Pika H3 Flex — Text To Video

videoproprietary

Generates 5–15 second videos with synchronized audio from text, images, and image, video or audio references. 1080p, 2K, and 4K are upscaled from 768p. This entry identifies the text-to-video API route.

Text or image to video
$0.01/USD per output second

Capabilities

Video Generation
Audio generation

Details

Model IDpika/pika-h3-flex/text-to-video
Provider Pika
Creator pika
Familypika-h3
Licenseproprietary
Statusactive
Typevideo
Input modalitiestext
Output modalitiesvideo, audio
Open weight—
Parameters—
Architecture—
Max duration15s
Max resolution4K
Resolutions480p, 768p, 1080p, 2K, 4K
FPS—
Release date—
Sourcecommunity

Endpoints

/v1/media/pika/pika-h3-flex/text-to-videoPOST
https://api.dev.pika.art/v1/media/pika/pika-h3-flex/text-to-video

Pricing

Text or image to videoUSD per output second
480p768p1080p2K4K
Output$0.01$0.02$0.035$0.04$0.08

Family Comparison: pika-h3

ModelMax durationMax resolutionResolutionsFPS
Pika H3 Flex — Image To Video15s4K480p, 768p, 1080p, 2K, 4K—
Pika H3 Flex — Reference To Video15s4K480p, 768p, 1080p, 2K, 4K—
Pika H3 Flex — Text To Video15s4K480p, 768p, 1080p, 2K, 4K—
Pika H3 Flex15s4K480p, 768p, 1080p, 2K, 4K—

API

GET/v1/models/pika/pika/pika-h3-flex/text-to-video