Veo 3.1 Lite veo3-lite

video model · provider: google · typical generation time ~110s

Capabilities

Credits

Per video: 4, 6 and 8 s cost the same.

Example

curl -X POST "https://api.aiveed.io/v1/generate/video" \
  -H "X-API-Key: $AIVEED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "veo3-lite",
  "prompt": "A golden retriever puppy chasing soap bubbles in a sunlit garden, slow motion",
  "resolution": "720p",
  "duration": "4",
  "aspect_ratio": "9:16"
}'

The response is a job — poll GET /v1/jobs/{id} or use webhooks/SSE; when status is completed, result_url is the hosted output.

Good to know

• image_url and first_frame_url are aliases here — either works (first_frame_url wins if both are sent).
• last_frame_url requires a first_frame_url.
• Aspect ratios are limited to 16:9 and 9:16.
• First/last frame and reference media (reference_*_urls) are separate modes — sending both returns 422.
• Completed videos can be extended ~7s via POST /v1/extend/video.
• Prompts that are valid JSON are passed to the model as structured prompts; plain text is wrapped automatically.
• Prompt cap: 10,000 characters.

← All models