Wan 2.7 Text to Image
alibaba/wan/2.7/text-to-imageAlibaba Wan 2.7 text-to-image model with high-quality generation and selectable aspect ratio.
- Base price
- $0.03USD / run
- Execution
- async
- Model type
- image
- Input fields
- 2
Try the model
Playground
Your output will appear here
Complete the inputs, then click Run.
Specifications
Pricing
- Base price
- $0.03 / run
- Billing formula
- 0.03
Context & modalities
- Input
- Schema-defined
- Output
- image
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-image
- Execution
- async
- API
- Unified Run API
- Endpoint
- /v1/run
API README
Wan 2.7 Text to Image
Wan 2.7 Text to Image creates a finished image from a natural-language description. The model is designed to understand detailed creative direction and translate it into a resolved visual. It works directly from text without requiring an input picture.
Prompts can describe subject, environment, composition, materials, and lighting in one brief. Chinese and English direction are supported for multilingual workflows. Seed, layout, and raster-format controls complete the request.
Highlights
- Advanced prompt understanding. The exact model page emphasizes stronger interpretation of written direction. Detailed prompts can coordinate multiple scene elements.
- Detailed visual output. Wan 2.7 is explicitly presented as producing detailed images. Fine visual attributes can be part of the brief.
- High-quality text-to-image generation. The model page positions Wan 2.7 as a high-quality image generator. Its role is producing a resolved raster visual from text.
- Faster standard-tier generation. Alibaba positions the standard Wan 2.7 image model as the faster generation option, favoring quicker text-to-image iteration within the 2.7 family.
Pricing
| Billing unit | Price |
|---|---|
| Base price per request | $0.03 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| Developing a visual concept from a detailed brief | Editing a supplied image |
| Creating product, environment, or character studies | Producing video |
| Working with Chinese or English direction | Requiring a mask-based edit |
| Preparing raster imagery in common layouts | Delivering SVG or layered files |
| Repeating a setup with a known seed | Requiring pixel-identical output across updates |
Prompt Guide
Write subject, action or state, environment, composition, material or style, then lighting and color.
Subject: [main subject]
Action/state: [what is happening]
Environment: [setting]
Composition: [camera and placement]
Material/style: [visual treatment]
Lighting/color: [light and palette]
{
"prompt": "Flowing liquid metal in iridescent blue and gold forming a Mobius strip, floating in a dark void, centered studio composition, soft caustic reflections, polished 3D render",
"aspect_ratio": "16:9"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/2.7/text-to-image |
| Required input | prompt |
| Prompt length | 1 to 10,000 characters |
| Prompt languages | Chinese and English |
| Aspect ratio | Seven presets; default 16:9 |
| Output | Image URL and content type |
| Execution | Asynchronous job |
Related
- Wan 2.7 Pro — choose the local Pro sibling for its corresponding tier.
- Wan 2.7 Image to Image — use the editing sibling when an input image must be changed.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.7/text-to-image",
"prompt": "Flowing liquid metal in iridescent blue and gold forming an impossible Möbius strip, floating in a void with soft caustic reflections, 3D render, octane, studio lighting",
"aspect_ratio": "16:9"
}
SANDBASE_JSON
)
run_id=$(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 ImageThis model Alibaba | Image | $0.03 / run | Apr 1, 2026 |
Alibaba | Image | $0.04 / run | Jul 21, 2026 |
Alibaba | Image | $0.04 / run | Jul 21, 2026 |
Alibaba | Image | $0.07 / run | Apr 1, 2026 |
Alibaba | Image | $0.03 / run | Apr 1, 2026 |
Alibaba | Image | $0.07 / run | Apr 1, 2026 |
Questions
FAQ
How do I call Wan 2.7 Text to Image through SandBase?
Create a SandBase API key, then send requests with the model ID "alibaba/wan/2.7/text-to-image" 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 Wan 2.7 Text to Image and the other models in the catalog; you do not need to sign up with Alibaba separately.