Seedance 2 Pro - Kyma API

Overview

Seedance 2 Pro generates 720p video from text prompts or input images. It produces multi-shot sequences with dynamic camera movement and includes synchronized audio in the output. On Kyma, the model runs through an OpenAI-compatible endpoint with automatic request failover. Prompt caching is supported, billing repeated prompt prefixes at this model’s cached input rate. Every response returns exact usage costs and the active model ID in the X-Kyma-Model header. The model operates at a medium speed tier and bills per second of generated video. It does not support reasoning, vision input analysis, or structured JSON outputs.

Specs

Field	Value
Model ID	`seedance-2-pro`
Best for	Action, multi-shot scenes, social with synced audio, product motion
Context window	0
Input modalities	Text, Image
Output modalities	Video, Audio
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.20
Output	$0.60

Use this when

Multi-shot scene generation — Generate video clips with multiple camera angles and dynamic movement from a single prompt.
Social video with audio — Create short-form content where video and synchronized audio are bundled in one output.
Product motion demos — Render moving product showcases from static images or descriptive text prompts.
Image-to-video conversion — Animate uploaded still images into 720p video sequences with camera motion.

Not ideal for

Do not use this model for tasks requiring text reasoning, image analysis, structured data extraction, or resolutions above 720p.

Pick something else when

You need faster turnaround for prototyping: use seedance-2-fast or veo-3-fast.
You require 1080p output resolution: use hailuo-02-1080p or veo-3.
You prioritize cinematic realism over multi-shot pacing: use kling-3-pro.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="seedance-2-pro",
    messages=[{"role": "user", "content": "..."}],
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=generate-video&tools=true&quality_tier=frontier-open"

FAQ

Can I pass an image to generate a video? Yes, provide the image via the image_url parameter to trigger image-to-video generation. How does billing work for this model? Billing is calculated per second of generated video, and repeated prompt prefixes are charged at this model’s cached input rate when caching is active. Does the output include audio? Yes, native audio is bundled with every generated video clip.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