# ByteDance Seedance 2.5 Flash Text to Video API

> ByteDance's Seedance 2.5 Flash text-to-video model, a faster and lower-cost tier of Seedance 2.5 that generates native single-shot clips up to 30 seconds at 480p or 720p with coherent motion, native audio, and camera control.

Source: https://www.sandbase.ai/models/bytedance/seedance/2.5/flash/text-to-video
API reference: https://www.sandbase.ai/models/bytedance/seedance/2.5/flash/text-to-video#api

## Facts

- Provider: ByteDance
- Type: Video model
- Model ID: `bytedance/seedance/2.5/flash/text-to-video`
- Price: From $1.20 per run
- Capabilities: text to video
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Unified Run API: `POST https://api.sandbase.ai/v1/run`

```bash
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance/2.5/flash/text-to-video",
  "prompt": "Photorealistic style: Under a clear blue sky, a vast expanse of white daisy fields stretches out. The camera gradually zooms in and finally fixates on a close-up of a single daisy, with several glistening dewdrops resting on its petals.",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}'
```

The response returns a run id; poll `GET https://api.sandbase.ai/v1/run/{id}` until the status is `completed` or `failed`.

## FAQ

### How do I call ByteDance Seedance 2.5 Flash Text to Video through SandBase?

Create a SandBase API key, then send requests with the model ID "bytedance/seedance/2.5/flash/text-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### Do I need a separate ByteDance account?

No. One SandBase API key and balance gives you access to ByteDance Seedance 2.5 Flash Text to Video and the other models in the catalog; you do not need to sign up with ByteDance separately.

## README

### Seedance 2.5 Flash Text to Video

Seedance 2.5 Flash text-to-video is the faster, lower-cost tier of Seedance 2.5: coherent single-shot clips up to 30 seconds with native audio and camera control, at 480p or 720p. Write the scene, including dialogue and sound, and get back a 4–30 second clip.

#### Fields

| Field | Type | Default | Notes |
|---|---|---|---|
| `prompt` | string, required | — | Up to 50,000 characters. |
| `duration` | `auto` / 4–30 | 5 | Output length in seconds (4–30), or `auto` to let the model choose. |
| `aspect_ratio` | `16:9` / `9:16` / `1:1` / `4:3` / `3:4` / `21:9` | `16:9` | Output frame shape. |
| `resolution` | `480p` / `720p` | `720p` | Sets the per-second rate. |
| `generate_audio` | boolean | true | Native dialogue, music, and effects. Same price on or off. |
| `seed` | integer -1–4294967295 | random | Fix it to compare prompt changes; `-1` is random. |

#### Billing

You pay for output seconds: $0.12 at 480p, $0.24 at 720p. Audio is included. With `duration: "auto"` the quote assumes 30 seconds and the final charge uses the generated length.

| Output | 480p | 720p |
|---|---|---|
| 4s | $0.48 | $0.96 |
| 5s (default) | $0.60 | $1.20 |
| 10s | $1.20 | $2.40 |
| 15s | $1.80 | $3.60 |
| 30s | $3.60 | $7.20 |

Failed runs are not charged.

#### Prompting

- Describe subject, action, camera move, and light in order; add the sound last.
- Quote dialogue and name the speaker.
- For several shots, number them and give each a camera direction.

#### Limits

- Clips are 4–30 seconds.
- Output is 480p or 720p. For 1080p or draft mode, use `bytedance/seedance/2.5/text-to-video`.

#### Also on SandBase

Other Seedance 2.5 endpoints and tiers: `bytedance/seedance/2.5/flash/image-to-video`, `bytedance/seedance/2.5/flash/reference-to-video`, `bytedance/seedance/2.5/text-to-video`, `bytedance/seedance/2.0/fast/text-to-video`.
