The Seedance 2.0 API on APIMart gives you ByteDance's Seedance 2.0 video model, listed on Volcano Engine as Doubao-Seedance-2.0, for text to video, image to video, first and last frame and multimodal reference generation with native audio. One Seedance API key gives you every Seedance 2 API variant—seedance-2.0, seedance-2.0-fast and seedance-2.0-mini.
Upload reference audio (requires image or video)
WAV, MP3 (max 20MB, up to 3 audios, duration ≤ 15s)
Video link valid for 72 hours
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
seedance-2.0 | 480P & uploaded videos | 0.4Credits(~$0.04)/secref. duration + gen. duration | 0.38Credits(~$0.038)/sec | 0.36Credits(~$0.036)/sec | 0.5Credits(~$0.05)/sec | 20% |
| 480P | 0.66Credits(~$0.066)/sec | 0.627Credits(~$0.0627)/sec | 0.594Credits(~$0.0594)/sec | 0.825Credits(~$0.0825)/sec | 20% | |
| 720P & uploaded videos | 0.8584Credits(~$0.0858)/secref. duration + gen. duration | 0.8155Credits(~$0.0815)/sec | 0.7726Credits(~$0.0773)/sec | 1.073Credits(~$0.1073)/sec | 20% | |
| 720P | 1.42Credits(~$0.142)/sec | 1.349Credits(~$0.1349)/sec | 1.278Credits(~$0.1278)/sec | 1.775Credits(~$0.1775)/sec | 20% | |
| 1080P & uploaded videos | 2.1568Credits(~$0.2157)/secref. duration + gen. duration | 2.049Credits(~$0.2049)/sec | 1.9411Credits(~$0.1941)/sec | 2.696Credits(~$0.2696)/sec | 20% | |
| 1080P | 3.544Credits(~$0.3544)/sec | 3.3668Credits(~$0.3367)/sec | 3.1896Credits(~$0.319)/sec | 4.43Credits(~$0.443)/sec | 20% | |
| 4K & uploaded videos | 4.4432Credits(~$0.4443)/secref. duration + gen. duration | 4.221Credits(~$0.4221)/sec | 3.9989Credits(~$0.3999)/sec | 5.554Credits(~$0.5554)/sec | 20% | |
| 4K | 7.22Credits(~$0.722)/sec | 6.859Credits(~$0.6859)/sec | 6.498Credits(~$0.6498)/sec | 9.025Credits(~$0.9025)/sec | 20% |
* Actual costs are subject to final output.
* uploaded videos pricing = (ref. duration + gen. duration) × current price
The Seedance 2.0 API brings ByteDance's Seedance 2.0 AI video generator to APIMart. Generate 4–15 second clips at up to 1080p or 4K from text, images, video and audio references, with sound created in the same pass.
50K+
Active Users
99.9%
Uptime
2x
Faster
—
Cost Savings
Call the ByteDance Seedance 2.0 API on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint to get the video URL.
Save the key you created above in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every Seedance 2.0 API request.
POST /v1/videos/generations with model seedance-2.0, your prompt, size, resolution and duration. Add image_urls for image to video, or video_urls and audio_urls for references. The Seedance 2.0 API response contains the task ID in data[0].task_id.
Poll GET /v1/tasks/{task_id} until status is completed, then read the video URL from data.result.videos[0].url[0]. If a Seedance 2.0 API task fails, the reason is returned in data.error.message.
See the Seedance 2.0 API reference for every parameter, scenario and response field.
curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "A cinematic tracking shot of a red vintage car driving along a coastal road at sunset, waves crashing below, warm golden light",
"size": "16:9",
"resolution": "720p",
"duration": 5
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "seedance-2.0",
"prompt": "A cinematic tracking shot of a red vintage car driving along a coastal road at sunset, waves crashing below, warm golden light",
"size": "16:9",
"resolution": "720p",
"duration": 5
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["videos"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(10)
else:
raise TimeoutError(f"task {task_id} did not finish in time")curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "The woman in the photo turns toward the camera and smiles as the wind moves her hair, slow push-in, soft daylight",
"image_urls": [
"https://example.com/portrait.jpg"
],
"resolution": "720p",
"duration": 5
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: seedance-2.0 | seedance-2.0 (standard), seedance-2.0-fast or seedance-2.0-mini. Fast and Mini support the same features at up to 720p. |
prompt | string | Optional | Default: — | Seedance 2.0 API video description. Required for text to video and optional when you pass images or reference video. Up to 4,000 characters; around 500 is recommended. |
duration | integer | Optional | Default: 5 | Seedance 2.0 API clip length from 4 to 15 seconds. |
size | string | Optional | Default: 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 or adaptive (matches the input image or video). |
resolution | string | Optional | Default: 720p | 480p or 720p; 1080p and 4k are available on seedance-2.0 only. |
seed | integer | Optional | Default: — | Random seed. The same seed with the same request gives similar, but not identical, results. |
generate_audio | boolean | Optional | Default: true | Generate synchronized audio. Set false for a silent video. |
return_last_frame | boolean | Optional | Default: false | Also return the URL of the last frame, for chaining Seedance 2.0 API clips into longer, multi-shot videos. |
image_urls | array | Optional | Default: — | Up to 9 image URLs or asset:// IDs for Seedance 2.0 API image to video. Cannot be used together with image_with_roles. |
image_with_roles | array | Optional | Default: — | Images with a role: first_frame, last_frame or reference_image (a reference portrait, used with an approved asset:// URL). Reference video and audio are not available with first and last frames. |
video_urls | array | Optional | Default: — | Up to 3 Seedance 2.0 API reference videos, total length between 1.8 and 15.2 seconds, 480p to 720p. |
audio_urls | array | Optional | Default: — | Up to 3 Seedance 2.0 API reference audio clips, 15 seconds in total. Must be used with a reference image or video. |
tools | array | Optional | Default: — | Optional tools. [{"type": "web_search"}] lets the model reference web information during generation. |
nsfw_check | boolean | Optional | Default: false | Check the prompt and images before submission. Flagged requests return HTTP 400 and no task is created. |
Compare every Seedance video model on APIMart. One API key calls all of them; each model page shows its live pricing.
| Model | Best for | Resolution | Duration |
|---|---|---|---|
| Seedance 2.5 API | Clips up to 30 s with up to 50 image, video and audio references, plus video editing and extension | 480P / 720P / 1080P | 4–30 s or auto |
| Seedance 2.0 APIThis page | Up to 4K, the highest resolution in the family, with image, video and audio references | 480P / 720P / 1080P / 4K | 4–15 s |
| Seedance 2.0 Fast API | Fast variant of Seedance 2.0 with the same image, video and audio references | 480P / 720P | 4–15 s |
| Seedance 2.0 Mini API | Mini variant of Seedance 2.0 with the same image, video and audio references | 480P / 720P | 4–15 s |
| Seedance 1.5 Pro API | Text-to-video and first/last-frame image-to-video, with optional audio | 480P / 720P / 1080P | 4–12 s |
| Seedance 1.0 Pro Quality API | Text-to-video and first/last-frame image-to-video | 480P / 720P / 1080P | 2–12 s |
| Seedance 1.0 Pro Fast API | Text-to-video and first-frame image-to-video (no last frame) | 480P / 720P / 1080P | 2–12 s |
Guides, comparisons and pricing analysis from the APIMart blog.
Comprehensive upgrade with more powerful video generation. This comparison covers the Seedance 2.0 series; output resolutions vary by model.
| Features | 1.5 Pro | 2.0NEW |
|---|---|---|
| Text to Video | ||
| Image to Video | ||
| First Frame | ||
| Last Frame | ||
| Audio Driven | ||
| Video Reference | ||
| Motion Control |
What the Seedance 2.0 API can do through one APIMart endpoint
Production scenarios for the Seedance 2.0 API, ByteDance's AI video generator, on APIMart
Go from sign-up to your first Seedance 2.0 API video in three steps
Register on APIMart and create an API key in your dashboard to call the Seedance 2.0 API.
Try Seedance 2.0 API prompts, reference images and resolutions on this page to find settings that fit your project.
Follow the API documentation to send Seedance 2.0 API requests from your backend and poll task results.
Real feedback from creators and developers using Seedance 2.0 worldwide. These reviews describe experiences with the Seedance 2.0 series.
“The visual quality of Seedance 2.0 is incredible! The motion is so smooth and natural, it really elevates my content.”
Sarah Kim
Content Creator
“As a developer, I appreciate the clean API and fast response times. Seedance 2.0 integrates seamlessly into our pipeline.”
Alex Wang
Full-Stack Engineer
Answers about Seedance 2.0 API capabilities, parameters and access
Seedance 2.0 is ByteDance Seed's multimodal video generation model, also written as Seedance 2 or Seedance V2 and often called simply Seedance AI. The Seedance 2.0 API turns text, images, video and audio into 4–15 second clips with sound. On APIMart, the Seedance 2.0 API uses the model ID seedance-2.0; on Volcano Engine the same model is listed as Doubao-Seedance-2.0.
