Velokey

Doubao Seedance 2.5

字节跳动Video0.144 Credits / second≈$0.144Available
Get API keyAPI docs

The Seedance 2.5 API on Velokey generates single-pass 30-second videos with synchronized audio. Submit model, prompt, duration, and up to 50 reference inputs to create AI videos through one unified video endpoint.

Single-pass 30s generationUp to 50 reference inputsNative synced audioTimestamp-level camera control

Use cases

Seedance 2.5 brand ads · Seedance 2.5 product videos

Input

Text, image, or video

Output

Video

Billing

Per second

Model Type:
0/30
0/10
0/10
5s
4s30s
Generate Audio

Sign up to get $0.5 in free credits — about 20 free images

Generate a video

Enter a prompt and click Generate

Pricing details

Transparent usage-based pricing with no hidden fees.

Detailed Pricing

Usage-based pricing breakdown

Text to Video

SpecPriceOfficial/Fal Price(USD)Savings
480p/second0.144 Credits≈$0.1440.16 Credits-10%
720p/second0.315 Credits≈$0.3150.35 Credits-10%

Billing Rules

  • Output price varies by model, resolution, quality, duration, or token usage.
  • Uploaded reference files may be charged separately when supported.
  • Add-on capabilities such as web search or image search may be billed per request.
  • Token-based models are billed by input and output tokens.
  • If the primary route is unavailable, Velokey may automatically switch to a stable fallback route when possible.
  • Usage is pay-as-you-go with transparent credit deduction.

* Final cost depends on the generated result.

Related models

Explore other models in the same family.

Affordable Seedance 2.5 API

Access ByteDance Seed's Seedance 2.5 on Velokey — single-pass 30-second audio-video joint generation, up to 50 reference inputs, clay-render camera control, and timestamp-level editing, all through a unified endpoint at below-list pricing.

Meet Seedance 2.5 and its API access

Seedance 2.5 is ByteDance Seed's new-generation video creation model released in mid-2026. Built on Seedance 2.0's unified multimodal audio-video joint-generation architecture, it doubles single-pass duration to 30 seconds and targets complete creative works rather than single clips — organizing setup, development, turning points, and resolution within one generation, with multi-round extensions reaching multi-minute videos while keeping characters, environments, and pacing consistent. Velokey provides an affordable, easy-to-integrate Seedance 2.5 API: a unified video generation endpoint, one API key, and below-list pricing for production creative pipelines, marketing teams, and automation tools.

One-take 30-second narratives

Generate up to 30 coherent seconds in a single pass, including scene changes and tempo shifts, with smoother shot transitions and stable subjects across cuts. Multi-round extension builds multi-minute videos while sound effects and voices carry across clips.

View Documentation →
One-take 30-second narratives

Up to 50 reference inputs

Combine up to 30 images, 10 video clips, and 10 audio clips in one request. The model reads composition, scenes, styles, characters, and props from your materials, preserving each character's appearance and voice in group scenes.

View Documentation →
Up to 50 reference inputs

Clay-render camera control

Define spatial structure, poses, motion paths, and camera trajectories with textureless 3D models, plus segmented per-timestamp camera plans — FPV moves, whip-pans, push-ins, top-down descents — for one-take continuous shots with physically plausible lighting.

View Documentation →
Clay-render camera control

Timestamp-level precise editing

Control narrative, camera, and rhythm per time frame during generation; afterwards, modify characters, actions, or plot in specific clips while maintaining continuity. Upgraded green-screen background replacement and camera-perspective editing suit film and advertising revisions.

View Documentation →
Timestamp-level precise editing

How to deploy the Seedance 2.5 API on Velokey

Get started with just a few steps.

1

Sign up and get an API Key

Sign in to the Velokey console to generate an API key that authenticates every request sent to Seedance 2.5.

2

Configure the request

Set model to doubao-seedance-2-5-text-to-video and provide your prompt with any image, video, or audio references. Choose a duration from 4 to 30 seconds and 480p or 720p resolution.

3

Generate and retrieve the video

Submit the request to Velokey's unified video generation endpoint, poll the task for the synchronized audio-video result, and manage usage in one console.

Seedance 2.5 real-world use cases

From advertising to short films, education, and product video, covering many production scenarios.

Commercial advertising

One-take 30-second ad narratives — setup, turn, and resolution generated together, reducing stitching and rework.

Short films and trailers

Organize logically connected shots within one generation, keep subjects stable across cuts, and extend to multi-minute pieces.

Reference-driven custom generation

Up to 30 images, 10 video clips, and 10 audio references lock in brand visuals, character designs, and motion style.

Game animation and cutscenes

Plan space and camera trajectories with clay-render models to generate one-take cutscenes and previz footage.

Commentary and education

Finished clips with native synced audio — narration, sound effects, and visuals precisely aligned for courses and explainers.

Targeted edits of existing footage

Modify characters, actions, or plot in specific time ranges, replace green-screen backgrounds with physically plausible lighting and motion.

Why choose Velokey for Seedance 2.5

Below list price

Call Seedance 2.5 at a lower price on Velokey — pay-as-you-go with no forced subscription, reducing upfront cost.

Unified API interface

One API key accesses Seedance 2.5 and other models — no juggling multiple accounts and keys, simplifying integration.

Complete docs and references

Endpoint references and parameter details for text, image, video, and audio inputs help you ship multimodal generation quickly.

Three variants, stable routing

Text-to-video, image-to-video, and reference-to-video variants share one integration pattern, with stable fallback routes keeping production reliable.

API Reference

Complete API call examples and parameter descriptions

Endpoint

https://api.velokey.ai/v1/chat/completions

Authentication

Bearer YOUR_API_KEY

Request Example

curl https://api.velokey.ai/v1/chat/completions \
  -X POST \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2-5-text-to-video",
    "prompt": "A cinematic shot...",
    "duration": 5,
    "resolution": "720p"
  }'

Response Example

{
  "id": "req_abc123",
  "model": "doubao-seedance-2-5-text-to-video",
  "created": 1234567890,
  "data": { ... }
}

Seedance 2.5 API FAQ

What is Seedance 2.5?

Seedance 2.5 is ByteDance Seed's new-generation video model. It generates up to 30 seconds of complete narrative with synchronized audio in a single pass, supports up to 50 multimodal reference inputs and timestamp-level editing, and succeeds Seedance 2.0.

Which parameters does Seedance 2.5 support?

Prompt, duration (4-30 seconds), resolution, aspect ratio (16:9, 9:16, 1:1), generate_audio, and seed, plus up to 30 reference images, 10 video clips, and 10 audio clips. JSON mode uses the same fields for easy copy to your server.

Which Seedance 2.5 variants exist?

The backend offers text-to-video, image-to-video, and reference-to-video variants. They share the same parameters and the pricing on this page — pick the task type you need.

How is Seedance 2.5 billed?

Billing is per second of output. The 480p and 720p tiers are shown in the pricing section on this page, synced live and below list price. Credits are managed from one Velokey account.

How does Seedance 2.5 differ from Seedance 2.0?

Single-pass duration doubles from 15 to 30 seconds with multi-round extension; reference capacity grows substantially; new clay-render (textureless 3D) control over spatial structure and camera trajectories; and timestamp-level editing is more precise, with smoother transitions, better long-video continuity, and a more natural look.

Start building with Doubao Seedance 2.5 today

Use one API key to access low-cost, stable AI models through Velokey.

Get API KeyView Docs