> ## 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 Veo 2.0 Generate 001 with Comfy Router

> Call veo/veo-2.0-generate-001 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `veo/veo-2.0-generate-001`, served by Comfy Router from Veo.

## 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:** `veo/veo-2.0-generate-001`

**Endpoint:** `POST https://api.comfy.org/v2/models/veo/veo-2.0-generate-001`

<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(
          "veo/veo-2.0-generate-001",
          {
              "instances": [
                  {
                      "prompt": "a single red maple leaf falling onto still water, slow motion",
                  },
              ],
              "parameters": {
                  "durationSeconds": 6,
                  "sampleCount": 1,
              },
          },
      )

  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("veo/veo-2.0-generate-001", {
    instances: [
      {
        prompt: "a single red maple leaf falling onto still water, slow motion",
      },
    ],
    parameters: {
      durationSeconds: 6,
      sampleCount: 1,
    },
  });

  console.log(data);
  ```

  ```bash cURL theme={null}
  curl https://api.comfy.org/v2/models/veo/veo-2.0-generate-001 \
    -H "X-API-Key: $COMFY_API_KEY" \
    -H "Idempotency-Key: $(uuidgen)" \
    -H "Content-Type: application/json" \
    -d "{\"instances\": [{\"prompt\":\"a single red maple leaf falling onto still water, slow motion\"}], \"parameters\": {\"durationSeconds\":6,\"sampleCount\":1}}"
  ```
</CodeGroup>

## Schema

### Input

<ParamField body="instances" type="object[]" />

<ParamField body="instances[].image" type="object">
  Optional image to guide video generation
</ParamField>

<ParamField body="instances[].image.bytesBase64Encoded" type="string (byte)">
  Format: `byte`
</ParamField>

<ParamField body="instances[].image.gcsUri" type="string" />

<ParamField body="instances[].image.mimeType" type="string" />

<ParamField body="instances[].prompt" type="string" required>
  Text description of the video
</ParamField>

<ParamField body="parameters" type="object" />

<ParamField body="parameters.aspectRatio" type="string" />

<ParamField body="parameters.durationSeconds" type="integer" />

<ParamField body="parameters.enhancePrompt" type="boolean" />

<ParamField body="parameters.negativePrompt" type="string" />

<ParamField body="parameters.personGeneration" type="string">
  Controls people in generated videos. `dont_allow`, `allow_adult` and `allowAll` are Vertex AI's own spellings and are the ones VeoGenVidRequest publishes for the same field. `ALLOW` and `BLOCK` are kept for compatibility with clients generated from this component before it was Router-authored -- see the note at the top of Veo2GenVidRequest.

  Possible values: `ALLOW`, `BLOCK`, `dont_allow`, `allow_adult`, `allowAll`
</ParamField>

<ParamField body="parameters.sampleCount" type="integer" />

<ParamField body="parameters.seed" type="integer">
  Format: `uint32`
</ParamField>

<ParamField body="parameters.storageUri" type="string">
  Optional Cloud Storage URI to upload the video
</ParamField>

Generated from the schema Router serves at `GET /v2/models/veo/veo-2.0-generate-001/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

<ResponseField name="done" type="boolean">
  Whether the operation has completed
</ResponseField>

<ResponseField name="error" type="object">
  Error details, present if the operation failed
</ResponseField>

<ResponseField name="error.code" type="integer">
  gRPC error code
</ResponseField>

<ResponseField name="error.message" type="string">
  Error message
</ResponseField>

<ResponseField name="name" type="string">
  Operation resource name
</ResponseField>

<ResponseField name="response" type="object">
  The prediction response, present when done is true
</ResponseField>

<ResponseField name="response.@type" type="string" />

<ResponseField name="response.raiMediaFilteredCount" type="integer">
  Number of videos filtered by responsible AI policies
</ResponseField>

<ResponseField name="response.raiMediaFilteredReasons" type="string[]">
  Reasons why videos were filtered by responsible AI policies
</ResponseField>

<ResponseField name="response.videos" type="object[]" />

<ResponseField name="response.videos[].bytesBase64Encoded" type="string">
  Base64-encoded video content
</ResponseField>

<ResponseField name="response.videos[].gcsUri" type="string">
  Cloud Storage URI of the generated video
</ResponseField>

<ResponseField name="response.videos[].mimeType" type="string">
  Video MIME type (video/mp4)
</ResponseField>

## Examples

### Input

```json theme={null}
{
  "instances": [
    {
      "prompt": "a single red maple leaf falling onto still water, slow motion"
    }
  ],
  "parameters": {
    "durationSeconds": 6,
    "sampleCount": 1
  }
}
```

### Output

```json theme={null}
{
  "done": true,
  "name": "projects/example-project/locations/us-central1/publishers/google/models/veo-3.1-fast-generate-001/operations/1a2b3c4d",
  "response": {
    "@type": "type.googleapis.com/cloud.ai.large_models.vision.GenerateVideoResponse",
    "raiMediaFilteredCount": 0,
    "videos": [
      {
        "gcsUri": "https://storage.googleapis.com/EXAMPLE_BUCKET/veo/USER_ID/REQUEST_ID/sample_0.mp4",
        "mimeType": "video/mp4"
      }
    ]
  }
}
```

## 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>