Veo 3.1 Lite.
Google's Veo 3.1 Lite: a prompt or a start frame to a clip with audio. No end frame. veo-3.1-lite implements video.generate on the Windpaint API and dashboard. It's a closed model run through Google Cloud Vertex AI, on purchased credits, from $0.21 per 4 second clip.
- Status
- Live
- Model id
veo-3.1-lite- Capability
video.generate- Takes
- Prompt, optional start frame
- Returns
- One clip with audio, 4 to 8 s
- Tiers
- 720p, 1080p, 4, 6, 8 s
- Runs on
- Google Cloud Vertex AI
- From
- $0.21 per 4 second clip (4.2 credits, metered)
- Credits
- Purchased only
Text or image to video, closed model.
The catalog describes it as “Veo 3.1 Lite. Text or first-frame to 24 fps video with audio, 4, 6 or 8 s.” It runs through Google Cloud Vertex AI, under Google's model id veo-3.1-lite-generate-001.
Audio is always generated.
Google's own page for the model has its full specs: Veo 3.1 Lite on Google Cloud.
What it costs.
Metered prices follow the job's actual usage, such as output size or clip length. The listed price is the estimate held when you submit, and the charge never goes over it.
| Model | Capability | Tier | Credits | USD | Billing |
|---|---|---|---|---|---|
veo-3.1-lite | video.generate | 720p, 4 s | 4.2 per 4 second clip | $0.21 | Metered |
veo-3.1-lite | video.generate | 720p, 6 s | 6.3 per 6 second clip | $0.315 | Metered |
veo-3.1-lite | video.generate | 720p, 8 s | 8.4 per 8 second clip | $0.42 | Metered |
veo-3.1-lite | video.generate | 1080p, 4 s | 6.72 per 4 second clip | $0.336 | Metered |
veo-3.1-lite | video.generate | 1080p, 6 s | 10.08 per 6 second clip | $0.504 | Metered |
veo-3.1-lite | video.generate | 1080p, 8 s | 13.44 per 8 second clip | $0.672 | Metered |
Closed models run on purchased credits only. The free signup credits work on the open-source models Windpaint serves. If your purchased balance can't cover the hold, the submit fails with 402 billing.insufficient_credits and nothing runs.
Failed and refused jobs aren't charged. Pricing covers credits and top-ups.
Request fields.
Submit to POST /v1/generation/capabilities/video.generate. Anything outside these values returns 422.
| Field | Values | Default | Notes |
|---|---|---|---|
model | veo-3.1-lite | none | Name it; another model may be the capability's default. |
prompt | string | none | Required. What happens in the clip, and how the camera moves. |
inputs.start_frame | 0 or 1 | none | The first frame. Leave it out to go from the prompt alone. |
resolution | 720p, 1080p | 720p | The clip's tier. |
duration | 4, 6, 8 | 4 | Seconds. |
aspect_ratio | 16:9, 9:16 | 16:9 | Any other ratio returns 422. |
seed | integer | random | Passed to the model. |
webhook_url | https URL | none | Signed POST when the job finishes. |
Call it.
The submit returns 202 with a request_id and a status_url. Poll it, stream it, or pass webhook_url and get a signed POST when the clip finishes.
curl -X POST https://api.windpaint.ai/v1/generation/capabilities/video.generate \ -H "Authorization: Bearer $WINDPAINT_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "veo-3.1-lite", "prompt": "a paper boat drifting down a rain-soaked street at dusk, slow push in", "resolution": "720p", "duration": 4, "aspect_ratio": "16:9" }'curl -X POST https://api.windpaint.ai/v1/generation/capabilities/video.generate \ -H "Authorization: Bearer $WINDPAINT_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "veo-3.1-lite", "prompt": "slow push in, rain falling, ripples spreading around the boat", "inputs": {"start_frame": ["8e1f2a3b-4c5d-4e6f-9a0b-1c2d3e4f5a6b"]}, "resolution": "720p", "duration": 4, "aspect_ratio": "16:9" }'Send an Idempotency-Key header so a retried submit returns the first job instead of billing a second. Each output is an asset in your project; its id can go straight into another job's inputs.
Veo 3.1 Lite limitations.
Current limits on Windpaint, from the API's catalog.
- One clip per request; num_outputs above 1 returns 422.
- Only 16:9 and 9:16. Any other aspect_ratio returns 422.
- Clips are 4, 6 or 8 seconds at 720p or 1080p, 24 fps, with audio. Other lengths or tiers return 422.
- No end frame, so no first-and-last-frame clips.
Where it runs.
veo-3.1-lite is a closed model from Google.
Windpaint runs it through Google Cloud Vertex AI. Your prompt and inputs for the job are sent to Google to make the output, and the output comes back to storage in your project. Windpaint doesn't train on your prompts, inputs or outputs.
Outputs are stored as assets in your project for your organization's retention period, 7 days by default. See Trust for moderation, data use and retention.
Questions.
How much does veo-3.1-lite cost?
4.2 credits ($0.21) for 720p 4 s; 6.3 credits ($0.315) for 720p 6 s; 8.4 credits ($0.42) for 720p 8 s; 6.72 credits ($0.336) for 1080p 4 s; 10.08 credits ($0.504) for 1080p 6 s; 13.44 credits ($0.672) for 1080p 8 s. The price is metered: it follows the job's actual usage, the listed price is the estimate held when you submit, and the charge never goes over it. One credit costs $0.05.
Can I use my free signup credits on it?
No. Veo 3.1 Lite is a closed model, so it runs on purchased credits only. The 200 signup credits work on the open-source models Windpaint serves.
Where does Veo 3.1 Lite run?
On Google Cloud Vertex AI, under Google's model id veo-3.1-lite-generate-001. Your prompt and inputs for the job are sent to Google to make the output, which comes back to your project as an asset. Windpaint doesn't train on your prompts, inputs or outputs.
Am I charged if a job fails?
No. The price is held when you submit and released in full if the job fails or the model refuses the request.
Can Veo 3.1 Lite start from an image?
Yes. Pass an image as start_frame. It takes no end frame. An output of image.generate is already an asset, so its id goes straight in.
Is Veo 3.1 Lite open source?
No. It's a closed model from Google, and Windpaint runs it through Google's own API. The open-source models Windpaint serves are z-image-turbo and flux-2-klein-4b for images, plus four audio models.