Wan 3.0 Image to Video
alibaba/wan/3.0/image-to-videoWan 3.0 by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
- Base price
- $0.42
$0.50USD / run - Execution
- async
- Model type
- video
- Input fields
- 8
Try the model
Playground
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Examples
Select an example to load its inputs and result into the playground.
Model card
Specifications
Pricing
- Base price
- $0.42 / run
Context & modalities
- Input
- Schema-defined
- Output
- video
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- Alibaba
- Model ID
- alibaba/wan/3.0/image-to-video
- Execution
- async
- Base URL
- https://api.sandbase.ai
- API
- Unified Run API
- Endpoint
- /v1/run
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Image to Video
- Rank
- #3 of 77
- Elo
- 1362 ±13
- Gap to #1
- −6
Image-to-video arena (silent): people pick the better of two clips animated from the same image, without seeing the model names; audio is not judged.
- #1Gemini Omni Flash1368±11
- #2Bach 1.0 Pro1362±11
- #3Wan 3.01362±13
- #4MiniMax H31356±11
- #5Vimoo 1.01348±14
- #6PixVerse V61339±10
- #7Dreamina Seedance 2.0 720p1339±9
- #8Grok Imagine Video 1.51331±11
- #9grok-imagine-video1328±9
- #10HappyHorse-1.11314±10
API README
Wan 3.0 Image to Video
Start a clip from your own picture. image becomes the exact first frame; add end_image and the model interpolates the motion between the two. Clips run 2–30 seconds with native audio.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
image | image URL, required | — | First frame. JPEG/PNG/BMP/WebP, 240–8000px per side, ≤20MB, no transparency. |
end_image | image URL | — | Last frame; needs image. |
duration | 2–30 or auto | 5 | auto lets the model pick the length. |
resolution | 480p / 720p / 1080p | 720p | Sets the per-second rate. |
aspect_ratio | adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | adaptive | adaptive follows the prompt and inputs. |
generate_audio | boolean | true | Native dialogue, music, and effects. Same price on or off. |
seed | integer 0–2147483647 | random | Fix it to compare prompt changes. |
Billing
You pay for output seconds only: $0.05 at 480p, $0.10 at 720p, $0.20 at 1080p. Input images, audio, and video are not metered. The frame images are free.
| Output | Billed | 480p | 720p | 1080p |
|---|---|---|---|---|
| 2s | 2s | $0.10 | $0.20 | $0.40 |
| 5s (default) | 5s | $0.25 | $0.50 | $1.00 |
| 10s | 10s | $0.50 | $1.00 | $2.00 |
| 30s | 30s | $1.50 | $3.00 | $6.00 |
With duration: "auto" the run is pre-authorized at 30 seconds, then settled on the length that was actually generated. Failed runs are not charged. Output files are copied to SandBase storage and the returned URL stays valid for 7 days; download anything you need to keep.
Prompting
- Describe what moves, not what is already visible: “she turns toward the lens as wind lifts her scarf”.
- With two frames, keep them compatible in framing and lighting, or describe the transition explicitly.
- Leave
aspect_ratioonadaptiveto keep the image's own proportions.
The subject slowly turns toward the camera as a breeze moves the fabric; subtle handheld push-in, natural daylight, no dialogue.
Limits
- Reference images, videos, and audio are not accepted here; use reference-to-video instead.
Also on SandBase
Other Wan 3.0 endpoints: alibaba/wan/3.0/video (all modes in one schema), alibaba/wan/3.0/text-to-video, alibaba/wan/3.0/reference-to-video, alibaba/wan/3.0/video-edit, alibaba/wan/3.0/video-extend.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/3.0/image-to-video",
"image": "https://static.sandbase.ai/samples/image-to-video/i2v-black-cat-sky-img0.png",
"duration": 5,
"resolution": "720p",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(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"Choose your model
Compare models
| Model | Type | Default price | Released |
|---|---|---|---|
Wan 3.0 Image to VideoThis model Alibaba | Video | $0.50 / run | Aug 24, 2026 |
Alibaba | Video | $1.40 / run | Oct 4, 2026 |
Alibaba | Video | $0.70 / run | Oct 4, 2026 |
Alibaba | Video | $1.00 / run | Oct 4, 2026 |
Alibaba | Video | $0.50 / run | Oct 4, 2026 |
Alibaba | Video | $0.70 / run | Aug 24, 2026 |
Questions
FAQ
How do I call Alibaba Wan 3.0 Image to Video through SandBase?
Create a SandBase API key, then send requests with the model ID "alibaba/wan/3.0/image-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.
Do I need a separate Alibaba account?
No. One SandBase API key and balance gives you access to Alibaba Wan 3.0 Image to Video and the other models in the catalog; you do not need to sign up with Alibaba separately.