# Pika | v2.2 | Text to Video

Pika v2.2 generates high-quality videos directly from text prompts with stunning visual detail.

## API Information

- **Model Slug:** pika-v2-2-text-to-video
- **Branded URL:** https://www.eachlabs.ai/pika/pika-v2-2/pika-v2-2-text-to-video
- **Provider:** Pika
- **Category:** Text to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** 720p (default): $0.04 per second
- **Estimated Processing Time:** 100 seconds
- **Last Updated:** 2026-06-10
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pika-v2-2-text-to-video

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.2000
- **Pricing Details:** 720p (default): $0.04 per second

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| resolution eq_i "1080p" | 1080p: $0.09 per second |
| Rule 2 | 720p (default): $0.04 per second |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | - |
| seed | integer | No | - | - | The seed for the random number generator |
| negative_prompt | string | No | ugly, bad, terrible | - | A negative prompt to guide the model |
| aspect_ratio | string | No | 16:9 | 16:9,9:16,1:1,4:5,5:4,3:2,2:3 | The aspect ratio of the generated video |
| resolution | string | No | 720p | 1080p,720p | The resolution of the generated video |
| duration | integer | No | 5 | 5,10 | The duration of the generated video in seconds |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "pika-v2-2-text-to-video",
  "input": {
    "prompt": "Soft afternoon light filters through the trees as a woman with wavy auburn hair walks slowly along a sun-dappled path. The camera captures her from behind at a slight angle, revealing the curve of her shoulder and the shimmer of her hair in the light. She turns her head slightly, her face half-hidden by sunlight, as the breeze moves gently through the scene. The shot feels intimate and cinematic — a quiet moment suspended between movement and stillness."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**pika-v2.2-text-to-video — Text to Video AI Model**

Developed by Pika as part of the **pika-v2.2** family, **pika-v2.2-text-to-video** transforms detailed text prompts into high-quality, fluid videos with unprecedented text alignment and scene control, solving the challenge of imprecise AI video generation for creators and marketers. This **text-to-video AI model** excels in producing stunning visual detail directly from descriptions, enabling precise storytelling without traditional production hurdles. Pika's **pika-v2.2-text-to-video** stands out with features like Pikaframes for smoother transitions and Scene Ingredients for custom element integration, making it ideal for **Pika text-to-video** applications in social media and branding.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.