Pika H3 Flex
Start creating
PIKA H3 FLEX · YOUR CREATIVE STUDIO

A little imagination.
A whole new scene.

Turn words, images and references into moving pictures with sound. Make your first scene in seconds of footage, not hours of editing.

Explore what’s possible

Text to Video

H3 FLEX

Describe a world. Watch it come to life.

Duration
Advanced settings
Generation cost24 credits
Failed generations are automatically refunded.
Ready to create
The dog and the cake
MADE WITH PIKA H3 FLEXThe dog and the cake768P · 15s · Native audio
Your next great scene starts here.
Synchronized audioUp to 4KFour ways to create

Small prompts. Big possibilities.

Explore scenes from text, images and references, including official Pika H3 Flex examples.

Explore the studio

From “what if” to “watch this.”

01

Start with a spark

Write a scene, upload keyframes, or bring a reference. Tell the model what happens and what we hear.

02

Make it your frame

Choose your duration, aspect ratio and resolution. See the credit cost before you create.

03

Play. Refine. Repeat.

Preview your scene, upgrade a draft to 4K, and download the result when it feels right.

A few things worth knowing.

What can I make with Pika H3 Flex?+

Create short scenes with synchronized audio from text, keyframe images or reference media. Use Draft to Video to upscale a completed 480p or 768p scene to 1080p, 2K or 4K.

How do credits work?+

Text and image modes cost 2 / 4 / 7 / 8 / 16 credits per second at 480p / 768p / 1080p / 2K / 4K. Prompt refinement adds 4 credits. Reference mode uses a higher rate, with a fixed 15-second input allowance when video references are included. The full price is shown before submission.

What happens if my video fails?+

A confirmed provider failure restores the credits automatically. If a request times out, it remains saved so you can refresh My videos without paying for the same job twice.

Can I use my own images and references?+

Yes. Image mode accepts a first frame, last frame or both. Reference mode accepts images, videos and audio; include at least one image or video. Only upload materials you have permission to use.

Are 2K and 4K native generations?+

480p and 768p are native resolutions. Higher resolutions use an upscale stage that preserves the scene and audio. Video duration is 5–15 seconds.