# Tencent WAND Vega Video 1.0 pro Text To Video — Atlas Cloud API

> Generates a short video from a text prompt. (Vega 1.0-pro · WAND VOD international site.)

This is the machine-readable API reference for **Tencent WAND Vega Video 1.0 pro Text To Video** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `tencent/vega-video-1.0-pro/text-to-video`
- **Built by**: TENCENT
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/tencent/vega-video-1.0-pro/text-to-video
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.064 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "tencent/vega-video-1.0-pro/text-to-video"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video tencent/vega-video-1.0-pro/text-to-video -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `tencent/vega-video-1.0-pro/text-to-video`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"tencent/vega-video-1.0-pro/text-to-video"`
  - Options: "tencent/vega-video-1.0-pro/text-to-video"

- **`prompt`** (`string`, _required_):
  Text prompt describing the video (≤7000 characters).
  - Default: `"A cat wearing a tiny astronaut helmet floats past glowing nebulae in deep space; cinematic, volumetric lighting, 8k."`

- **`duration`** (`integer`, _optional_):
  Output length in seconds, 4..15. Use -1 for smart duration (pre-charge capped at 15s, final billing based on the upstream-generated actual duration).
  - Default: `5`

- **`resolution`** (`string`, _optional_):
  Output pixel grade.
  - Default: `"480P"`
  - Options: "480P", "720P", "1080P", "2K", "4K"

- **`aspect_ratio`** (`string`, _optional_):
  Frame aspect. `adaptive` lets the upstream choose.
  - Default: `"16:9"`
  - Options: "16:9", "9:16", "1:1", "4:3", "3:4", "adaptive"

- **`generate_audio`** (`boolean`, _optional_):
  Generate a soundtrack alongside the video.
  - Default: `true`

- **`storage_mode`** (`string`, _optional_):
  VOD-side storage policy for the source clip (downstream always gets our OSS copy, so `Temporary` is the default and `Permanent` only adds upstream retention).
  - Default: `"Temporary"`
  - Options: "Permanent", "Temporary"

- **`quality_mode`** (`string`, _optional_):
  Upstream quality knob (`VideoQualityMode`). Not accepted at 480P on this model version — leave it unset there.
  - Options: "Standard", "Fast", "SuperFast"

- **`enhance_prompt`** (`boolean`, _optional_):
  Let the upstream internally expand the prompt.
  - Default: `false`

- **`moderation_mode`** (`string`, _optional_):
  Content moderation strictness.
  - Default: `"Moderation_L1"`
  - Options: "Moderation_L0", "Moderation_L1", "Moderation_L2"



**Required Parameters Example**:

```json
{
  "model": "tencent/vega-video-1.0-pro/text-to-video",
  "prompt": "A cat wearing a tiny astronaut helmet floats past glowing nebulae in deep space; cinematic, volumetric lighting, 8k."
}
```


**Full Example**:

```json
{
  "model": "tencent/vega-video-1.0-pro/text-to-video",
  "prompt": "A cat wearing a tiny astronaut helmet floats past glowing nebulae in deep space; cinematic, volumetric lighting, 8k.",
  "duration": 5,
  "resolution": "480P",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "storage_mode": "Temporary",
  "quality_mode": "Standard",
  "enhance_prompt": false,
  "moderation_mode": "Moderation_L1"
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Prediction ID.

- **`urls`** (`object`, _optional_):
  Related API endpoints.

- **`model`** (`string`, _optional_):
  Model ID.

- **`status`** (`string`, _optional_):
  created | processing | completed | failed.

- **`outputs`** (`array[string]`, _optional_):
  Output URLs (empty when not completed).

- **`created_at`** (`string`, _optional_):
  ISO timestamp.

- **`usage`** (`object`, _optional_):
  Upstream usage details (VL token counts).



**Example Response**:

```json
{
  "id": "",
  "urls": {},
  "model": "",
  "status": "",
  "outputs": [
    ""
  ],
  "created_at": "",
  "usage": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tencent/vega-video-1.0-pro/text-to-video",
  "prompt": "A cat wearing a tiny astronaut helmet floats past glowing nebulae in deep space; cinematic, volumetric lighting, 8k.",
  "duration": 5,
  "resolution": "480P",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "storage_mode": "Temporary",
  "quality_mode": "Standard",
  "enhance_prompt": false,
  "moderation_mode": "Moderation_L1"
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/tencent/vega-video-1.0-pro/text-to-video)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Tencent WAND Vega Video 1.0-pro · Text To Video

Asynchronous text to video on top of Tencent Cloud VOD's WAND Vega 1.0-pro model. Upstream ModelName `wand-vega-video`, ModelVersion `1.0-pro`.

#### Usage
Supply only `prompt`. `duration` defaults to 5 and must be 4..15; use -1 for smart duration (pre-charge capped at 30s, final settlement on actual clip length).

#### Media Limits
- Pro-family limits not published by the upstream; enforced there.
- `generate_mode` is not accepted on this model version. `quality_mode` is accepted from 720P upwards only — at 480P every value is rejected, so leave it unset there.

#### Billing
- USD prices — see `script/sql/20261102/vega/02_model.sql`.

#### Output
Completed outputs are transferred to AtlasCloud's own OSS bucket, so returned URLs remain valid past the Tencent 7-day Temporary-VOD window.

#### Compliance
Real-person inputs require Tencent asset IDs with upstream Liveness verification. This model is exposed for non-real-person references only.

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/tencent/vega-video-1.0-pro/text-to-video · Docs: https://www.atlascloud.ai/docs