# Google Veo 3.1 Generate Preview — Text To Video

> Try veo-3.1-generate-preview on GPT Proto. Generate high-quality 4-8s videos in 720p/1080p, text-to-video, image-to-video, and video-to-video.

## Overview

- **Endpoint**: `POST https://gptproto.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning`
- **Query endpoint**: `POST https://gptproto.com/v1beta/models/veo-3.1-generate-preview/operations/{{operation_id}}`
- **Model ID**: `veo-3.1-generate-preview`
- **Vendor**: Google
- **Scene**: `text-to-video`
- **Category**: text-to-video
- **Modalities**: input text → output video
- **Model page**: https://gptproto.com/model/google/veo-3.1-generate-preview
- **API documentation**: https://docs.gptproto.com/docs/allapi/Google/veo-3.1-generate-preview/official-format/text-to-video
- **Other scenes of this model**: `image-to-video`, `video-to-video` — same auth, different endpoint path and input schema

## Authentication

Every request needs a GPTProto API key. Create one at https://gptproto.com/dashboard/api-key, then export it:

```bash
export GPTPROTO_API_KEY="your-api-key"
```

Header: `x-goog-api-key: $GPTPROTO_API_KEY`.

## Pricing

Platform price by tier (USD, already includes the GPTProto discount):

- **Per run** — $3.2 per run

Price range: $3.2 – $3.2 per generation.

Prices may change. The model page always shows the live price: https://gptproto.com/model/google/veo-3.1-generate-preview

## API Information

The examples below use this model's official request format. Submit the first request, then poll the query endpoint until the vendor operation finishes.

### Input Schema

The accepted JSON body is the official request shape below:

**Full Example**:

```json
{
  "instances": [
    {
      "prompt": "a cat"
    }
  ]
}
```

## Usage Examples

### 1. Submit a request

```bash
curl --request POST "https://gptproto.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning" \
  --header "x-goog-api-key: $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "instances": [
      {
        "prompt": "a cat"
      }
    ]
  }'
```

```python
import os
import requests

url = "https://gptproto.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning"
headers = {
  "x-goog-api-key": os.environ["GPTPROTO_API_KEY"],
  "Content-Type": "application/json"
}
payload = {
  "instances": [
    {
      "prompt": "a cat"
    }
  ]
}

response = requests.request("POST", url, headers=headers, json=payload)
print(response.json())
```

```typescript
const response = await fetch("https://gptproto.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning", {
  method: "POST",
  headers: {
    "x-goog-api-key": process.env.GPTPROTO_API_KEY ?? "",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    instances: [
      {
        prompt: "a cat",
      },
    ],
  }),
});

const data = await response.json();
console.log(data);
```

### 2. Check status

Replace `{{operation_id}}` (or the operation name in the URL) with the value returned by the submit request, and keep polling until the operation completes.

```bash
curl --request POST "https://gptproto.com/v1beta/models/veo-3.1-generate-preview/operations/{{operation_id}}" \
  --header "x-goog-api-key: $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json"
```

```python
import os
import requests

url = "https://gptproto.com/v1beta/models/veo-3.1-generate-preview/operations/{{operation_id}}"
headers = {
  "x-goog-api-key": os.environ["GPTPROTO_API_KEY"],
  "Content-Type": "application/json"
}

response = requests.request("POST", url, headers=headers)
print(response.json())
```

```typescript
const response = await fetch("https://gptproto.com/v1beta/models/veo-3.1-generate-preview/operations/{{operation_id}}", {
  method: "POST",
  headers: {
    "x-goog-api-key": process.env.GPTPROTO_API_KEY ?? "",
    "Content-Type": "application/json",
  },
});

const data = await response.json();
console.log(data);
```

## Example Prompts

- A teenage girl sketching in a notebook at a café window, rain tapping on the glass. Lo-fi music plays faintly. She whispers: "I just want to draw forever..."
- Two best friends lying in a grassy field under the stars, pointing at constellations. One says: "Do you ever think about how big the universe is?" The other replies: "All the time... and it still amazes me."
- A man walking alone on a forest trail in autumn, leaves crunching underfoot. Birds chirp in the distance. He murmurs: "Feels good to be away from everything for a while."

## HTTP Status Codes

- `400` — malformed body, a parameter or value this model does not accept, or input blocked by the provider's content moderation
- `401` — missing or invalid API key
- `403` — insufficient credits
- `413` — request body too large
- `429` — rate limited; retry with backoff
- `500` — An internal server error occurred
- `502` — An internal server error occurred
- `504` — Gateway timeout — upstream service did not respond in time; retry later

## Additional Resources

- [Model page](https://gptproto.com/model/google/veo-3.1-generate-preview)
- [API documentation](https://docs.gptproto.com/docs/allapi/Google/veo-3.1-generate-preview/official-format/text-to-video)
- [All models](https://gptproto.com/model)
- [API keys](https://gptproto.com/dashboard/api-key)
- [Platform overview for LLMs](https://gptproto.com/llm-full.txt)
- Any other model: `https://gptproto.com/model/{vendor}/{model}/{scene}/llms.txt`