Pika V2.1 generates high-quality, multi-resolution videos from text prompts with prompt optimization and flexible sizes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Ocioso
$0.2por execução·~50 / $10
ExemplosVer todos
A static long shot of a young girl sitting on a bay window seat, reading a book peacefully with headphones on. It's raining outside, and raindrops streak down the glass, blurring the street view. The room is softly lit, and her profile looks serene in the soft light. Shallow depth of field, emotional, cinematic feel.
Boy staring out of a moving bus window, raindrops trailing on glass, passing buildings reflecting a muted mood
Young woman waiting at a crosswalk on a rainy afternoon, holding a transparent umbrella, traffic reflected on wet pavement
A barista preparing coffee in a cozy cafe, steam rising from the espresso machine, sunlight hitting wooden surfaces
A man walking his dog through a quiet park in the early morning, light fog, dew on the grass, slow cinematic pacing
Father helping son ride a bike for the first time in a suburban street, shaky wheels, encouragement, joy and fear
Taxi driver lighting a cigarette, dashboard lights glowing in the dark, urban landscape moving past the window
A group of teenagers playing basketball on a neighborhood court at sunset, slow-motion jump shots, laughter and sneakers squeaking
Young woman rushing through a grocery store after work, grabbing items quickly, checking phone, ambient noise of daily routine
Pedestrian crossing at a busy Tokyo intersection, umbrellas moving in sync, neon ads reflecting in puddles
Modelos relacionados
README
Pika V2.1 Text-to-Video
Create cinematic videos from pure imagination with Pika V2.1 Text-to-Video. Simply describe your scene and watch it come to life — no source images required. Pika excels at emotionally resonant, atmospheric content with natural motion and cinematic quality.
Why It Looks Great
- Pure text-to-video: Generate complete videos from descriptions alone — no images needed.
- Latest version: V2.1 delivers improved motion quality and temporal consistency.
- Emotional storytelling: Excels at moody, atmospheric, and narrative-driven content.
- 720p HD output: Sharp, professional-quality video in landscape or portrait.
- Extended duration: Generate up to 10 seconds of video.
- Prompt Enhancer: Built-in tool to refine your descriptions automatically.
- Safety Checker: Optional content filtering for appropriate output.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the scene, action, and atmosphere you want. |
| size | No | Output dimensions: 1280×720 (landscape) or 720×1280 (portrait). Default: 1280×720. |
| duration | No | Video length: 5 or 10 seconds. Default: 5. |
| Enable Safety Checker | No | Toggle content safety filtering. |
How to Use
- Write your prompt — describe the scene, characters, motion, and mood in detail.
- Use Prompt Enhancer (optional) — click to automatically enrich your description.
- Choose size — select landscape (1280×720) or portrait (720×1280).
- Set duration — choose 5 or 10 seconds.
- Run — click the button to generate.
- Download — preview and save your video.
Pricing
Per 5-second billing based on duration.
| Duration | Calculation | Cost |
|---|---|---|
| 5 seconds | 5 ÷ 5 × $0.20 | $0.20 |
| 10 seconds | 10 ÷ 5 × $0.20 | $0.40 |
Size Options
| Size | Orientation | Best For |
|---|---|---|
| 1280×720 | Landscape | YouTube, presentations, desktop viewing |
| 720×1280 | Portrait | TikTok, Instagram Reels, Stories, mobile |
Best Use Cases
- Atmospheric Scenes — Create moody, emotionally evocative video content.
- Narrative Moments — Generate story-driven scenes with emotional depth.
- Music Video Visuals — Produce dreamy, cinematic sequences for music content.
- Social Media Content — Create platform-optimized videos without source material.
- Concept Visualization — Bring ideas and stories to life from imagination.
Example Prompts
- "Boy staring out of a moving bus window, raindrops trailing on glass, passing buildings reflecting a muted mood"
- "Lonely figure walking through neon-lit city streets at night, rain falling, melancholic atmosphere"
- "Elderly couple dancing slowly in an empty ballroom, dust particles in golden light, nostalgic"
- "Cat watching fish in an aquarium, curious paw touching glass, soft ambient lighting"
- "Astronaut floating alone in space, Earth in the distance, contemplative silence"
Pro Tips for Best Results
- Pika excels at emotional, atmospheric content — lean into mood and feeling.
- Include sensory details: "raindrops trailing", "muted mood", "melancholic atmosphere".
- Describe visual metaphors: "reflecting a muted mood", "contemplative silence".
- Match orientation to platform: portrait for TikTok/Reels, landscape for YouTube.
- Start with 5-second videos to test concepts before extending to 10 seconds.
- V2.1 delivers improved temporal consistency for smoother results.
Notes
- Duration options are 5 or 10 seconds.
- Pika is known for emotionally resonant, cinematic output.
- Enable Safety Checker for content that will be publicly shared.
- V2.1 offers improved quality over previous versions.
v2.1 T2v API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pika/v2.1-t2v with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for v2.1 T2v below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/pika/v2.1-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
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("pika/v2.1-t2v", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"pika/v2.1-t2v",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5
}
)
print(output["outputs"][0]) # → URL of the generated outputv2.1 T2v API — Frequently asked questions
What is the v2.1 T2v API?
v2.1 T2v is a Pika model for video generation, exposed as a REST API on WaveSpeedAI. Pika V2.1 generates high-quality, multi-resolution videos from text prompts with prompt optimization and flexible sizes. 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 v2.1 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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/pika/pika-v2.1-t2v.
How much does v2.1 T2v cost per run?
v2.1 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 v2.1 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-v2.1-t2v.
How long does v2.1 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 v2.1 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.