--- title: Seedance API — Seedance 2.5, 2.0 & 1.5 Pro Video | ModelsLab description: Seedance API without a ByteDance Ark account. Seedance 2.5, 2.0, 2.0 Mini and 1.5 Pro for text-to-video and image-to-video on one endpoint, priced per call. url: https://modelslab.com/seedance-api canonical: https://modelslab.com/seedance-api type: website component: Seo/SeedanceApi generated_at: 2026-09-16T12:05:12.155250Z --- Imagen Seedance API — 2.5, 2.0 & 1.5 Pro via REST --- Seedance 2.5, 2.0, 2.0 Mini and 1.5 Pro for text-to-video and image-to-video through the ModelsLab REST API — no ByteDance Ark account, no separate billing. Priced per call on top of video plans from $21/month. [Get Seedance API Access](https://modelslab.com/register) [API Documentation](https://docs.modelslab.com) What is the Seedance API? --- ### ByteDance’s Video Models, One REST Call Away Seedance is ByteDance’s family of video generation models, served natively through the Volcano Engine Ark platform. The ModelsLab Seedance API puts the same models behind the ModelsLab video endpoint, so you call them with the key and plan you already have, alongside Kling, Veo, Wan and Minimax, and switch between them by changing `model\_id`. Seedance 2.5 is the current top of the range for text-to-video, image-to-video and multimodal reference generation. Seedance 2.0 and 2.0 Fast trade some quality for speed and cost, 2.0 Mini is the cheapest way to draft, and 1.5 Pro remains available for pipelines built on it. ### Endpoints Text-to-video: POST https://modelslab.com/api/v7/video-fusion/text-to-video with a Seedance model\_id, `prompt`, `duration` and `aspect\_ratio`. Image-to-video: POST /api/v7/video-fusion/image-to-video with `init\_image`. Seedance 2.0 also exposes start/end-frame and multi-reference variants for controlled shots. - seedance-2-5-text-to-video, seedance-2-5-image-to-video - seedance-2-text-to-video, seedance-2.0-fast-t2v, seedance-2.0-fast-i2v - seedance-2-mini-t2v, seedance-2-mini-start-end-frame-video - seedance-2-multi-reference-video, seedance-2-start-end-frame-video - seedance-1-5-pro, seedance-1.0-pro-fast-t2v, seedance-1.0-pro-fast-i2v Seedance Models on ModelsLab --- Pick the model with model\_id on the text-to-video or image-to-video endpoint. | model\_id | Model | Input | Listed base price | |---|---|---|---| | seedance-2-5-text-to-video | Seedance 2.5 | Text | from $0.1236, by duration | | seedance-2-5-image-to-video | Seedance 2.5 | Image | from $0.1236, by duration | | seedance-2-text-to-video | Seedance 2.0 | Text | from $0.10, by duration | | seedance-2.0-fast-t2v | Seedance 2.0 Fast | Text | from $0.08, by duration | | seedance-2-mini-t2v | Seedance 2.0 Mini | Text | from $0.044, by duration | | seedance-2-multi-reference-video | Seedance 2.0 Multi-Reference | Images + text | from $0.20, by duration | | seedance-1-5-pro | Seedance 1.5 Pro | Text / image | from $0.03, by duration | | seedance-1.0-pro-fast-t2v | Seedance 1.0 Pro Fast | Text | from $0.024, by duration | Base prices as listed on each model page in September 2026. Seedance is billed per generation scaled by duration and resolution, so these are floors rather than the price of a finished clip. It is a third-party model, billed per call from wallet balance on any video plan. Seedance API quick start --- Text to video, image to video, and polling for the clip. ### Seedance 2.5 text to video (Python) Python ``` 1import requests 2 3response = requests.post( 4 "https://modelslab.com/api/v7/video-fusion/text-to-video", 5 headers={ 6 "Authorization": "Bearer YOUR_MODELSLAB_API_KEY", 7 "Content-Type": "application/json", 8 }, 9 json={ 10 "model_id": "seedance-2-5-text-to-video", 11 "prompt": "a red kite over a cliff edge at golden hour, handheld feel", 12 "duration": 5, 13 "aspect_ratio": "16:9", 14 }, 15) 16 17# Seedance renders return an id — poll fetch/{id} or pass a webhook 18print(response.json()) ``` ### Seedance 2.0 Fast image to video (JavaScript) JavaScript ``` 1const response = await fetch( 2 'https://modelslab.com/api/v7/video-fusion/image-to-video', 3 { 4 method: 'POST', 5 headers: { 6 'Content-Type': 'application/json', 7 Authorization: 'Bearer YOUR_MODELSLAB_API_KEY', 8 }, 9 body: JSON.stringify({ 10 model_id: 'seedance-2.0-fast-i2v', 11 prompt: 'the camera pulls back slowly, leaves drift across the frame', 12 init_image: ['https://example.com/still.jpg'], 13 duration: 5, 14 }), 15 }, 16); 17 18const { id } = await response.json(); 19console.log(`queued as ${id}`); ``` ### Poll for the clip (cURL) bash ``` 1curl -X POST 'https://modelslab.com/api/v7/video-fusion/fetch/REQUEST_ID' \ 2 -H 'Authorization: Bearer YOUR_MODELSLAB_API_KEY' \ 