> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Use P Video 2 with Comfy Router

> Call pruna/p-video-2 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `pruna/p-video-2`, served by Comfy Router from Pruna.

## Quick start

Create a key in [your Comfy workspace](https://platform.comfy.org/profile/api-keys) and export it as `COMFY_API_KEY`. The Python and TypeScript snippets use the Comfy SDKs (`pip install comfy-sdk`, `npm install @comfyorg/sdk`); the cURL snippet is the same call over raw HTTP.

**Model ID:** `pruna/p-video-2`

**Endpoint:** `POST https://api.comfy.org/v2/models/pruna/p-video-2`

<CodeGroup>
  ```python Python theme={null}
  from comfy_sdk import Comfy

  # Reads COMFY_API_KEY from the environment.
  # The SDK automatically creates an idempotency key and reuses it for automatic retries.
  with Comfy() as client:
      result = client.models.run(
          "pruna/p-video-2",
          {
              "input": {
                  "aspect_ratio": "16:9",
                  "draft": False,
                  "duration": 2,
                  "fps": 24,
                  "prompt": "A single red maple leaf resting on a plain white background.",
                  "resolution": "720p",
              },
          },
      )

  print(result)
  ```

  ```typescript TypeScript theme={null}
  import { comfy } from "@comfyorg/sdk";

  // Reads COMFY_API_KEY from the environment.
  // The SDK automatically creates an idempotency key and reuses it for automatic retries.
  const { data } = await comfy.models.run("pruna/p-video-2", {
    input: {
      aspect_ratio: "16:9",
      draft: false,
      duration: 2,
      fps: 24,
      prompt: "A single red maple leaf resting on a plain white background.",
      resolution: "720p",
    },
  });

  console.log(data);
  ```

  ```bash cURL theme={null}
  curl https://api.comfy.org/v2/models/pruna/p-video-2 \
    -H "X-API-Key: $COMFY_API_KEY" \
    -H "Idempotency-Key: $(uuidgen)" \
    -H "Content-Type: application/json" \
    -d "{\"input\": {\"aspect_ratio\":\"16:9\",\"draft\":false,\"duration\":2,\"fps\":24,\"prompt\":\"A single red maple leaf resting on a plain white background.\",\"resolution\":\"720p\"}}"
  ```
</CodeGroup>

## Schema

### Input

<ParamField body="input" type="object" required>
  P-Video-2 generation parameters. The generation is billed per second of the finished video, measured from the returned file, at a rate set by `resolution` and `draft`. The safety filter is always on; a `disable_safety_filter` value in the request is ignored.
</ParamField>

<ParamField body="input.aspect_ratio" type="string" default="&#x22;16:9&#x22;">
  Aspect ratio: 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 or 1:1. Ignored when `image` is set.
</ParamField>

<ParamField body="input.audio" type="string">
  Input audio URI to condition the generation (flac, mp3 or wav). The output length follows the audio.
</ParamField>

<ParamField body="input.draft" type="boolean" default="false">
  Faster, lower-quality preview, billed at the draft rate.
</ParamField>

<ParamField body="input.duration" type="integer">
  Duration of the generated video in seconds (1-20). When omitted the model chooses the length from the prompt, up to 20 seconds. Ignored when `audio` is set.

  Range: `1` to `20`
</ParamField>

<ParamField body="input.fps" type="integer" default="24">
  Frame rate: 24 or 48.
</ParamField>

<ParamField body="input.image" type="string">
  Input image URI for image-to-video (jpg, jpeg, png or webp).
</ParamField>

<ParamField body="input.last_frame_image" type="string">
  Reference image URI for the last frame.
</ParamField>

<ParamField body="input.prompt" type="string" required>
  Text prompt for video generation.
</ParamField>

<ParamField body="input.prompt_upsampling" type="boolean" default="true">
  Rewrite the prompt before generation. Disable it when a `seed` must reproduce a result.
</ParamField>

<ParamField body="input.resolution" type="string" default="&#x22;720p&#x22;">
  Output resolution: 720p or 1080p.
</ParamField>

<ParamField body="input.save_audio" type="boolean" default="true">
  Save the video with audio.
</ParamField>

<ParamField body="input.seed" type="integer">
  Random seed for reproducible generation. Random when omitted.
</ParamField>

Generated from the schema Router serves at `GET /v2/models/pruna/p-video-2/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

<ResponseField name="error" type="string">
  Error message. Present when status is failed.
</ResponseField>

<ResponseField name="generation_url" type="string">
  URL of the finished video. Present when status is succeeded.
</ResponseField>

<ResponseField name="message" type="string">
  Human-readable progress message.
</ResponseField>

<ResponseField name="status" type="string">
  Prediction status: starting, processing, succeeded, failed or canceled.
</ResponseField>

## Examples

### Input

```json theme={null}
{
  "input": {
    "aspect_ratio": "16:9",
    "draft": false,
    "duration": 2,
    "fps": 24,
    "prompt": "A single red maple leaf resting on a plain white background.",
    "resolution": "720p"
  }
}
```

### Output

```json theme={null}
{
  "generation_url": "https://example.invalid/pruna/p-video-2/output.mp4",
  "status": "succeeded"
}
```

## Before you ship

The SDKs create an `Idempotency-Key` and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.

When a request fails, Router sends an `X-Comfy-Error-Type` response header explaining why. A `422` means Router rejected the input before calling the provider. Download generated assets promptly because [result URLs can expire](/development/comfy-router/reference#result-assets).

<CardGroup cols={3}>
  <Card title="Headers" icon="list" href="/development/comfy-router/headers">
    Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
  </Card>

  <Card title="Using the Router API" icon="code" href="/development/comfy-router/api">
    Model discovery, validation errors, retries, and billing.
  </Card>

  <Card title="Limitations" icon="triangle-exclamation" href="/development/comfy-router/limitations">
    What Router does not do today, and what to use instead.
  </Card>
</CardGroup>