Wan 2.7 Text to Video
alibaba/wan/2.7/text-to-videoAlibaba Wan 2.7 text-to-video model with cinematic visuals, native audio generation, and configurable duration and resolution.
- Base price
- $0.50USD / run
- Execution
- async
- Model type
- video
- Input fields
- 6
Try the model
Playground
Examples
Select an example to load its inputs and result into the playground.
Model card
Specifications
Pricing
- Base price
- $0.50 / 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/2.7/text-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
- Text to Video
- Rank
- #14 of 33
- Elo
- 1022 ±17
- Gap to #1
- −121
Text-to-video arena (silent): people pick the better of two clips from the same prompt, without seeing the model names; audio is not judged.
- #9Gemini Omni Flash 1.11067±17
- #10Agnes-Video-2.51054±17
- #11Grok Imagine Video 1.51034±17
- #12HappyHorse-1.01032±17
- #13HappyHorse-1.11032±17
- #14Wan2.7-2606121022±17
- #15MAGI-2 Preview1008±16
- #16Kling 3.0 1080p (Pro)1000
- #17PixVerse V6993±17
- #18Kling 3.0 Omni 1080p (Pro)982±17
API README
Wan 2.7 Text to Video
Write a scene and get back a 2–15 second clip with optional driving audio. Wan 2.7 improves motion smoothness and scene fidelity over 2.6 and keeps camera instructions more faithfully.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 50,000 characters. |
duration | 2–15 | 5 | Output length in seconds. |
audio | audio URL | — | Optional WAV/MP3 URL that drives speech or rhythm in the clip. |
aspect_ratio | 16:9 / 9:16 / 1:1 / 4:3 / 3:4 | 16:9 | Output frame shape. |
resolution | 720p / 1080p | 720p | Sets the per-second rate. |
seed | integer | random | Fix it to compare prompt changes. |
Billing
You pay for output seconds: $0.10 at 720p and $0.15 at 1080p, the same as Alibaba's list price.
| Output | 720p | 1080p |
|---|---|---|
| 2s | $0.20 | $0.30 |
| 5s (default) | $0.50 | $0.75 |
| 10s | $1.00 | $1.50 |
| 15s | $1.50 | $2.25 |
Failed runs are not charged.
Prompting
- Describe the shot in order: subject, action, setting, camera move, light, and sound.
- Give camera timing explicitly, e.g. “holds for two seconds, then pushes in slowly”.
- Put spoken lines in quotes and say who speaks them.
A young woman sits by a rain-streaked café window, slowly turns toward the camera and smiles; slow push-in, warm interior light, soft rain on the glass.
Limits
- Text only; to start from your own picture use
alibaba/wan/2.7/image-to-video.
Also on SandBase
Other Wan 2.7 endpoints: alibaba/wan/2.7/image-to-video, alibaba/wan/2.7/reference-to-video, alibaba/wan/2.7/video-edit, alibaba/wan/2.7/video-extend, alibaba/wan/3.0/video (newer, up to 30s).
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.7/text-to-video",
"prompt": "A young woman sitting by a rain-streaked window in a café, slowly turning to look at the camera with a gentle smile, warm interior lighting",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9"
}
SANDBASE_JSON
)
run_id=$(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 2.7 Text to VideoThis model Alibaba | Video | $0.50 / run | Mar 28, 2026 |
Alibaba | Video | $1.40 / run | Oct 4, 2026 |
Alibaba | Video | $2.80 / run | Oct 4, 2026 |
Alibaba | Video | $1.00 / run | Oct 4, 2026 |
Alibaba | Video | $2.00 / run | Oct 4, 2026 |
Alibaba | Video | $0.70 / run | Aug 24, 2026 |
Questions
FAQ
How do I call Alibaba Wan 2.7 Text to Video through SandBase?
Create a SandBase API key, then send requests with the model ID "alibaba/wan/2.7/text-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 2.7 Text to Video and the other models in the catalog; you do not need to sign up with Alibaba separately.
