Guide
Seedance API: Text and Image to Video From One REST Endpoint
Run ByteDance's Seedance 2.5 video model, the successor to Seedance 2.0, through one REST endpoint.
Text-to-video, image-to-video with frame control, and multi-shot output, orchestrated next to Kling 3 and Veo 3.1 in the same workflow.
Free to build · no credit card · Read the agent docs
Andrew Adams · Co-Founder & Operations at Wireflow · 
What the Seedance API Gives You
Seedance 2.0 is ByteDance's flagship video generation model. It handles text-to-video, image-to-video with first and last frame control, and reference-to-video, and it is known for strong motion fidelity, character consistency, and multi-shot narrative output in clips up to 15 seconds. Direct access runs through ByteDance's own cloud platforms, so most teams outside China reach the model through third-party API providers instead.
Most of those providers give you a raw single-model endpoint and stop there. Wireflow treats Seedance as one node in a larger pipeline: prototype the workflow on a visual canvas, chain Seedance with image generators, upscalers, and LLM prompt steps, then call the whole pipeline as a single REST endpoint with one Bearer token. You get the model plus the orchestration layer production apps actually need, including async execution, per-node cost reporting, and model swaps without code changes.
Seedance 2.0 Capabilities Through the API
Text-to-Video Generation
Generate cinematic clips from a text prompt, with control over aspect ratio, duration, and motion style.
Image-to-Video with Frame Control
Animate a still image, or pin first and last frames to control exactly where a shot starts and ends.
Character Consistency
Reference inputs keep faces, outfits, and visual style stable across shots, a known strength of Seedance 2.0.
Chain with Other Models
Pipe a GPT Image 2.5 Flare or Flux 2 Pro image straight into a video node, then upscale the result, all in one workflow.
Async Execution Pattern
Submit a request, receive an executionId, poll until COMPLETED. Predictable states built for production queues.
Per-Node Cost Reporting
Every execution response itemizes credit usage per node, so you can track exact cost per second of video.
What one Seedance clip costs through the API
Each API call bills the credits its nodes use, and the execution response lists them per node. Starter is $36 a month for 2,660 credits, and Professional is $59 a month for 4,370 credits.
- One 5 second Seedance 2.5 clip uses 135 credits, $1.83 on Starter or $1.82 on Professional. That is about 19 clips a month on Starter and about 32 on Professional.
- One 5 second Seedance 2.0 clip uses 90 credits, $1.22 on Starter or Professional. That is about 29 clips a month on Starter and about 48 on Professional.
Shorter clips can cost a bit more per second; you're always charged for the real length.
Run Seedance from Claude
You can also run Seedance from a Claude chat, with no code. Add Wireflow as a connector once:
- In Claude, open Customize, then Connectors. Click + Add and choose Add custom connector.
- Name it Wireflow and paste
https://www.wireflow.ai/api/mcpas the server URL. - Sign in to Wireflow when Claude asks, and approve the access.
The Claude app setup guide has the full steps. Then ask in plain words, for example:
Example prompt: "Use Wireflow to make five 5 second Seedance 2.5 clips, one for each of these product prompts, and send me the links. Tell me the credit cost and wait for my yes before you run it."
With that last line, Claude looks up the price and waits for your yes before it spends any credits. Runs use the credits on your Wireflow account.
More Than Just Seedance API: Text and Image to Video From One REST Endpoint
The Full Seedance 2.0 Model
Get ByteDance's strongest video model without managing Volcano Engine accounts. The Seedance 2.0 page covers the model's specs, strengths, and prompt behavior in detail.
Benchmark Against Kling 3
Run the same prompt through two video models in parallel branches and compare output before committing. Kling Video 3 sits one node swap away in the same workflow. You can benchmark Alibaba's model the same way with the Wan 2.5 text to video API. Prefer xAI's model for a shot? You can run Grok Imagine Video on the same canvas and swap back any time.
Built for Programmatic Pipelines
Raw model endpoints leave orchestration to you. Our comparison of the best programmatic video generation platforms shows why a workflow layer beats stitching providers together by hand.
Prototype Visually, Ship via REST
Design and test the pipeline on a canvas before writing integration code. The node-based video generation editor and the API execute the exact same workflow definition.
Pay Per Generation, Capped
Video API bills can spike fast at scale. Wireflow's usage-based AI API pricing charges per execution with spend limits, so a runaway queue cannot blow the budget.
Build Any AI Workflow
AI Models Integrated
Full Commercial License
FAQs
It is programmatic access to Seedance 2.0, ByteDance's video generation model. The API accepts text prompts, images, and reference material, and returns MP4 video with strong motion fidelity, character consistency, and multi-shot narrative support.
More From Wireflow
Written by
Andrew Adams · Co-Founder & Operations at Wireflow
Runs client operations and content strategy at Wireflow. Works directly with creative teams and agencies to build production AI workflows.
Run Seedance 2.5 From Your Codebase
Design the video pipeline visually, then call it as a REST endpoint. Seedance 2.5, Kling 3, and Veo 3.1 behind one API key, with async execution, spend limits, and per-node cost reporting built in.