## Basic model info

- Model name: pika/pika pika-h3-flex
- Model description: Pika H3 Flex: 5–15 second videos with synchronized native audio from text, a first/last frame, or up to 12 image, video and audio references. 480p/768p native, with 1080p, 2K and 4K upscaling; draft-to-video finishes a 480p/768p draft at 1080p–4K and charges only the difference.
- Endpoint name: draft-to-video


## Model schema

The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/pika/pika-h3-flex/latest.json)

### Model input schema

The model input schema is:



```json
{
  "additionalProperties": false,
  "properties": {
    "video_url": {
      "description": "HTTP(S) URL of a source video whose measured short edge is exactly 480 or 768 pixels. Other or unmeasurable source tiers are rejected before submission because draft pricing subtracts the exact native source-tier rate. Pika accepts up to 512 MiB and 1441 frames. Use one of your prior Sunra outputs or another accessible URL.",
      "maxLength": 2083,
      "minLength": 1,
      "pattern": "^https?://",
      "title": "Video Url",
      "type": "string",
      "x-sr-order": 301
    },
    "resolution": {
      "default": "2k",
      "description": "Final resolution. Pika preserves the source take, frame rate and audio.",
      "enum": [
        "1080p",
        "2k",
        "4k"
      ],
      "title": "Resolution",
      "type": "string",
      "x-sr-order": 401
    }
  },
  "required": [
    "video_url"
  ],
  "title": "DraftToVideoInput",
  "type": "object"
}
```



### Model output schema

The model output schema is:



```json
{
  "properties": {
    "units": {
      "description": "Published rate-card amount in USD × 1000; model-data prices one unit at USD 0.001.",
      "minimum": 0,
      "title": "Units",
      "type": "number"
    },
    "video": {
      "properties": {
        "content_type": {
          "description": "The mime type of the file.",
          "title": "Content Type",
          "type": "string"
        },
        "file_name": {
          "description": "The name of the file. It will be auto-generated if not provided.",
          "title": "File Name",
          "type": "string"
        },
        "file_size": {
          "description": "The size of the file in bytes.",
          "title": "File Size",
          "type": "integer"
        },
        "url": {
          "description": "The URL where the file can be downloaded from.",
          "title": "Url",
          "type": "string"
        }
      },
      "required": [
        "content_type",
        "file_name",
        "file_size",
        "url"
      ],
      "title": "SunraFile",
      "type": "object"
    }
  },
  "required": [
    "video",
    "units"
  ],
  "title": "PikaH3FlexOutput",
  "type": "object"
}
```



## Example inputs and outputs

Use the following example inputs and outputs to understand the model.

### Input example



```json
{
  "video_url": "",
  "resolution": "2k"
}
```



### Output example



```json
{
}
```



## Model code examples

### JavaScript



```javascript
import { sunra } from "@sunra/client";

const result = await sunra.subscribe("pika/pika-h3-flex/draft-to-video", {
  input: {
  	video_url: '',
  	resolution: '2k'
  },
  logs: true,
  onQueueUpdate: (update) => {
    console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`);
  },
});
console.log(result.data);
console.log(result.requestId);
```



### Python



```python
import sunra_client

result = sunra_client.subscribe(
    "pika/pika-h3-flex/draft-to-video",
    arguments={
        "video_url": "",
        "resolution": "2k"
    },

    with_logs=True,
    on_enqueue=print,
    on_queue_update=print,
)
print(result)
```



### Java



```java
import ai.sunra.client.*;
import java.util.Map;
import com.google.gson.JsonObject;

var client = SunraClient.withEnvCredentials();

var response = client.subscribe(
    "pika/pika-h3-flex/draft-to-video",
    SubscribeOptions.<JsonObject>builder()
        .input(Map.of(
            "video_url", "",
            "resolution", "2k"))

        .resultType(JsonObject.class)
        .onQueueUpdate(update -> System.out.printf(
            "\nStatus Update: %s, Request ID: %s%n",
            update.getStatus(),
            update.getRequestId()
        ))
        .logs(true)
        .build()
);

System.out.println("Completed!");
System.out.println(response.getData());
  
```



### Kotlin



```kotlin
import ai.sunra.client.kt.*
import com.google.gson.JsonObject

val client = createSunraClient()

val response = client.subscribe<JsonObject>(
    endpointId = "pika/pika-h3-flex/draft-to-video",
    input = mapOf(
            "video_url" to "",
            "resolution" to "2k"),
    options = ai.sunra.client.kt.SubscribeOptions(logs = true),
    onUpdate = { update ->
        println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}")
    }
)

println("Completed!")
println(response.data)
  
```



### Curl



```bash

curl --request POST \
  --url https://api.sunra.ai/v1/queue/pika/pika-h3-flex/draft-to-video \
  --header "Authorization: Key $SUNRA_KEY" \
  --header "Content-Type: application/json" \
  --data '{"video_url":"","resolution":"2k"}'
    
```



## Model readme

undefined