Pika modelsvideo generation api

pika/v2.2/frames

Name: Pika V2.2 Frames
Author: Pika

V2.2 Frames is Pika's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Input

Prompt(string)

Default prompt for all transitions. Individual transition prompts override this.

Image URL or upload(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

URLs of keyframe images (2-5 images) to create transitions between

Resolution(string)

The resolution of the generated video Allowed values: 720p, 1080p.

Transitions(array)

Configuration for each transition. Length must be len(image_urls) - 1. Total duration of all transitions must not exceed 25 seconds. If not provided, uses default 5-second transitions with the global prompt.

Seed(integer)

The seed for the random number generator

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDpika/v2.2/frames

Input Schema

5 parameters · 1 required · 4 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Default prompt for all transitions. Individual transition prompts override this.
`seed`	integer	Optional	The seed for the random number generator
`images`	string[]	Optional	URLs of keyframe images (2-5 images) to create transitions between
`resolution`	string	Optional	The resolution of the generated video · Options: 720p, 1080p · Default: "720p" 720p1080p
`transitions`	object[]	Optional	Configuration for each transition. Length must be len(image_urls) - 1. Total duration of all transitions must not exceed 25 seconds. If not provided, uses default 5-second transitions with the global prompt.

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "pika/v2.2/frames",
  "images": [
    "https://static.sandbase.ai/examples/pika/v2.2/frames/input_images_0.png",
    "https://static.sandbase.ai/examples/pika/v2.2/frames/input_images_1.png"
  ],
  "prompt": "smooth cinematic transition",
  "resolution": "1080p"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Pika V2.2 Frames

API README

Pika Frames

Pika Frames is the Pika route for multi-keyframe video generation, turning an ordered keyframe sequence into a production-ready result while keeping the operation distinct from neighboring endpoints. V2.2 Frames is Pika's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output. The workflow is designed for creators who need the model’s specific transformation to remain visible in the request, so the source, intended change, and finished artifact can be reviewed as one coherent creative decision.

In practical use, this route exposes seed, prompt, sync_mode, image_urls, resolution, transitions, negative_prompt, safety_tolerance to shape the exact deliverable. Those controls let a team preserve the important source constraints, state subject behavior or material treatment precisely, choose supported timing or output characteristics, and reproduce successful settings across alternate takes. The result fits an iterative pipeline: establish the core brief, compare controlled variations, then pass the selected asset into editorial, design, localization, visualization, or publishing work.

Highlights

Sequenced keyframes. Arrange multiple supplied images as visual beats and direct the transition between each adjacent pair.
Prompt-directed motion. Describe subject action and camera behavior while the route keeps the selected source workflow intact.
Short-form iteration. Produce concise clips suited to rapid creative review and alternate takes.
Delivery control. Use the route’s documented timing, resolution, seed, or transition controls to shape the final result.

Pricing

Configuration	Price
1s · 720p	`$0.20`
1s · 1080p	`$0.30`
2s · 720p	`$0.20`
2s · 1080p	`$0.30`
3s · 720p	`$0.20`
3s · 1080p	`$0.30`
4s · 720p	`$0.20`
4s · 1080p	`$0.30`
5s · 720p	`$0.20`
5s · 1080p	`$0.30`
6s · 720p	`$0.24`
6s · 1080p	`$0.36`
7s · 720p	`$0.28`
7s · 1080p	`$0.42`
8s · 720p	`$0.32`
8s · 1080p	`$0.48`
9s · 720p	`$0.36`
9s · 1080p	`$0.54`
10s · 720p	`$0.40`
10s · 1080p	`$0.60`
11s · 720p	`$0.44`
11s · 1080p	`$0.66`
12s · 720p	`$0.48`
12s · 1080p	`$0.72`
13s · 720p	`$0.52`
13s · 1080p	`$0.78`
14s · 720p	`$0.56`
14s · 1080p	`$0.84`
15s · 720p	`$0.60`
15s · 1080p	`$0.90`
16s · 720p	`$0.64`
16s · 1080p	`$0.96`
17s · 720p	`$0.68`
17s · 1080p	`$1.02`
18s · 720p	`$0.72`
18s · 1080p	`$1.08`
19s · 720p	`$0.76`
19s · 1080p	`$1.14`
20s · 720p	`$0.80`
20s · 1080p	`$1.20`
21s · 720p	`$0.84`
21s · 1080p	`$1.26`
22s · 720p	`$0.88`
22s · 1080p	`$1.32`
23s · 720p	`$0.92`
23s · 1080p	`$1.38`
24s · 720p	`$0.96`
24s · 1080p	`$1.44`
25s · 720p	`$1.00`
25s · 1080p	`$1.50`

When to Use

Scenario	Why it fits
Exact workflow fit	Choose this route when the required deliverable is multi-keyframe video generation, rather than a related route with different source media.
Directed creative iteration	Use it when subject, motion, material, speech, framing, or finish should be expressed explicitly and compared across controlled variants.
Existing-asset continuity	Use it when supplied images, video, audio, references, or styles must remain the anchor for the generated result.
Repeatable production	Use it when successful inputs need to be saved and rerun across a campaign, asset set, localization pass, or batch.
Pipeline handoff	Use it when the returned artifact will move into editorial, compositing, visualization, review, storage, or publishing.

Prompt Guide

Start with the source or subject, then describe the intended transformation, movement or behavior, camera and composition, and the desired finish. Keep media URLs reachable, use only fields documented for this exact route, and change one major control at a time when comparing results. For source-led tasks, describe what should change as well as what must remain recognizable.

{
  "prompt": "A cinematic close shot with clear subject action, camera movement, lighting, and final visual treatment.",
  "resolution": "720p"
}

Technical Specs

Property	Value
Model ID	`pika/v2.2/frames`
Execution mode	`async`
Required inputs	`prompt`
`seed`	integer
`prompt`	string
`sync_mode`	boolean; default: false
`image_urls`	array
`resolution`	string; options: 720p, 1080p; default: 720p
`transitions`	array
`negative_prompt`	string; default:
`safety_tolerance`	string; default: 6

Related Models

pika/v2.2/image-to-video
pika/v2.2/scenes
pika/v2.2/text-to-video
pika/v1.5/effects