The Seedance 2.0 release date is February 12, 2026, when ByteDance Seed announced its official launch and made it available in Jimeng, the Doubao app and the Volcano Engine Ark experience center. You can call it through the Seedance 2.0 API on APIMart with the model ID seedance-2.0.
Send POST /v1/videos/generations with model seedance-2.0 and your prompt. The Seedance 2.0 API runs as an asynchronous task: read the task ID from data[0].task_id, poll GET /v1/tasks/{task_id} until the status is completed, then read the video URL from data.result.videos[0].url[0]. The example on this page shows the full flow in cURL and Python.
Seedance 2.0 keeps the core workflows of Seedance 1.5 Pro—text-to-video, image-to-video, and first/last frame control—and adds audio-driven generation and video reference, so a reference clip can drive a character's motion. Both workflows are available through the Seedance 2.0 API on APIMart.
In the Seedance 2.0 API, model is required, and prompt is required for text to video. Optional parameters are duration (4–15 seconds, default 5), size (default 16:9), resolution (default 720p), seed, generate_audio (default true), return_last_frame, image_urls, image_with_roles, video_urls, audio_urls, tools for web search and nsfw_check. The parameter table on this page lists every limit.
The Seedance 2.0 API generates clips from 4 to 15 seconds. The standard seedance-2.0 model outputs 480p, 720p, 1080p or 4K, while Fast and Mini output 480p or 720p. Aspect ratios are 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 and adaptive, which follows the input image or video.
Yes. Pass a picture in image_urls and the Seedance 2.0 API uses it as the opening frame, or use image_with_roles with first_frame and last_frame to fix both ends of the clip. image_urls and image_with_roles cannot be combined, and first- and last-frame tasks cannot include reference video or audio.
Yes. The Seedance 2.0 API adds synchronized sound by default through generate_audio. You can also send up to 3 reference videos (total length between 1.8 and 15.2 seconds, 480p to 720p) to guide motion, and up to 3 reference audio clips (15 seconds in total) that must be paired with a reference image or video.
For the Seedance 2.0 API, name the subject, the action, the camera move and the visual style, and describe sound or dialogue when audio is on. Keep prompts around 500 characters so details are not dropped, and describe how each reference image or video should be used, for example which one sets the first frame and which one sets the motion.
Both seedance-2.0-fast and seedance-2.0-mini output 480p or 720p video, while the standard seedance-2.0 model also offers 1080p and 4K. All three accept 4–15 second durations and are billed by resolution, so the Seedance 2.0 price differs per variant—compare prices on each model's page and test each one in its playground before you scale up.
Prices use the selected model and resolution’s original price and actual discount. Without a reference video, the estimate is based on output duration. With a reference video, the input tier covers reference plus output duration; unknown reference duration is shown as a range.
No. There is no free quota for the Seedance 2.0 API on APIMart. Billing is pay-as-you-go and you only pay for successful requests. Members save 20%–28%: Gold members get 20% off, and Platinum and Diamond members up to 28%. See this page's live pricing table for current prices.
Sign up for APIMart, open the API Keys page in your dashboard and create a key. The same key calls the ByteDance Seedance 2.0 API and every other model on the platform, with pay-as-you-go billing and no subscription.
You can use and get access to ByteDance Seedance 2.0 directly through the Seedance 2.0 API on APIMart: create an account, generate an API key, and send requests with the model ID seedance-2.0. Whether you search for Seedance AI or know it as Dreamina Seedance 2.0, BytePlus Seedance 2.0, the Seedance API or the Seedance2.0 API, it is the same ByteDance model. If your code comes from a platform that names it bytedance/seedance-2.0, switch the model field to seedance-2.0 and check the APIMart docs for parameters.
Explore more models in the same category.

Wan 2.5 Preview
wan‑2.5 video is an advanced AI video generation model developed by Alibaba’s Wan AI team. It transforms text or image prompts into high‑quality videos with synchronized audio, realistic motion, and cinematic visuals. Supporting resolutions up to 1080p and short clips up to around 10 seconds, it integrates audiovisual generation in one pass, enabling creators to produce expressive, professional‑grade video content efficiently and affordably.

Kling Video O1
Kling-Video-O1 is a multimodal AI video model that combines generation and editing, emphasizing high consistency and strong controllability.

MiniMax Hailuo 2.3 Fast
MiniMax-Hailuo-2.3-Fast is an AI video generation model designed with a focus on speed.

Kling V3
Kling-V3 is an AI video model that balances quality and control, making it ideal for creating medium- to high-quality content.