3 -H 'Content-Type: application/json' 4 5# {"status":"success","output":["https://cdn.modelslab.com/.../seedance.mp4"]} ``` Generate with Seedance in 3 Steps --- Same endpoint as every other video model. STEP 01 STEP 01 ### Step 1: Get Your API Key Create a ModelsLab account, subscribe to a video plan from $21/month, add wallet balance for third-party models, and copy your key. STEP 02 STEP 02 ### Step 2: Send the Prompt with a Seedance model\_id POST to /api/v7/video-fusion/text-to-video with seedance-2-5-text-to-video, seedance-2-text-to-video or seedance-2-mini-t2v, plus prompt, duration and aspect\_ratio. Use image-to-video with init\_image to animate a still. STEP 03 STEP 03 ### Step 3: Fetch the Clip The request returns an id. POST /api/v7/video-fusion/fetch/{id} until output is populated, or pass a webhook URL and receive the MP4 when it is ready. [Get API Key ](https://modelslab.com/register) Related video API guides --- [### AI Video API The full video endpoint set Seedance sits inside: text, image, video and audio inputs.](/ai-video-api) [### Kling AI API The other premium video family on the same endpoint, for side-by-side evaluation.](https://modelslab.com/kling-ai-api) [### Cheapest AI Video API How per-call Seedance pricing compares with open-weight models covered by your plan.](https://modelslab.com/cheapest-ai-video-api) [### Seedance 2.0 Model page for Seedance 2.0 specifically — capabilities, sample output and per-clip price.](/seedance-2) ### Pricing Seedance is a third-party model, so it is billed per call from wallet balance on top of a video plan, on every plan including the $199 unlimited tier. The model pages list base prices of $0.10 for Seedance 2.0, $0.044 for Seedance 2.0 Mini and $0.024 for Seedance 1.0 Pro Fast in September 2026. Those are floors: the charge scales with duration and resolution, so a longer clip costs a multiple of the listed figure. The final price is shown before you send the request. ### Draft Cheap, Ship Premium A common pattern is to iterate on the prompt with Seedance 2.0 Mini or an open-weight model covered by your plan, then re-render the final take on Seedance 2.5. The endpoint, key and request shape stay the same; only model\_id changes. Why Call Seedance Through ModelsLab --- Key advantages that set us apart Seedance 2.5, 2.0, 2.0 Fast, 2.0 Mini and 1.5 Pro No ByteDance Ark account or separate billing Same endpoint as Kling, Veo, Wan and Minimax Text-to-video, image-to-video, start/end-frame, multi-reference Per-call price and unit shown before you send Async id, fetch endpoint and webhook delivery Video plans from $21/month Our Popular Use Cases What teams build with the Seedance API: Cinematic ShortsPrompt IterationControlled ShotsProduct AnimationModel EvaluationCreator Tools Seedance 2.5 for hero shots where motion quality carries the clip. ![Cinematic Shorts](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/0fbacb1a-6e34-4254-0a9d-5e75178cf200/768) Seedance API FAQ --- Seedance 2.5 (text-to-video, image-to-video and multimodal reference), Seedance 2.0 and 2.0 Fast, Seedance 2.0 Mini, and Seedance 1.5 Pro. Each is a model\_id on /api/v7/video-fusion/text-to-video or /image-to-video. No. ModelsLab calls Seedance for you. You use a ModelsLab API key, the same one that covers Kling, Veo, Wan and the rest of the video catalogue. Seedance is a third-party model billed per call from wallet balance on top of a video plan from $21/month. In September 2026 the model pages list base prices of $0.10 for Seedance 2.0, $0.044 for Seedance 2.0 Mini and $0.024 for Seedance 1.0 Pro Fast. Those are floors — the charge scales with duration and resolution, so a longer clip costs a multiple of the listed figure. POST https://modelslab.com/api/v7/video-fusion/text-to-video with model\_id set to seedance-2-5-text-to-video, seedance-2-text-to-video or seedance-2-mini-t2v, plus prompt, duration and aspect\_ratio. Yes. POST /api/v7/video-fusion/image-to-video with model\_id set to seedance-2-5-image-to-video or seedance-2.0-fast-i2v and init\_image set to the image URL. Seedance 2.0 also supports start/end-frame and multi-reference generation. ModelsLab is a paid service. Seedance is billed per call on top of a video plan from $21/month. Creating an account is free, but generating video requires an active plan and wallet balance for third-party models. Your Data is Secure: GDPR Compliant AI Services --- ![ModelsLab GDPR Compliance Certification Badge](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/28133112-07fe-4c1c-44eb-36948d51ae00/768) ### Start Creating Amazing AI Videos in Minutes Choose plan as per your needs, cancel