and confirm the available balance and task billing in the console.
Review likeness rights, brand assets, readable text, sensitive content, and input-asset compliance.
A Seedance 2.0 task that reaches a final failed state is not charged. Keep the task ID, inspect the final state, and identify whether the cause is validation, review, or execution before retrying.
callback_url must be a public HTTPS URL, not localhost or a private network address. Always keep the task ID as a polling fallback.
| Feature | Seedance 2.0 | Kling 3.0 | Happy Horse |
|---|---|---|---|
| Price (720p 5s) | ~$0.993 | ~$0.398 | ~$0.560 |
| 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 |
Generate video from text, images, or reference material — all on the same Seedance 2.0 API page.
Use Fast mode for cheap drafts, then switch to Standard mode when you are ready to check the final quality.
Describe the subject, camera motion, lighting, visual style, scene continuity, and the audio you want.
See estimated credits, per-second pricing, and sample cost before you add credits.
One API key works across Seedance, Kling, Sora, Veo, image, and LLM models.
Track credits, spending, and model usage in one console.
See whether a video task is submitted, processing, completed, or failed.
Test product ads, creator clips, spokesperson videos, and short UGC scenes.
Compare Seedance generations under one EvoLink account and API key, then choose by clip length, reference workflow, speed, and cost.
Next in the family: Seedance 2.5 is now live on EvoLink — 4–30s clips, synchronized audio, and up to 50 reference inputs, with API and playground access. See the Seedance 2.5 API docs page for pricing, docs, and migration guidance.

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



Billed by video duration and resolution. A 5s 480p Fast sample is about 19.0681 credits, roughly $0.281.
Yes. Test output quality and estimate credits in the Playground before integrating the API.
You can check task status and billing details in the console. Failed tasks are not charged.
Yes. Seedance 2.0 supports Text-to-Video, Image-to-Video, Reference-to-Video, and Fast mode.
Not confirmed yet. We will update this page once it is officially released.
Return to the Playground to keep testing, or create an API key in the console to start integrating.
Fast mode is quicker and cheaper, ideal for prompt iteration and drafts; Standard mode offers higher quality for final output.
Videos generated through the EvoLink API have no watermark and can be used commercially.
We support 480p, 720p, and 1080p. We recommend iterating quickly in 480p, then rendering the final at a higher resolution.