Who created SeeDance 1 Lite?

SeeDance 1 Lite was created by Bytedance.

Is SeeDance 1 Lite multimodal?

Yes, SeeDance 1 Lite is multimodal and can accept both text and images as input.

Where can I use SeeDance 1 Lite?

SeeDance 1 Lite is available through 1 provider including Replicate.

SeeDance 1 Lite Benchmarks, Pricing & Context Window

Name: SeeDance 1 Lite
Author: Bytedance

SeeDance 1 Lite examples

Recent arena outputs from SeeDance 1 Lite, picked from the highest-ranked matchups.

SeeDance 1 Lite API

POST/v1/generations

Modelseedance-1-lite

API key●

Prompt●

First frame

Image-to-video start frame.

Negative prompt

Aspect ratio

Resolution

Duration (seconds)

Run a request to see the response

Use it in your code

OpenAI-compatible endpoint through the LLM Stats gateway.

import requests

# Create the generation. wait="auto" long-polls (up to 60s) so most short
# jobs return as "completed" in a single round-trip.
res = requests.post(
    "https://gateway.llm-stats.com/v1/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "seedance-1-lite",
        "input": {"prompt": "A timelapse of clouds moving across the sky"},
        "wait": "auto",
    },
)
job = res.json()

# If it didn't finish inside the wait window, poll the same resource.
while job["status"] in ("queued", "running"):
    res = requests.get(
        f"https://gateway.llm-stats.com/v1/generations/{job['id']}",
        params={"wait": 60},
        headers={"Authorization": "Bearer YOUR_API_KEY"},
    )
    job = res.json()

if job["status"] == "completed":
    print("video:", job["output"]["media"][0]["url"])
else:
    print("Failed:", job["error"]["message"])

Need an API key? Create one above in the playground, or read the API documentation.

SeeDance 1 Lite pricing

Providers

SeeDance 1 Lite starts at $0.0360 per second of 720p video via Replicate.

Provider	720p $/s	1080p $/s	high $/s	Latency p95 s	Input	Output
Replicate	$0.0360	$0.0720	$0.0720	—