# Pika 2.5

> Video AI Model by Pika — available on Layer

Pika's highest-quality image-to-video model, generating 480p, 720p, or 1080p clips from a still frame.

Pika 2.5 is an image-to-video model from Pika that animates a still image into a dynamic clip guided by a text prompt. It supports 480p, 720p, and 1080p output at 5 or 10 seconds, with optional negative prompt and seed controls.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Pika |
| Category | Video |
| Price | 1.7 / megapixel second per megapixel_per_second |
| Aspect Ratios | 16:9, 9:16, 1:1, 4:3, 3:4 |
| Durations | 5s, 10s |

---

[Try Pika 2.5](https://next.app.layer.ai/me/session/new?baseModelId=PIKA_V2_5) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)