Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No video yet. Submit the form to generate video.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
Billing for Video Models
You might notice that models "with video input" have a lower unit price. This is because the billing method differs:
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
seedance-2-mini-without-video-480p videoByteDanceresolution: 480p, reference_video_urls: empty | Starter | 4per second | $0.018 | ByteDance$0.060per second | Based on 1,000 10-second videos/dayByteDance costs $418.180/day moreApiPass is 69.70% lower |
Competitor pricing costs $1001.550/day more
ApiPass is 64.74% lower, estimated at Based on 1,000 10-second videos/day
seedance-2-mini-without-video-720p
resolution: 720p, reference_video_urls: empty
ApiPass Price
$0.055
12 credits per second
Competitor Prices
Complete guide to using Seedance 2.0 mini
Access the Seedance 2.0 Mini API on ApiPass to create high-quality videos from text, first-frame images, last-frame guidance, and multimodal references. Built for scalable AI video applications, it combines fast generation, lower inference cost, cinematic motion, consistent character support, and production-friendly asynchronous task workflows.
Seedance 2.0 Mini is a cost-efficient AI video generation model designed for faster generation and lower inference costs. It supports text-to-video, image-to-video, multi-reference video creation, synchronized audio generation, cinematic camera motion, and character-consistent storytelling. Through ApiPass, developers can submit generation tasks with prompts, optional frame inputs, image/video/audio references, resolution, aspect ratio, duration, and safety settings, then retrieve results asynchronously by task ID or receive callbacks when a task completes.
Generate videos from natural language prompts, or provide a first frame and optional last frame to guide image-to-video generation. Describe camera movement, subject behavior, scene transitions, lighting, and visual style to control the final result.
Guide video creation with up to 9 reference images, up to 3 reference videos, and up to 3 reference audio files. These inputs help control appearance, motion, style, and audio direction for more consistent production outputs.
Submit jobs through POST /api/v1/jobs/createTask and query status through GET /api/v1/jobs/recordInfo?taskId=<taskId>. If callBackUrl is provided, ApiPass posts the task result to your endpoint when generation completes.
Seedance 2.0 Mini is optimized for faster generation speeds and lower inference costs, making it practical for high-volume AI video products, content automation platforms, and developer workflows that need reliable throughput.
Use multimodal inputs to guide character appearance, visual style, motion behavior, and audio cues. The API supports reference_image_urls, reference_video_urls, and reference_audio_urls while keeping frame inputs and reference inputs mutually exclusive for predictable validation.
Set generate_audio to true to create video with synchronized AI audio in a unified workflow. This reduces the need to integrate separate sound generation systems for immersive short-form video experiences.
Create videos with pans, zooms, tracking shots, smooth motion, and professional scene transitions. Detailed prompts can specify subject movement, camera behavior, lighting, pacing, and cinematic style.
Maintain character identity, visual style, and scene consistency across generated clips using image references and detailed prompts. This is useful for AI storytelling, branded content, virtual influencers, and narrative video apps.
Turn ideas, scripts, and prompts into engaging short-form content for social platforms. Use aspect_ratio values such as 9:16, 16:9, 1:1, or adaptive to match different publishing formats.
Transform product photos into promotional videos with image-to-video generation. Use first_frame_url to preserve the product starting composition, then describe camera movement, lighting, and commercial style in the prompt.
Use multi-image references to maintain character identity across scenes, short dramas, virtual influencer content, and narrative-driven video experiences.
Integrate Seedance 2.0 Mini into creative tools, marketing platforms, and automated content pipelines. The async task flow, callback support, and query endpoint make it suitable for scalable production systems.
Seedance 2.0 Mini is positioned for developers who need strong video quality with faster generation and better cost efficiency, while the broader Seedance 2.0 family can be used when maximum visual quality is the top priority.
Seedance 2.0 Mini focuses on faster generation, lower cost, and better price-performance for large-scale AI video applications. Seedance 2.0 is better suited to flagship-quality outputs where premium motion detail and maximum visual quality matter more than cost efficiency.
Use POST /api/v1/jobs/createTask to submit a generation request. The response returns data.taskId. Use GET /api/v1/jobs/recordInfo?taskId=<taskId> to check state values such as waiting, queuing, generating, success, or fail, and read resultJson when the task succeeds.
