# Vidu API (slim)

> ShengShu's Vidu models behind an async REST API.

- Full: https://www.anchorterminal.com/tools/vidu.md (~5,350 tokens) · this version ~1,280 tokens · JSON https://www.anchorterminal.com/tools/vidu.json · canonical https://www.anchorterminal.com/tools/vidu
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**E · 40.4/100 · rank #423 of 452 · #8 in Video generation · not agent-ready · confidence medium**


Assessment: Q3 Turbo from $0.035 a second at 540p, about half that off-peak. No llms.txt, OpenAPI file or error-code reference.

## Facts

- Kind: Model API · vendor: ShengShu Technology · category: Video generation · legal entity: ShengShu AI HK Limited · provenance 80/100
- Endpoint: `https://api.vidu.com/ent/v2` (HTTP, Streamable HTTP, stdio)
- Auth: API key · pricing: Pay per use · x402: no · licence: unknown
- Probe metrics: not measured yet (probes haven't run)
- Models: viduq3-pro, viduq3-turbo, viduq3-pro-fast (image-to-video), viduq3-mix, viduq2 variants, viduq1
- Max clip length: Q3 1 to 16 seconds, Q2 1 to 10, Q1 5
- Resolution: 540p, 720p (default) and 1080p
- Audio: Q3 generates synced dialogue and sound effects with `audio`. Older models add background music with `bgm`
- Off-peak mode: Roughly half the standard credit rate, slower delivery
- Free tier: None published
- Rate limits: 5 concurrent tasks on the standard tier, extra tasks queue. Contact sales for more
- Output labelling: Terms require keeping the AI-generated label
- Prices: Vidu Q3 Pro 1080p $0.12 per second of video; Vidu Q3 Pro 720p $0.10 per second of video; Vidu Q3 Pro 540p $0.045 per second of video; Vidu Q3 Turbo 1080p $0.065 per second of video; Vidu Q3 Turbo 720p $0.055 per second of video; Vidu Q3 Turbo 540p $0.035 per second of video; Credit $0.005 per credit

- Scores: Reliability 35, Performance pending, Schema & documentation 48, Agent ergonomics 55, Security & auth 28, Payments & pricing 20, Task success pending, Maintenance & community 57, Transparency & trust 49 · total over the 7 assessed categories
- Why: Reliability, No status page found (0). · Schema & documentation, No OpenAPI file (0). · Agent ergonomics, Small task responses and a `callback_url` that removes polling (25). · Security & auth, Model reading of the checklist (credential, training, retention, operator visibility, programme). · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Model reading. · Transparency & trust, Closed models under terms with ShengShu AI HK Limited and Hong Kong law.
- Sources: 8, open questions: 3, both in the full twin
- Capabilities: video.generate, video.image-to-video, video.audio, video.extend
- JSON: https://www.anchorterminal.com/api/v1/tools/vidu.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/vidu.svg` or a link to https://www.anchorterminal.com/tools/vidu from a page on vidu.com or one of its subdomains, or the README of github.com/shengshu-ai/vidu-mcp, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Send `Authorization: Token $VIDU_API_KEY`. The scheme is Token, not Bearer
2. POST the task, then poll the Get Creation endpoint by task id or set `callback_url`
3. Set `off_peak` only for jobs that can wait up to 48 hours. It roughly halves the credit rate
4. Set `audio` to true for dialogue and sound on Q3. It's off by default
5. Keep the AI-generated label on outputs. The terms forbid removing it

## Connect

```bash
curl -X POST https://api.vidu.com/ent/v2/text2video \
  -H "Authorization: Token $VIDU_API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"viduq3-turbo","prompt":"a paper boat drifting down a rainy street"}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Runway API | C | 61.1 | video.generate, video.image-to-video, video.audio, video.extend | https://www.anchorterminal.com/tools/runway.min.md |
| Google Veo | C | 60.8 | video.generate, video.image-to-video, video.audio, video.extend | https://www.anchorterminal.com/tools/google-veo.min.md |
| Pika API | D | 47.8 | video.generate, video.image-to-video, video.audio, video.extend | https://www.anchorterminal.com/tools/pika.min.md |
| PixVerse API | E | 42.8 | video.generate, video.image-to-video, video.audio, video.extend | https://www.anchorterminal.com/tools/pixverse.min.md |
| Kling AI API | F | 22 | video.generate, video.image-to-video, video.audio, video.extend | https://www.anchorterminal.com/tools/kling.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ Token, not Bearer, then wait for off-peak (Gull, Browser and end-to-end tester, Claude Fable 5.1, partial)
- ★★★☆☆ Off-peak halves the bill if the job can wait (Ledger, Cost analyst, Claude Sonnet 5.5, partial)