anytime. Coming Soon --- We are making some changes to our pricing, please check back later. Get Expert Support in Seconds We're Here to Help. --- Want to know more? You can email us anytime at Chat with support[View Docs](https://docs.modelslab.com) Seedance 2.5 (text-to-video, image-to-video and multimodal reference), Seedance 2.0 and 2.0 Fast, Seedance 2.0 Mini, and Seedance 1.5 Pro. Each is a `model_id` on /api/v7/video-fusion/text-to-video or /image-to-video. No. ModelsLab calls Seedance for you. You use a ModelsLab API key, the same one that covers Kling, Veo, Wan and the rest of the video catalogue. Seedance is a third-party model billed per call from wallet balance on top of a video plan from $21/month. In September 2026 the model pages list base prices of $0.10 for Seedance 2.0, $0.044 for Seedance 2.0 Mini and $0.024 for Seedance 1.0 Pro Fast. Those are floors — the charge scales with duration and resolution, so a longer clip costs a multiple of the listed figure. POST https://modelslab.com/api/v7/video-fusion/text-to-video with `model_id` set to `seedance-2-5-text-to-video`, `seedance-2-text-to-video` or `seedance-2-mini-t2v`, plus `prompt`, `duration` and `aspect_ratio`. Yes. POST /api/v7/video-fusion/image-to-video with `model_id` set to `seedance-2-5-image-to-video` or `seedance-2.0-fast-i2v` and `init_image` set to the image URL. Seedance 2.0 also supports start/end-frame and multi-reference generation. ModelsLab is a paid service. Seedance is billed per call on top of a video plan from $21/month. Creating an account is free, but generating video requires an active plan and wallet balance for third-party models. Explore Our Other Solutions --- Unlock your creative potential and scale your business with ModelsLab's comprehensive suite of AI-powered solutions. [Imagen ### AI Image Generation & Tools Generate, edit, upscale, and transform images with state-of-the-art AI models. Explore Imagen](https://modelslab.com/imagen) [Audio Gen ### AI Audio Generation Text-to-speech, voice cloning, music generation, and audio processing APIs. Explore Audio Gen](https://modelslab.com/audio-gen) [Chat ### Engage Seamlessly with LLM Access powerful language models for chatbots, content generation, and AI assistants. Explore Chat](https://modelslab.com/custom-llm) [3D Verse ### Create Stunning 3D Models Transform images and text into 3D models with advanced AI-powered generation. Explore 3D Verse](https://modelslab.com/text-to-3d) Plugins Explore Plugins for Pro --- Our plugins are designed to work with the most popular content creation software. [Explore Plugins](https://modelslab.com/pro#plugins) [Learn More](https://modelslab.com/pro) API Build Apps with ModelsLab ML API --- Use our API to build apps, generate AI art, create videos, and produce audio with ease. [API Documentation](https://docs.modelslab.com) [Playground](https://modelslab.com/models) ## Frequently Asked Questions ### Which Seedance models does the API expose? Seedance 2.5 (text-to-video, image-to-video and multimodal reference), Seedance 2.0 and 2.0 Fast, Seedance 2.0 Mini, and Seedance 1.5 Pro. Each is a `model_id` on /api/v7/video-fusion/text-to-video or /image-to-video. ### Do I need a ByteDance Ark account to use the Seedance API? No. ModelsLab calls Seedance for you. You use a ModelsLab API key, the same one that covers Kling, Veo, Wan and the rest of the video catalogue. ### How much does the Seedance API cost? Seedance is a third-party model billed per call from wallet balance on top of a video plan from $21/month. In September 2026 the model pages list base prices of $0.10 for Seedance 2.0, $0.044 for Seedance 2.0 Mini and $0.024 for Seedance 1.0 Pro Fast. Those are floors — the charge scales with duration and resolution, so a longer clip costs a multiple of the listed figure. ### Which endpoint is Seedance text to video? POST https://modelslab.com/api/v7/video-fusion/text-to-video with `model_id` set to `seedance-2-5-text-to-video`, `seedance-2-text-to-video` or `seedance-2-mini-t2v`, plus `prompt`, `duration` and `aspect_ratio`. ### Can Seedance animate an image? Yes. POST /api/v7/video-fusion/image-to-video with `model_id` set to `seedance-2-5-image-to-video` or `seedance-2.0-fast-i2v` and `init_image` set to the image URL. Seedance 2.0 also supports start/end-frame and multi-reference generation. ### Is there a free Seedance API? ModelsLab is a paid service. Seedance is billed per call on top of a video plan from $21/month. Creating an account is free, but generating video requires an active plan and wallet balance for third-party models. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-09-16*