If callBackUrl is provided, ApiPass posts the completed task result to your endpoint. If no callback URL is provided, no callback notifications are sent, and your application should poll the Query Task API until the task reaches success or fail.
Seedance 2.0 Mini is designed to reduce video generation costs while maintaining strong visual performance, making it suitable for SaaS teams, AI video products, and high-volume content workflows.
The optional channel parameter supports auto, starter, regular, and official. auto lets ApiPass allocate tasks across available providers based on real-time pricing and stability metrics, while official prioritizes the model-native API path.
Prompt length must be 3 to 20000 characters. reference_image_urls supports up to 9 images, reference_video_urls supports up to 3 videos, and reference_audio_urls supports up to 3 audio files. Duration is clamped to the 4 to 15 second range, and resolution supports 480p or 720p.
New users can use free credits to test Seedance 2.0 Mini in the ApiPass Playground before moving to production integration. Try text-to-video, image-to-video, audio generation, references, and different aspect ratios.
Start in the ApiPass Playground to experiment with prompts, first-frame or last-frame image guidance, reference images, reference videos, reference audio, duration, resolution, aspect ratio, generate_audio, web_search, and nsfw_checker settings.
Create a JSON request with model set to bytedance/seedance-2-mini and input containing your prompt and generation parameters. Do not combine first_frame_url or last_frame_url with reference_image_urls, reference_video_urls, or reference_audio_urls. Use web_search=true only for pure text-to-video requests.
Send a POST request to https://api.apipass.dev/api/v1/jobs/createTask with your API key. The response returns data.taskId, which identifies the asynchronous generation task.
Query GET /api/v1/jobs/recordInfo?taskId=<taskId> until the task state is success or fail. If you provide callBackUrl, ApiPass sends the completed task result to your endpoint, using the same structure as the Query Task API response.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Submit a new Seedance 2.0 Mini text-to-video or image-to-video generation task.
The API accepts a JSON payload with the following structure:
1{
2 "model": "bytedance/seedance-2-mini",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string",
7 "first_frame_url": "string (optional)",
8 "last_frame_url": "string (optional)",
9 "reference_image_urls": ["string"],
10 "reference_video_urls": ["string"],
11 "reference_audio_urls": ["string"],
12 "return_last_frame": false,
13 "generate_audio": true,
14 "resolution": "720p",
15 "aspect_ratio": "16:9",
16 "duration": 5,
17 "web_search": false,
18 "nsfw_checker": false
19 }
20}modelRequiredstringThe model name to use for generation.
"bytedance/seedance-2-mini"
callBackUrlOptionalstringCallback URL for task completion notifications. If omitted, no callback will be sent.
"https://your-domain.com/api/callback"
channelOptionalstringOptional APIPASS provider routing parameter. The default channel is auto; APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. starter is ultra-low-cost with limited quotas and weaker stability; regular is standard and much cheaper than official APIs with moderate stability; official uses the model native API with high stability, fast task execution, and official pricing.
The default channel is auto; APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. starter is ultra-low-cost with limited quotas and weaker stability; regular is standard and much cheaper than official APIs with moderate stability; official uses the model native API with high stability, fast task execution, and official pricing.
Available options:
auto
The input object contains the following parameters:
input.promptRequiredstringText prompt for text-to-video generation.
Prompt length must be 3-20000 characters. Describe the subject, camera movement, style, lighting, scene changes, and motion details for best results.
"A quiet sunrise over a mountain lake, thin mist drifting across the water, soft cinematic light, realistic natural motion."
input.first_frame_urlOptionalstringURL of the first frame image for image-to-video generation.
Compatible aliases: firstFrameUrl, image_url, image. Do not use together with reference_image_urls, reference_video_urls, or reference_audio_urls.
"https://example.com/first.png"
input.last_frame_urlOptionalstringURL of the last frame image to guide the ending frame of the generated video.
Compatible alias: lastFrameUrl. Do not use together with reference_image_urls, reference_video_urls, or reference_audio_urls.
