Video

Veo 3.1 Fast video

Google Veo 3.1 Fast — 8s fixed. 720p/1080p/4K. Text + image-to-video + frame.

Category: Create · veo-3-1-fast

How to use & limits

Text-to-video and image-to-video; fixed 8-second duration.
prompt: up to 1,000 characters.
image_urls: up to 3 images (JPEG/JPG/PNG/WebP, up to 10MB each).
generation_type: 'frame' (2 images — start and end) or 'reference' (3 reference images).
Resolution: 720p, 1080p or 4K; aspect ratio 16:9 or 9:16.

Capabilities

What this model supports, straight from the schema — no pricing, no infrastructure detail.

Capability	Value
`frame_mode` Frame mode	Yes
`video_edit` Video edit	—
`text_to_video` Text-to-video	Yes
`image_to_video` Image-to-video	Yes
`reference_mode` Reference mode	Yes
`max_prompt_length` Max prompt length	1000
`reference_to_video` Reference-to-video	Yes

Parameters

Fields accepted in params (or first-class, where applicable) for POST /generations.

Name	Label	Type	Required	Default	Options	Min / Max	Description
`prompt`	Prompt	textarea	Required	—	—	—	Video description, up to 1,000 characters.
`image_urls`	Image references	multi_select	Optional	—	—	— – 3	Up to 3 images (JPEG/PNG/WebP, up to 10MB). In frame mode: 1st = start frame, 2nd = end frame.
`generation_type`	Generation type	select	Optional	frame	frame · reference	—	'frame' (2 images, start/end) or 'reference' (3 reference images).
`duration`	Duration	select	Required	8	—	—	Fixed duration: 8 seconds.
`aspect_ratio`	Aspect ratio	select	Optional	16:9	16:9 · 9:16	—	Aspect ratio: 16:9 or 9:16.
`resolution`	Resolution	select	Optional	720p	720p · 1080p · 4k	—	Resolution: 720p, 1080p or 4K.

Example request

bash

curl -X POST https://caranguejo.art/api/v1/dev/generations \
  -H "Authorization: Bearer $CK" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "veo-3-1-fast",
  "prompt": "Dolphins jumping in a bright blue ocean, realistic motion.",
  "params": {
    "duration": 8,
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "generation_type": "frame"
  }
}'

javascript

const res = await fetch("https://caranguejo.art/api/v1/dev/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.CK,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "veo-3-1-fast",
    "prompt": "Dolphins jumping in a bright blue ocean, realistic motion.",
    "params": {
      "duration": 8,
      "aspect_ratio": "16:9",
      "resolution": "1080p",
      "generation_type": "frame"
    }
  }),
});
const { data } = await res.json();

Example response

json

{
  "id": "9f0c1a7e-…",
  "object": "generation",
  "model": "veo-3-1-fast",
  "type": "video",
  "status": "completed",
  "output": {
    "assets": [
      {
        "url": "https://media.caranguejo.art/outputs/example.mp4",
        "type": "video"
      }
    ]
  }
}

The job's real cost is returned as credits_charged on the completed response — check GET /balance for the account balance.

Common errors for this job type:

`insufficient_credits`	Account balance can't cover the job cost.
`content_policy_violation`	Prompt or media rejected by content policy.
`generation_timeout`	The job exceeded the maximum processing time.
`rate_limited`	Too many requests per minute.
`invalid_input`	A required parameter is missing or outside the model's schema.
`generation_failed`	Generic processing failure.