Hailuo 02 (1080p)

Overview

This model generates video clips from text prompts or reference images via image_url. It operates on Kyma’s premium cost tier and is configured for 1080p resolution, prioritizing visual fidelity over speed. On Kyma, requests route through an OpenAI-compatible endpoint with automatic failover if a serving path degrades. Prompt caching is supported, billing repeated prompt prefixes at this model’s cached input rate. The exact generation cost is returned in the usage.cost field, and the X-Kyma-Model header confirms which model executed the request. The model does not support reasoning, vision analysis, or structured JSON outputs. Generation latency is classified as slow, making it unsuitable for real-time or high-throughput pipelines. It is designed for single-clip production rather than long-context or multi-step workflows.

Specs

Field	Value
Model ID	`hailuo-02-1080p`
Best for	Hero brand video, premium social campaigns, high-fidelity character motion
Context window	0
Input modalities	Text, Image
Output modalities	Video
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Slow
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.20
Output	$0.60

Use this when

Hero Brand Video — Generate high-fidelity clips for premium marketing campaigns and product showcases.
Character Motion Animation — Produce detailed, fluid character movements from static reference images or text descriptions.
Premium Social Content — Create polished, full-HD video assets tailored for high-engagement social media posts.

Not ideal for

Do not use this model for rapid prototyping, bulk clip generation, or workflows that require low-latency responses.

Pick something else when

You need faster generation at lower resolution: use hailuo-02-512p.
You need a balance of speed and quality: use seedance-2-fast.
You need slightly lower resolution with quicker turnaround: use hailuo-02-768p.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="hailuo-02-1080p",
    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 generate video from an existing image? Yes. Include an image_url in your request to run image-to-video generation. How does prompt caching affect billing? Repeated prompt prefixes are billed at this model’s cached input rate, reducing costs for iterative workflows. Is there a way to test the API before committing? Yes, signup includes a $0.50 free credit with no card required.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