seedinteger
Random seed for more reproducible results.
Minimum: 0
Maximum: 4294967295
Veo 3.1 Fast First-Last Frame to Video
google/veo3.1/fast/first-last-frame-to-videoVeo3.1 Fast First Last Frame To Video is Google's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.
Try the model
Playground
Input
The text prompt describing the video you want to generate
PNG, JPEG, WebP, or GIF · 20 MiB maximum
First frame of the video. 720p or higher in 16:9 or 9:16 works best.
This field is required.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Last frame of the video.
This field is required.
Additional Settings More
Customize your input with more control.
Duration of the generated video in seconds. Allowed values: 4, 6, 8.
Output resolution. Allowed values: 720p, 1080p, 4k.
Output aspect ratio. Omit to match the input image. Allowed values: 16:9, 9:16.
Generate synchronized audio. Videos without audio are cheaper.
What to avoid in the video.
Random seed for more reproducible results. Range: 0 to 4294967295.
ResultIdle
Your output will appear here
Complete the inputs, then click Run.
Veo 3.1 Fast First-Last Frame to Video
Veo 3.1 Fast with first and last frame control: send a start image and an end image and Veo generates the motion between them, with native audio.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 20,000 characters. |
image | image URL, required | — | First frame. JPEG, PNG, or WebP URL. |
end_image | image URL, required | — | Last frame. JPEG, PNG, or WebP URL. |
duration | 4 / 6 / 8 | 8 | Output length in seconds. |
resolution | 720p / 1080p / 4k | 720p | Sets the per-second rate. |
aspect_ratio | 16:9 / 9:16 | — | Output frame shape. |
generate_audio | boolean | true | Native dialogue, music, and effects; turning it off lowers the rate. |
negative_prompt | string | — | What to avoid. |
seed | integer 0–4294967295 | random | Fix it to compare prompt changes. |
Billing
You pay for output seconds, Google's list price. With audio: $0.10 at 720p, $0.12 at 1080p, $0.30 at 4k. Without audio: $0.08 / $0.10 / $0.25 respectively.
| Output | 720p | 1080p | 4k |
|---|---|---|---|
| 4s with audio | $0.40 | $0.48 | $1.20 |
| 6s with audio | $0.60 | $0.72 | $1.80 |
| 8s with audio (default) | $0.80 | $0.96 | $2.40 |
| 8s without audio | $0.64 | $0.80 | $2.00 |
Failed runs are not charged.
Prompting
- Keep both frames compatible in framing and lighting, or describe the transition explicitly.
- Describe how the subject travels from the first frame to the last.
Limits
- Both frames are required.
- Use Veo 3.1 for the highest quality.
Also on SandBase
Other Veo 3.1 Fast endpoints: google/veo3.1/fast/text-to-video, google/veo3.1/fast/image-to-video, google/veo3.1/fast/reference-to-video, google/veo3.1/fast/video-extend, google/veo3.1/text-to-video, google/veo3.1/lite/text-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "google/veo3.1/fast/first-last-frame-to-video",
"prompt": "A woman looks into the camera, breathes in, then exclaims energetically, \"have you guys checked out Veo3.1 First-Last-Frame-to-Video on Fal? It's incredible!\"",
"duration": 8,
"resolution": "720p",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
imagestringrequired
First frame of the video. 720p or higher in 16:9 or 9:16 works best.
promptstringrequired
The text prompt describing the video you want to generate
durationinteger
Duration of the generated video in seconds.
Default: 8
Possible values: 4, 6, 8
end_imagestringrequired
Last frame of the video.
resolutionstring
Output resolution.
Default: "720p"
Possible values: "720p", "1080p", "4k"
aspect_ratiostring
Output aspect ratio. Omit to match the input image.
Possible values: "16:9", "9:16"
generate_audioboolean
Generate synchronized audio. Videos without audio are cheaper.
Default: true
negative_promptstring
What to avoid in the video.
{
"model": "google/veo3.1/fast/first-last-frame-to-video",
"prompt": "A woman looks into the camera, breathes in, then exclaims energetically, \"have you guys checked out Veo3.1 First-Last-Frame-to-Video on Fal? It's incredible!\"",
"duration": 8,
"resolution": "720p",
"generate_audio": true
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.