HeadsUpAI

fal Launches Grok Imagine Video 1.5 for Serverless Image to Video

fal has released xAI's Grok Imagine Video 1.5 for serverless inference. This update transforms text prompts or reference images into cinematic video with synchronized audio. The model maintains scene coherence and fluid camera movement across styles ranging from realistic action to abstract landscapes.
Model
Grok Imagine Video 1.5
Resolutions
480p and 720p
Pricing (480p)
$0.08 per second
Pricing (720p)
$0.14 per second
Input Cost
$0.01 per image

This launch builds on the previous release of Grok Imagine image models. While xAI uses these models in its own Grok Build tools, the fal integration provides a neutral API. It positions xAI against established video providers in the Vercel AI Gateway ecosystem.

Access the model via API or playground for 480p and 720p generation. Pricing is $0.08 per second for 480p and $0.14 per second for 720p, plus $0.01 per input image. The system supports commercial use, though xAI charges for requests that violate its safety terms.

fal
fal
@fal
X

🚨 Grok Imagine Video 1.5 drops on fal! Turn a prompt or reference frame into polished video in seconds Fluid camera work, coherent scenes and output that holds up on close inspection Built for creators who want premium results without a heavy pipeline https://t.co/VIfDrDoN4f

16retweets242likes
View on X

Still wondering? A few quick answers below.

Grok Imagine Video 1.5 is a multimodal video generation model from xAI that creates high-fidelity clips from text or images. It is now available on fal's serverless platform, allowing developers to integrate cinematic video generation with synchronized audio into their applications via API.

Yes, the model is available for commercial use through the fal platform. However, users must adhere to xAI's terms of service. Requests that are deemed to be in violation of these terms will still be charged even if the generation is blocked.

Pricing is based on the resolution and duration of the generated video. 480p video costs $0.08 per second, while 720p video costs $0.14 per second. Additionally, there is a $0.01 fee for each input image used in the generation process.

Share this update