Pika v2.0 Turbo is a text-to-video model that supports multiple sizes and includes advanced prompt optimization for improved results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
대기 중
$0.2실행당·~50 / $10
예시전체 보기
A majestic snow leopard walks on the summit of a Himalayan peak, its fur fluttering in the harsh wind. The background features rolling snow-capped mountains and a golden sunrise. Drone long shot, photorealistic style, masterpiece, 8K UHD, cinematic lighting.
Military squad moving through abandoned warehouse, flashlight beams cutting through dust, whispered commands, cinematic realism
A woman hiding in a dimly lit apartment, heavy breathing, footsteps approaching outside, close-up on her eyes, suspense building
Intense argument between two people in a small kitchen, harsh lighting, handheld camera perspective, raw emotions
Firefighters entering a burning building, smoke everywhere, radios crackling, heat waves distorting vision, cinematic urgency
Sunlight pouring into a kitchen as someone prepares breakfast, eggs sizzling, toast popping up, morning calm
Teenagers hanging out at a convenience store at night, neon lights flickering, eating snacks, casual fun
Roommates cooking dinner together, music playing in the background, kitchen slightly messy, slice-of-life style
Young couple grocery shopping together, casual conversation, checking items off a list, supermarket ambiance
A futuristic hovercar speeds through the sky of a cyberpunk city on a rainy night. Its body glides past a massive holographic billboard, creating a ripple of digital distortion. Chase view, motion blur, neon lighting, photorealistic CG, extreme detail.
관련 모델
README
Pika V2.0 Turbo — Text-to-Video
Pika V2.0 Turbo Text-to-Video is a fast and powerful text-to-video generation model optimized for speed. Generate high-quality 720p videos from text descriptions quickly and efficiently — perfect for rapid content creation and iteration.
Why It Stands Out
- Turbo speed: Optimized for fast generation without sacrificing quality.
- HD 720p output: Generate crisp videos in landscape (1280×720) or portrait (720×1280).
- Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
- Photorealistic capability: Excellent at generating realistic, cinematic scenes.
- Flexible duration: Choose between 5 or 10 second video lengths.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video you want to generate. |
| size | No | Output resolution: 1280×720 or 720×1280 (default: 1280×720). |
| duration | No | Video length: 5 or 10 seconds (default: 5). |
How to Use
- Write a prompt describing the scene, action, and style you want. Use the Prompt Enhancer for AI-assisted optimization.
- Select size — choose landscape (1280×720) or portrait (720×1280).
- Set duration — choose 5 or 10 seconds.
- Click Run and wait for your video to generate.
- Preview and download the result.
Best Use Cases
- Nature & Wildlife — Generate stunning nature scenes and animal footage.
- Social Media Content — Create platform-optimized videos for TikTok, Reels, and Shorts.
- Marketing & Advertising — Produce promotional videos and ad creatives quickly.
- Concept Visualization — Rapidly prototype video ideas before full production.
- Cinematic Scenes — Create dramatic, movie-quality scenes from descriptions.
Pricing
| Duration | Price |
|---|---|
| 5 seconds | $0.20 |
| 10 seconds | $0.40 |
Pro Tips for Best Quality
- Be detailed in your prompt — describe subject, action, environment, lighting, and style.
- Include quality keywords like "photorealistic," "8K UHD," "cinematic lighting," "masterpiece."
- Describe camera movements like "drone long shot," "tracking shot," or "close-up."
- Choose portrait (720×1280) for mobile-first platforms like TikTok.
- Start with 5-second videos to test concepts, then extend to 10 seconds for final versions.
Notes
- Processing time is optimized for speed — expect quick turnaround.
- Please ensure your prompts comply with content guidelines.
v2.0 Turbo T2v API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pika/v2.0-turbo-t2v with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read URLs from data.outputs. Examples for v2.0 Turbo T2v below.
HTTP example
# Submit the prediction
curl --fail-with-body --connect-timeout 10 --max-time 60 \
-X POST "https://api.wavespeed.ai/api/v3/pika/v2.0-turbo-t2v" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5
}'
# Wait at least 2 seconds, then poll. Safe GET requests may be retried.
curl --fail-with-body --connect-timeout 10 --max-time 30 \
--retry 4 --retry-all-errors --retry-delay 1 \
-X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Start at 2 seconds and increase the interval for long-running tasks.
# Stop on completed, failed, cancelled, or timeout.Node.js example
// npm install wavespeed
const { Client } = require('wavespeed');
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
const client = new Client(apiKey);
try {
const result = await client.run("pika/v2.0-turbo-t2v", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5
}, {
timeout: 3600,
pollInterval: 2.0,
});
console.log(result.outputs);
} catch (error) {
console.error('Generation failed:', error);
process.exitCode = 1;
}Python example
# pip install wavespeed
import os
from wavespeed import Client
client = Client(api_key=os.environ["WAVESPEED_API_KEY"])
try:
output = client.run(
"pika/v2.0-turbo-t2v",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5
},
timeout=3600.0,
poll_interval=2.0,
)
print(output["outputs"])
except Exception as error:
raise SystemExit(f"Generation failed: {error}") from errorv2.0 Turbo T2v API — Frequently asked questions
What is the v2.0 Turbo T2v API?
v2.0 Turbo T2v is a Pika model for video generation, exposed as a REST API on WaveSpeedAI. Pika v2.0 Turbo is a text-to-video model that supports multiple sizes and includes advanced prompt optimization for improved results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the v2.0 Turbo T2v API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/pika/pika-v2.0-turbo-t2v.
How much does v2.0 Turbo T2v cost per run?
v2.0 Turbo T2v starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does v2.0 Turbo T2v accept?
Key inputs: `prompt`, `duration`, `size`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/pika/pika-v2.0-turbo-t2v.
How long does v2.0 Turbo T2v take to generate?
Average end-to-end generation time on WaveSpeedAI is around 77 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use v2.0 Turbo T2v outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Pika). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.