> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-stale2000-router-model-pages.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Veo 3.0 Generate 001 with Comfy Router

> Call veo/veo-3.0-generate-001 through Comfy Router: endpoint, request shape and the response Router returns.

Use `veo/veo-3.0-generate-001` with the Comfy Router API. Veo provides the model; Router gives it the shared authentication and request route below.

## Quick start

Create a key at [platform.comfy.org/profile/api-keys](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-3.0-generate-001`

**Endpoint:** `POST https://api.comfy.org/v2/models/veo/veo-3.0-generate-001`

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

  # Reads COMFY_API_KEY from the environment. Save this key and reuse it if you
  # retry this request after the SDK returns an error.
  idempotency_key = str(uuid.uuid4())
  with Comfy() as client:
      result = client.models.run(
          "veo/veo-3.0-generate-001",
          {
              # Request fields are the provider's own — see Input below.
          },
          idempotency_key=idempotency_key,
      )

  print(result)
  ```

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

  // Reads COMFY_API_KEY from the environment. Save this key and reuse it if you
  // retry this request after the SDK returns an error.
  const idempotencyKey = crypto.randomUUID();
  const { data } = await comfy.models.run("veo/veo-3.0-generate-001", {
    // Request fields are the provider's own — see Input below.
  }, { idempotencyKey });

  console.log(data);
  ```

  ```bash cURL theme={null}
  # Request fields are the provider's own — see Input below.
  # Run this line once. Reuse ROUTER_REQUEST_KEY if you retry the curl command.
  ROUTER_REQUEST_KEY=$(uuidgen)
  curl https://api.comfy.org/v2/models/veo/veo-3.0-generate-001 \
    -H "X-API-Key: $COMFY_API_KEY" \
    -H "Idempotency-Key: $ROUTER_REQUEST_KEY" \
    -H "Content-Type: application/json" \
    -d '{}'
  ```
</CodeGroup>

## Schema

### Input

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

<ParamField body="instances[].cameraControl" type="string">
  Camera motion type. Requires image to be provided.

  Possible values: `fixed`, `pan_left`, `pan_right`, `tilt_up`, `tilt_down`, `truck_left`, `truck_right`, `pedestal_up`, `pedestal_down`, `push_in`, `pull_out`
</ParamField>

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

<ParamField body="instances[].image.bytesBase64Encoded" type="string (byte)">
  Base64-encoded image data

  Format: `byte`
</ParamField>

<ParamField body="instances[].image.gcsUri" type="string">
  Cloud Storage URI of the image
</ParamField>

<ParamField body="instances[].image.mimeType" type="string">
  MIME type of the image (image/jpeg or image/png)

  Possible values: `image/jpeg`, `image/png`
</ParamField>

<ParamField body="instances[].lastFrame" type="object | object">
  Optional last frame image. Used with image to generate video between first and last frames. Supported by Veo 3.0+ models.
</ParamField>

<ParamField body="instances[].lastFrame.bytesBase64Encoded" type="string (byte)">
  Base64-encoded image data

  Format: `byte`
</ParamField>

<ParamField body="instances[].lastFrame.gcsUri" type="string">
  Cloud Storage URI of the image
</ParamField>

<ParamField body="instances[].lastFrame.mimeType" type="string">
  MIME type of the image (image/jpeg or image/png)

  Possible values: `image/jpeg`, `image/png`
</ParamField>

<ParamField body="instances[].mask" type="object | object">
  Optional mask for video editing. Applies to input video.
</ParamField>

<ParamField body="instances[].mask.bytesBase64Encoded" type="string (byte)">
  Base64-encoded mask bytes

  Format: `byte`
</ParamField>

<ParamField body="instances[].mask.gcsUri" type="string">
  Cloud Storage URI to mask file
</ParamField>

<ParamField body="instances[].mask.maskMode" type="string">
  How the mask is applied

  Possible values: `insert`, `remove`, `remove_static`, `outpaint`
</ParamField>

<ParamField body="instances[].mask.mimeType" type="string">
  MIME type of the mask (image/png, image/jpeg, image/webp, or video formats)
</ParamField>

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

<ParamField body="instances[].referenceImages" type="object[]">
  Optional reference images to guide video generation. Supports up to 3 asset images or 1 style image. Supported by Veo 3.1 models (preview).
</ParamField>

