ByteDance: Seedance 1.5 Pro

Coming soonQuick Start

Seedance 1.5 Pro is ByteDance's audio-visual generation model, released 2026-03, built on a 4.5B parameter Dual-Branch Diffusion Transformer. It generates video and audio simultaneously in a single pass, avoiding the timing problems of sequential dubbing, and supports multi-language lip-sync and cinematic camera control.

This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inTextinImageoutVideo
Per second
$0.052720p
Resolution
480p · 720p · 1080p
Duration
4–12s

Capabilities

Vision

Video pricing

Billed per second of generated video. The rate depends on the output resolution, and on whether audio is generated with it.

Resolution
Per second
480pderived
$0.023
720pderived
$0.052
1080pderived
$0.117

Rows marked “derived” are billed per video token upstream; the per-second figure comes from the published token-usage formula (width × height × 24 fps ÷ 1024) at 16:9.

Duration
4–12s
Aspect ratios
1:1 · 3:4 · 9:16 · 9:21 · 4:3 · 16:9 · 21:9
Audio generation
Yes

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="bytedance/seedance-1-5-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Seedance 1.5 Pro into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free