"https://example.com/last.png"
input.reference_image_urlsOptionalarray<string>List of reference image URLs. Supports up to 9 images.
Compatible alias: referenceImageUrls. Empty values are filtered before being sent upstream. Cannot be used together with first_frame_url or last_frame_url.
["https://example.com/reference-1.png", "https://example.com/reference-2.png"]
input.reference_video_urlsOptionalarray<string>List of reference video URLs. Supports up to 3 videos.
Compatible alias: referenceVideoUrls. Empty values are filtered before being sent upstream. Cannot be used together with first_frame_url or last_frame_url.
["https://example.com/reference-video.mp4"]
input.reference_audio_urlsOptionalarray<string>List of reference audio URLs. Supports up to 3 audio files.
Compatible alias: referenceAudioUrls. Empty values are filtered before being sent upstream. Cannot be used together with first_frame_url or last_frame_url.
["https://example.com/reference-audio.mp3"]
input.return_last_frameOptionalbooleanWhether to return the last frame image together with the generated video.
Compatible alias: returnLastFrame. Default: false.
false
input.generate_audioOptionalbooleanWhether to generate audio for the output video.
Compatible alias: generateAudio. Default: true.
false
input.resolutionOptionalstringOutput video resolution.
Also compatible with the historical quality parameter. Default: 720p.
Available options:
"720p"
input.aspect_ratioOptionalstringAspect ratio of the generated video.
Compatible alias: aspectRatio. Default: 16:9.
Available options:
"16:9"
input.durationOptionalintegerDuration of the output video in seconds.
Allowed range: 4-15 seconds. Default: 5. Values outside the range are clamped to the valid range by the adapter.
5
input.web_searchOptionalbooleanWhether to enable web search to enhance prompt understanding or content grounding.
Compatible alias: webSearch. Default: false. web_search=true is only allowed for pure text-to-video requests without frame or reference inputs.
false
input.nsfw_checkerOptionalbooleanWhether to enable NSFW checking for the request.
Compatible alias: nsfwChecker. Default: false.
false
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Authorization: Bearer YOUR_API_KEY" \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "bytedance/seedance-2-mini",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "channel": "auto",
8 "input": {
9 "prompt": "A quiet sunrise over a mountain lake, thin mist drifting across the water, soft cinematic light, realistic natural motion.",
10 "duration": 5,
11 "resolution": "720p",
12 "aspect_ratio": "16:9",
13 "generate_audio": false,
14 "web_search": false
15 }
16 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code, 200 for success, others for failure.
messageResponse message, or error description when the request fails.
data.taskIdTask ID for querying task status and results.
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Turn text, images, video clips, and audio into cinematic, audio-synced videos with a single API call.
Starting from
0 credits
MiniMax
MiniMax
Starting from
0 credits
ByteDance
ByteDance
Generate cinematic 4K AI videos up to 30 seconds with Seedance 2.5's multimodal power.
Starting from
0 credits
Google Veo 3.1 is the latest state-of-the-art generative video model designed to transform text and image prompts into high-fidelity cinematic visuals. Building upon its predecessors, Veo 3.1 features significant upgrades in prompt adherence, visual realism, and native audio generation, creating 8-second clips with synchronized sound effects and dialogue.
Starting from
0 credits
wan
wan
Starting from
0 credits
Runway
Runway
Starting from
0 credits
Kling
Kling
Transform text prompts and images into high-quality videos with advanced AI. Generate cinematic content with customizable duration, aspect ratio, and audio capabilities.
Starting from
0 credits
MiniMax
MiniMax
Generate high-quality AI videos from text prompts or images with MiniMax's Hailuo 2.3 model. Support for both 6s and 10s durations, 768p and 1080p resolutions, with intelligent prompt optimization.
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
Luma
Luma
Starting from
0 credits
Kling
Kling
Kling v3 video generation model, supports text-to-video and image-to-video, up to 15 seconds, 1080p pro mode
Starting from
0 credits
wan
wan
Generate videos with cinematic consistency by reimagining existing footage through high-fidelity visual transformation and structural control.
Starting from
0 credits
Starting from
0 credits
grok
grok
Starting from
0 credits
kling
kling
Starting from
0 credits