Wan 2.5

High-resolution video generation with prompt expansion support

Endpoints

Authentication

All requests require an API Key in the header:

Authorization: Bearer YOUR_API_KEY

Request Body

{
  "request_type": "async",
  "callback_url": "https://...",
  "provider": "auto",
  "input": {
    "mode": "text-to-video",
    "prompt": "...",
    "resolution": "1080p",
    "duration": 10,
    "aspect_ratio": "16:9",
    "image_urls": ["..."],
    "negative_prompt": "...",
    "seed": 12345,
    "enable_prompt_expansion": true
  }
}

Parameters

Mode Options:

• text-to-video — Generate video from text
• image-to-video — Generate video from image

Example

Text-to-Video

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-5" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "provider": "value",
    "input": {
      "mode": "text-to-video",
      "prompt": "a serene mountain landscape with moving clouds and gentle breeze",
      "resolution": "1080p",
      "duration": 10,
      "aspect_ratio": "16:9",
      "negative_prompt": "low quality, blurry",
      "enable_prompt_expansion": true
    }
  }'

Image-to-Video

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-5" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/callback",
    "provider": "official",
    "input": {
      "mode": "image-to-video",
      "prompt": "make this picture into a smooth cinematic shot with camera slowly zooming in",
      "resolution": "720p",
      "duration": 5,
      "image_urls": ["https://example.com/ref.jpg"],
      "enable_prompt_expansion": false,
      "seed": 42
    }
  }'

Response

POST /api/v1/generateTask/wan-2-5

Returns taskId on success for subsequent status queries.

Success:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Error:

{
  "code": 400,
  "message": "Insufficient credits",
  "data": null
}

GET /api/v1/statusTask/wan-2-5

Query task execution status and results via taskId.

curl -X GET "https://api.apixo.ai/api/v1/statusTask/wan-2-5?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Success:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://r2.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines"
  }
}

Status Response Fields

Error Codes

Rate Limits

Exceeding limits returns 429 error. Wait and retry.

Tips

• Generation time:
  • 720p resolution: ~50-70 seconds
  • 1080p resolution: ~70-90 seconds
  • Submit task, wait 50 seconds, then poll every 5 seconds
• Callback mode: Recommend using callback mode to avoid frequent polling.
• Video expiration: Result URLs are valid for 15 days. Download promptly.
• Content moderation: Prompts must comply with content safety guidelines.
• High resolution support:
  • 720p: Fast generation, for previews and social media
  • 1080p: HD output, for professional publishing and high-quality content
• Prompt expansion:
  • enable_prompt_expansion: true (default): System auto-optimizes and expands prompt with more details
  • enable_prompt_expansion: false: Strictly uses original prompt, for precise control
  • Short prompts benefit from expansion; detailed prompts can disable it
• Aspect ratio selection:
  • 16:9: Landscape (default), for traditional video platforms
  • 9:16: Portrait, for short video platforms and mobile viewing
  • 1:1: Square, for social media
• Negative prompt:
  • Use negative_prompt to avoid blur, low quality, jitter, and other unwanted effects
  • Example: "low quality, blurry, shaky, distorted"
  • Helps improve video stability and clarity
• Seed reproduction:
  • Same seed + prompt + parameters reproduces identical results
  • Ideal for consistent batch generation or iterative refinement
• Image-to-video:
  • Reference image becomes video start frame
  • Describe desired animation effects and camera movement in prompt
  • Ideal for bringing still images to life, character animation, scene expansion
• Prompt tips:
  • Describe specific scenes and actions (e.g., "clouds drifting over mountains", "slow dolly in")
  • Describe dynamic elements (e.g., "swaying leaves", "flowing water", "flying birds")
  • Describe camera movement (e.g., "slow push in", "orbiting shot", "wide to close")
  • Be specific; concrete descriptions work better than abstract ones
• Duration selection:
  • 5 seconds: Quick previews, short clips, loop animations
  • 10 seconds: More narrative space, complete scene showcases
• Image formats: image_urls supports JPG, PNG, WebP, max 10MB per image.
• Best practices:
  • Use clear, specific prompts
  • Enable prompt expansion for richer details
  • Use negative prompt to avoid common issues
  • 720p for quick iteration, 1080p for final output

Related

• Pricing
• Error Codes