Pika logo

Pika V2.2

PikaReleased Feb 12, 2025pika/pika-v2-2
CostCompare

Pika 2.2 (early 2025) is a versatile video model supporting text-to-video and image-to-video. It generates dynamic 10-second clips at 1080p with improved realism and prompt responsiveness. New features include keyframe transitions (Pikaframes) that smoothly interpolate between start/end images, and various AI-powered effects (Pikaffects, Pikadditions, etc.) for creative control. Pika 2.2 delivers cinematic motion and camera effects, though very complex prompts can still produce occasional artifacts. Overall, it represents a major upgrade with higher resolution and fluidity over Pika 2.1, aimed at content creators and social media applications.

Context
8K
Max output
4K
Input /1M
—
Output /1M
$0.21/vid
AcceptsTextImageProducesVideoTokenizer PikaTokenizerInstruct type instruct

Providers

FastRouter routes your requests to this provider. You can also bring your own key.

PA
Pollo AI
pollo
Input /1M—
Output /1M$0.21/vid
Context8K
Max output4K

Supported parameters

Request parameters you can send with this model.

Parameter
Type
Pollo AI
Core (Sampling & basic generation)
seedSeed for deterministic sampling.
number
-
Media (Generation Controls)
aspectRatioOutput image aspect ratio.
string
"16:9", "9:16", "1:1", "4:3", "3:4"
Other
image
string
-
length
number
5, 10
negativePrompt
string
-
prompt
string
-
resolution
string
"720p", "1080p"

Make your first API call

OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.

Full API docs
Replace <FASTROUTER_API_KEY> with your key · Get your key →
HTTP

Frequently asked questions

Model scores sourced from ArtificialAnalysis