About Kie
Kie is an API that provides access to video, image, and music models from a single endpoint. It serves developers and product teams building media-enabled applications, helping them add AI-powered media features without juggling multiple providers.
Key Features
When teams evaluate media AI, they care about breadth, reliability, and a simple integration path:
Unified Media API
Access video, image, and music models through one API, reducing integration friction across media tasks.
Single authentication & Endpoints
One API key and a consistent surface to reach all model families, easing onboarding and access control.
Model versions & Config
Choose among model versions and tailor outputs with straightforward parameter controls.
Developer tooling
Practical SDKs, examples, and reference docs to accelerate integration.
Summary
Best for product and ML teams building media-rich applications, plus engineering teams prototyping video, image, or music features.
Pricing
View pricinggrok-imagine-image-2-0, text to image
$0.02 / per image
grok-imagine-image-2-0, image edit
$0.02 / per image
Gemini 3.7 Flash, chat, output
$1.125 / per million
Gemini 3.7 Flash, chat, input
$0.225 / per million
grok-4-6, Chat, Input
$0.80 / per 1M tokens
grok-4-6, Chat, Output
$2.40 / per 1M tokens
grok-4-6, Chat, Cached Input
$0.20 / per 1M tokens
bytedance/seedance-2-5, 720p with video
$0.190 / per second
bytedance/seedance-2-5, 720p no video
$0.315 / per second
bytedance/seedance-2-5, 480p with video
$0.085 / per second
bytedance/seedance-2-5, 480p no video
$0.140 / per second
Qwen image 3.0 Pro, output, 2K
$0.06 / per image
Qwen image 3.0 Pro, output, 1K
$0.032 / per image
Qwen image 3.0 Pro, input, 2K
$0.0025 / per image
Qwen image 3.0 Pro, input, 1K
$0.0025 / per image
Qwen image 3.0 Pro, text to image, 2K
$0.06 / per image
Qwen image 3.0 Pro, text to image, 1K
$0.032 / per image
Qwen image 3.0, output, 2K
$0.024 / per image
Qwen image 3.0, output, 1K
$0.024 / per image
Qwen image 3.0, input, 2K
$0.0025 / per image
Qwen image 3.0, input, 1K
$0.0025 / per image
Qwen image 3.0, text to image, 2K
$0.024 / per image
Qwen image 3.0, text to image, 1K
$0.024 / per image
MiniMax H3, video input, 768p
$0.08 / per second
MiniMax H3, reference to video, 768p
$0.08 / per second
