Pika · model guide

Pika 2.5 Guide

Current Pika general text/image-to-video model. This page connects the model data to working GenVideoKit prompt, image-to-video, comparison and cost tools.

Prompting strategy

Keep prompts compact, visual and action-first. Describe one clear transformation or motion beat, camera behavior and the intended payoff. Avoid overloading the shot with too many simultaneous actions.

Capabilities

Text → videoImage → video
Reference pricing snapshot
$0.04 / second
From rate · checked 2026-09-19
Official/provider pricing source