Available nowNew

Veo 3.1 Fast: text to video

By Google

Google's Veo 3.1 Fast makes 4, 6 or 8 second clips with sound from a prompt, a first frame, or a first and a last frame, at 720p, 1080p or 4K.

Model ID
Maker
Google
Added
October 30, 2026

Model id

Use this in every request
veo-3-1-fast

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "veo-3-1-fast",
  "input": {
    "prompt": "An old fisherman mends a net on a wooden pier at sunrise. He looks up and says \"The sea is calm today\" as waves lap against the posts and gulls cry overhead."
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "veo-3-1-fast", "quote_id": "QUOTE_ID", "input": {"prompt":"An old fisherman mends a net on a wooden pier at sunrise. He looks up and says \"The sea is calm today\" as waves lap against the posts and gulls cry overhead."}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for veo-3-1-fast
NameTypeDescription
inputImagearray of image URLs
Optional. Input image for the first frame of the video.

Default: []

inputImage2array of image URLs
Optional. Last frame of the video.

Default: []

promptstring
The prompt to generate the video.
aspectRatiostring (enum)
Aspect ratio of the generated video

Default: match_input_image

One of: 16:9, 9:16, match_input_image

resolutionstring (enum)
Resolution of the generated video

Default: 720p

One of: 720p, 1080p, 4k

negativePromptstring
A text string that describes anything you want to discourage the model from generating
seedinteger
A number to make generated videos deterministic. For random result do not send.
durationSecondsstring (enum)
Duration of the generated video in seconds. When using reference images duration is set to 8 by default.

Default: 4

One of: 4, 6, 8

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt
"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

  • 4 · 720p$0.64/ video
  • 6 · 720p$0.96/ video
  • 8 · 720p$1.27/ video
  • 4 · 1080p$0.77/ video
  • 6 · 1080p$1.15/ video
  • 8 · 1080p$1.53/ video
  • 4 · 4k$1.91/ video
  • 6 · 4k$2.86/ video
  • 8 · 4k$3.81/ video

The exact charge for your input comes from a quote. How charges settle

API docs

About this model

Overview

Veo 3.1 Fast is the Fast tier of Google's Veo 3.1. It renders 4, 6 or 8 seconds at 720p, 1080p or 4K, in 16:9 or 9:16, with dialogue, sound effects and ambience made together with the picture.

Add a first frame to start from your image, and a last frame to set where the clip ends; the shape can then follow your image. A negative prompt keeps things out and a seed repeats a result.

What you can build

  • Short social clips with speech and ambient sound
  • Drafts of a scene at 720p before a 4K final
  • A move between two stills you choose
  • Vertical 9:16 clips for phone-first posts

Prompting tips

  • Write speech in quotation marks and describe the sounds around it: wind, footsteps, a distant crowd.
  • Try ideas at 720p and 4 seconds, then render the one you like longer and at a higher resolution.
  • With a first and a last frame, describe the motion that connects them rather than the images themselves.

What to check

Play with sound enabled when reviewing your result. Check the action from start to finish and confirm that any audio suits the scene before publishing.

Questions

Is the Veo 3.1 Fast API free on Raywake?
Generating with Veo 3.1 Fast uses Raywake USD balance. You can request a quote before submitting; obtaining the quote does not start a generation or charge your balance. Any free tier offered by a different service has its own terms.

Inputs

  • First frame (optional): Input image for the first frame of the video.
  • Last Frame (optional): Last frame of the video.
  • Prompt (optional): The prompt to generate the video.
  • Aspect Ratio (optional): Aspect ratio of the generated video. Options: 16:9, 9:16, Match input image.
  • Resolution (optional): Resolution of the generated video. Options: 720p, 1080p, 4k.
  • Negative Prompt (optional): A text string that describes anything you want to discourage the model from generating.
  • Seed (optional): A number to make generated videos deterministic. For random result do not send. From 0 to 4294967295.
  • Duration Seconds (optional): Duration of the generated video in seconds. When using reference images duration is set to 8 by default. Options: 4, 6, 8.

Output and limits

  • Resolutions: 720p, 1080p, 4k.
  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 4 · 720p: $0.64 / video
  • 6 · 720p: $0.96 / video
  • 8 · 720p: $1.27 / video
  • 4 · 1080p: $0.77 / video
  • 6 · 1080p: $1.15 / video
  • 8 · 1080p: $1.53 / video
  • 4 · 4k: $1.91 / video
  • 6 · 4k: $2.86 / video
  • 8 · 4k: $3.81 / video