<ParamField body="instances[].referenceImages[].image" type="object | object" required />

<ParamField body="instances[].referenceImages[].image.bytesBase64Encoded" type="string (byte)">
  Base64-encoded image data

  Format: `byte`
</ParamField>

<ParamField body="instances[].referenceImages[].image.gcsUri" type="string">
  Cloud Storage URI of the image
</ParamField>

<ParamField body="instances[].referenceImages[].image.mimeType" type="string">
  MIME type of the image (image/jpeg or image/png)

  Possible values: `image/jpeg`, `image/png`
</ParamField>

<ParamField body="instances[].referenceImages[].referenceId" type="string">
  Optional identifier for the reference image
</ParamField>

<ParamField body="instances[].referenceImages[].referenceType" type="string" required>
  Type of reference image

  Possible values: `asset`, `style`
</ParamField>

<ParamField body="instances[].video" type="object | object">
  Optional input video for video extension or editing. Incompatible with image and referenceImages.
</ParamField>

<ParamField body="instances[].video.bytesBase64Encoded" type="string (byte)">
  Base64-encoded video bytes

  Format: `byte`
</ParamField>

<ParamField body="instances[].video.gcsUri" type="string">
  Cloud Storage URI of the input video
</ParamField>

<ParamField body="instances[].video.mimeType" type="string">
  MIME type of the video

  Possible values: `video/mov`, `video/mpeg`, `video/mp4`, `video/mpg`, `video/avi`, `video/wmv`, `video/mpegps`, `video/x-flv`
</ParamField>

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

<ParamField body="parameters.aspectRatio" type="string">
  Aspect ratio of the generated video. Default: 16:9

  Possible values: `16:9`, `9:16`
</ParamField>

<ParamField body="parameters.compressionQuality" type="string">
  Video compression quality. Default: optimized

  Possible values: `optimized`, `lossless`
</ParamField>

<ParamField body="parameters.durationSeconds" type="number">
  Target duration of the generated video in seconds. Veo 2: 5-8. Veo 3/3.1: 4, 6, or 8. Default: 8
</ParamField>

<ParamField body="parameters.enhancePrompt" type="boolean">
  Automatically improve prompt for higher quality. Defaults to true.
</ParamField>

<ParamField body="parameters.fps" type="integer">
  Frame rate of generated videos in frames per second
</ParamField>

<ParamField body="parameters.generateAudio" type="boolean">
  Whether to generate audio along with the video. Defaults to true. Supported by Veo 3.0+ models.
</ParamField>

<ParamField body="parameters.negativePrompt" type="string">
  Text describing what to avoid in the generated video
</ParamField>

<ParamField body="parameters.personGeneration" type="string">
  Controls people in generated videos. Default: allow\_adult

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

<ParamField body="parameters.pubsubTopic" type="string">
  Cloud Pub/Sub topic for progress updates (projects/\{project}/topics/\{topic})
</ParamField>

<ParamField body="parameters.resizeMode" type="string">
  Resize approach for input image. Default: pad

  Possible values: `pad`, `crop`
</ParamField>

<ParamField body="parameters.resolution" type="string">
  Output video resolution. Supported by Veo 3.0+ models. Default: 720p

  Possible values: `720p`, `1080p`, `4k`
</ParamField>

<ParamField body="parameters.sampleCount" type="integer">
  Number of videos to generate. If not specified, 1 video is generated.

  Range: `1` to `4`
</ParamField>

<ParamField body="parameters.seed" type="integer">
  Random seed for deterministic output. Different seeds used per video if sampleCount > 1.

  Format: `uint32`
</ParamField>

<ParamField body="parameters.storageUri" type="string">
  Cloud Storage URI (gs\://) for saving generated videos
</ParamField>

<ParamField body="parameters.task" type="string">
  Operation type for the video generation request

  Possible values: `textToVideo`, `imageToVideo`, `referenceToVideo`, `edit`, `extend`, `upscale`
</ParamField>

Generated from the schema Router serves at `GET /v2/models/veo/veo-3.0-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": 4,
    "generateAudio": false,
    "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

Save one `Idempotency-Key` for each call and reuse it for retries. Router can hold the connection for up to 10 minutes. The SDKs handle authentication; raw HTTP clients send the headers themselves.

Use `X-Comfy-Error-Type` to classify a failure. 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/models">
    Find models, inspect schemas, and retry safely.
  </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>